Search

The increasing size of deep learning models has created the need for more efficient alternatives to the standard error backpropagation algorithm, that make better use of asynchronous, parallel and distributed computing. One major shortcoming of backpropagation is the interlocking between the forward phase of the algorithm, which computes a global loss, and the backward phase where the loss is backpropagated through all layers to compute the gradients, which are used to update the network parameters. To address this problem, we propose a method that parallelises SGD updates across the layers of a model by asynchronously updating them from multiple threads. Furthermore, since we observe that the forward pass is often much faster than the backward pass, we use separate threads for the forward and backward pass calculations, which allows us to use a higher ratio of forward to backward threads than the usual 1:1 ratio, reducing the overall staleness of the parameters. Thus, our approach performs asynchronous stochastic gradient descent using separate threads for the loss (forward) and gradient (backward) computations and performs layer-wise partial updates to parameters in a distributed way. We show that this approach yields close to state-of-the-art results while running up to 2.97x faster than Hogwild! scaled on multiple devices (Locally-Partitioned-Asynchronous-Parallel SGD). We theoretically prove the convergence of the algorithm using a novel theoretical framework based on stochastic differential equations and the drift diffusion process, by modeling the asynchronous parameter updates as a stochastic process., Comment: 16 pages, 4 figures

In recent years, there has been significant effort to align large language models with human preferences. This work focuses on developing a chatbot specialized in the real estate domain, with an emphasis on incorporating compliant behavior to ensure it can be used without perpetuating discriminatory practices like steering and redlining, which have historically plagued the real estate industry in the United States. Building on prior work, we present a method for generating a synthetic general instruction-following dataset, along with safety data. Through extensive evaluations and benchmarks, we fine-tuned a llama-3-8B-instruct model and demonstrated that we can enhance it's performance significantly to match huge closed-source models like GPT-4o while making it safer and more compliant. We open-source the model, data and code to support further development and research in the community.

India's urbanization is often characterized as particularly challenging and very unequal but systematic empirical analyses, comparable to other nations, have largely been lacking. Here, we characterize India's economic and human development along with changes in its personal income distribution as a function of the nation's growing urbanization. On aggregate, we find that India outperforms most other nations in the growth of various indicators of development with urbanization, including income and human development. These results are due in part to India's present low levels of urbanization but also demonstrate the transformational role of its cities in driving multi-dimensional development. To test these changes at the more local level, we study the income distributions of large Indian cities to find evidence for high positive growth in the lowest decile (poorest) of the population, enabling sharp reductions in poverty over time. We also test the hypothesis that inequality-reducing cities are more attractive destinations for rural migrants. Finally, we use income distributions to characterize changes in poverty rates directly. This shows much lower levels of poverty in urban India and especially in its largest cities. The dynamics of poverty rates during the recent COVID-19 pandemic shows both a high fragility of these improvements during a crisis and their resilience over longer times. Sustaining a long-term dynamic where urbanization continues to be closely associated with human development and poverty reduction is likely India's fastest path to a more prosperous and equitable future.

Combining Atacama Large Millimeter/sub-millimeter Array CO(2-1) mapping and JWST near- and mid-infrared imaging, we characterize the relationship between CO(2-1) and polycyclic aromatic hydrocarbon (PAH) emission at ~100 pc resolution in 66 nearby star-forming galaxies, expanding the sample size from previous ~100 pc resolution studies by more than an order of magnitude. Focusing on regions of galaxies where most of the gas is likely to be molecular, we find strong correlations between CO(2-1) and 3.3 micron, 7.7 micron, and 11.3 micron PAH emission, estimated from JWST's F335M, F770W, and F1130W filters. We derive power law relations between CO(2-1) and PAH emission, which have indices in the range 0.8-1.2, implying relatively weak variations in the observed CO-to-PAH ratios across the regions that we study. We find that CO-to-PAH ratios and scaling relationships near HII regions are similar to those in diffuse sight lines. The main difference between the two types of regions is that sight lines near HII regions show higher intensities in all tracers. Galaxy centers, on the other hand, show higher overall intensities and enhanced CO-to-PAH ratios compared to galaxy disks. Individual galaxies show 0.19 dex scatter in the normalization of CO at fixed I_PAH and this normalization anti-correlates with specific star formation rate (SFR/M*) and correlates with stellar mass. We provide a prescription that accounts for these galaxy-to-galaxy variations and represents our best current empirical predictor to estimate CO(2-1) intensity from PAH emission, which allows one to take advantage of JWST's excellent sensitivity and resolution to trace cold gas., Comment: 21 pages, 4 figures, 3 tables. Submitted to ApJ

The motion of several plates in an inviscid and incompressible fluid is studied numerically using a vortex sheet model. Two to four plates are initially placed in-line, separated by a specified distance, and actuated in the vertical direction with a prescribed oscillatory heaving motion. The vertical motion induces the plates' horizontal acceleration due to their self-induced thrust and fluid drag forces. In certain parameter regimes, the plates adopt equilibrium "schooling modes," wherein they translate at a steady horizontal velocity while maintaining a constant separation distance between them. The separation distances are found to be quantized on the flapping wavelength. As either the number of plates increases or the oscillation amplitude decreases, the schooling modes destabilize via oscillations that propagate downstream from the leader and cause collisions between the plates, an instability that is similar to that observed in recent experiments on flapping wings in a water tank (Newbolt et al., 2024). A simple control mechanism is implemented, wherein each plate accelerates or decelerates according to its velocity relative to the plate directly ahead by modulating its own flapping amplitude. This mechanism is shown to successfully stabilize the schooling modes, with remarkable impact on the regularity of the vortex pattern in the wake. Several phenomena observed in the simulations are obtained by a reduced model based on linear thin-airfoil theory.

Existing unsupervised keypoint detection methods apply artificial deformations to images such as masking a significant portion of images and using reconstruction of original image as a learning objective to detect keypoints. However, this approach lacks depth information in the image and often detects keypoints on the background. To address this, we propose Distill-DKP, a novel cross-modal knowledge distillation framework that leverages depth maps and RGB images for keypoint detection in a self-supervised setting. During training, Distill-DKP extracts embedding-level knowledge from a depth-based teacher model to guide an image-based student model with inference restricted to the student. Experiments show that Distill-DKP significantly outperforms previous unsupervised methods by reducing mean L2 error by 47.15% on Human3.6M, mean average error by 5.67% on Taichi, and improving keypoints accuracy by 1.3% on DeepFashion dataset. Detailed ablation studies demonstrate the sensitivity of knowledge distillation across different layers of the network. Project Page: https://23wm13.github.io/distill-dkp/

In various applications, the multivariate time series often suffers from missing data. This issue can significantly disrupt systems that rely on the data. Spatial and temporal dependencies can be leveraged to impute the missing samples. Existing imputation methods often ignore dynamic changes in spatial dependencies. We propose a Spatial Dynamic Aware Graph Recurrent Imputation Network (SDA-GRIN) which is capable of capturing dynamic changes in spatial dependencies.SDA-GRIN leverages a multi-head attention mechanism to adapt graph structures with time. SDA-GRIN models multivariate time series as a sequence of temporal graphs and uses a recurrent message-passing architecture for imputation. We evaluate SDA-GRIN on four real-world datasets: SDA-GRIN improves MSE by 9.51% for the AQI and 9.40% for AQI-36. On the PEMS-BAY dataset, it achieves a 1.94% improvement in MSE. Detailed ablation study demonstrates the effect of window sizes and missing data on the performance of the method. Project page:https://ameskandari.github.io/sda-grin/

A wide family of two dimensional (2D) systems, including stripe-phase superconductors, sliding Luttinger liquids, and anisotropic 2D materials, can be modeled by an array of coupled one-dimensional (1D) electron channels or nanowire arrays. Here we report experiments in arrays of conducting nanowires with gate and field tunable interwire coupling, that are programmed at the LaAlO$_3$/SrTiO$_3$ interface. We find a magnetically-tuned metal-to-insulator transition in which the transverse resistance of the nanowire array increases by up to four orders of magnitude. To explain this behavior, we develop a minimal model of a coupled two-wire system which agrees well with observed phenomena. These nanowire arrays can serve as a model systems to understand the origin of exotic behavior in correlated materials via analog quantum simulation.

Coupled quasi-one-dimensional (quasi-1D) electron systems host rich emergent physics that cannot be accounted for by understanding isolated 1D electron systems alone. Open questions remain about how transport in these arrays can be manipulated by the application of external electric and magnetic fields. In this theoretical study, we consider a pair of coupled nanowires with non-interacting electrons. We find that a metal-insulator transition is induced by an out-of-plane magnetic field and a transverse potential bias on an array of such coupled wires. We demonstrate the existence of distinct conductance features and highlight the crucial role played by the field dependence of the interwire potential barrier on transport properties. These predictions agree well with transport experiments performed on coupled nanowires sketched on an LaAlO3/SrTiO3 interface. Since our model makes minimal assumptions, we expect our predictions to hold for a wide class of coupled 1D systems.

Current galaxy formation simulations often approximate star-formation, necessitating models of star-forming regions to produce observables. In the first paper of the series, we introduced TODDLERS, a time-resolved model of UV-mm emission from star-forming regions implemented in the radiative transfer code SKIRT. This work uses SKIRT-TODDLERS to produce synthetic observations, demonstrating its potential through observables related to star-formation and comparing results with existing models in SKIRT. We calculate broadband and line emission maps for 30 Milky Way-like galaxies from the Auriga simulation at z=0. Analyzing FUV and IR data, we calculate kpc-resolved IR correction factors (k_IR), quantifying the ratio of FUV luminosity absorbed by dust to reprocessed IR luminosity. We use IR maps to calculate kpc-scale MIR (8 micron / 24 micron) and FIR (70 micron / 500 micron) colors. H alpha and H beta line maps are used to study the Balmer decrement and dust correction. We also verify the fidelity of our model FIR fine structure lines as SFR indicators. We find that the Auriga integrated UV-mm SEDs show higher FUV/NUV attenuation and lower 24 micron emission when using TODDLERS instead of the existing models in SKIRT, alleviating tensions with observations. The light-weighted mean k_IR increases with aperture and inclination, while its correlation with kpc-resolved sSFR is weaker than literature values. Kpc-scale MIR-FIR colors agree excellently with local observations, with anti-correlation degree varying by galaxy morphology. The Balmer decrement effectively corrects for dust, with attenuation law varying with dust amount. H alpha emission attenuation levels are comparable to high-density regions in state-of-the-art simulations. FIR fine-structure line emission-based luminosity-SFR relations align with global observations, [CII] showing best agreement., Comment: 22 pages, 20 figures. Accepted for publication in Astronomy and Astrophysics on October 21, 2024

This expository article makes a connection between Euler's homogeneous function theorem and a Lagrange integral for a simplified version of the Clairaut Equation. After describing both solutions in detail, we prove a new result, that the Lagrange solution is strictly more general than Euler's solution. This is shown using a few examples which substitute Euler's homogeneous function with a more general surface. The first rather complicated example is based directly on Goursat's definition of a general integral, while the subsequent simpler examples are based on a suitably expanded notion of the general integral. These new examples, and the expanded notion of the general integral may be of interest. We aim to present these classical PDE concepts to readers with a basic knowledge of multivariable calculus., Comment: 14 pages, 7 figures

As information retrieval systems continue to evolve, accurate evaluation and benchmarking of these systems become pivotal. Web search datasets, such as MS MARCO, primarily provide short keyword queries without accompanying intent or descriptions, posing a challenge in comprehending the underlying information need. This paper proposes an approach to augmenting such datasets to annotate informative query descriptions, with a focus on two prominent benchmark datasets: TREC-DL-21 and TREC-DL-22. Our methodology involves utilizing state-of-the-art LLMs to analyze and comprehend the implicit intent within individual queries from benchmark datasets. By extracting key semantic elements, we construct detailed and contextually rich descriptions for these queries. To validate the generated query descriptions, we employ crowdsourcing as a reliable means of obtaining diverse human perspectives on the accuracy and informativeness of the descriptions. This information can be used as an evaluation set for tasks such as ranking, query rewriting, or others.

We identify certain gaps in the literature on the approximability of stationary random variables using the Autoregressive Moving Average (ARMA) model. To quantify approximability, we propose that an ARMA model be viewed as an approximation of a stationary random variable. We map these stationary random variables to Hardy space functions, and formulate a new function approximation problem that corresponds to random variable approximation, and thus to ARMA. Based on this Hardy space formulation we identify a class of stationary processes where approximation guarantees are feasible. We also identify an idealized stationary random process for which we conjecture that a good ARMA approximation is not possible. Next, we provide a constructive proof that Pad\'e approximations do not always correspond to the best ARMA approximation. Finally, we note that the spectral methods adopted in this paper can be seen as a generalization of unit root methods for stationary processes even when an ARMA model is not defined., Comment: 10 pages, 3 figures

Fast Radio Bursts (FRBs) are millisecond-duration events detected from beyond the Milky Way. FRB emission characteristics favor highly magnetized neutron stars, or magnetars, as the sources, as evidenced by FRB-like bursts from a galactic magnetar, and the star-forming nature of FRB host galaxies. However, the processes that produce FRB sources remain unknown. Although galactic magnetars are often linked to core-collapse supernovae (CCSNe), it's uncertain what determines which supernovae result in magnetars. The galactic environments of FRB sources can be harnessed to probe their progenitors. Here, we present the stellar population properties of 30 FRB host galaxies discovered by the Deep Synoptic Array. Our analysis shows a significant deficit of low-mass FRB hosts compared to the occurrence of star-formation in the universe, implying that FRBs are a biased tracer of star-formation, preferentially selecting massive star-forming galaxies. This bias may be driven by galaxy metallicity, which is positively correlated with stellar mass. Metal-rich environments may favor the formation of magnetar progenitors through stellar mergers, as higher metallicity stars are less compact and more likely to fill their Roche lobes, leading to unstable mass transfer. Although massive stars do not have convective interiors to generate strong magnetic fields by dynamo, merger remnants are thought to have the requisite internal magnetic-field strengths to result in magnetars. The preferential occurrence of FRBs in massive star-forming galaxies suggests that CCSN of merger remnants preferentially forms magnetars., Comment: Accepted for publication in Nature. The final version will be published by the journal

Machine learning models implemented in hardware on physical devices may be deployed for a long time. The computational abilities of the device may be limited and become outdated with respect to newer improvements. Because of the size of ML models, offloading some computation (e.g. to an edge cloud) can help such legacy devices. We cast this problem in the framework of learning with abstention (LWA) in which the expert (edge) must be trained to assist the client (device). Prior work on LWA trains the client assuming the edge is either an oracle or a human expert. In this work, we formalize the reverse problem of training the expert for a fixed (legacy) client. As in LWA, the client uses a rejection rule to decide when to offload inference to the expert (at a cost). We find the Bayes-optimal rule, prove a generalization bound, and find a consistent surrogate loss function. Empirical results show that our framework outperforms confidence-based rejection rules., Comment: 12 pages, 4 figures

Peer-to-peer learning is an increasingly popular framework that enables beyond-5G distributed edge devices to collaboratively train deep neural networks in a privacy-preserving manner without the aid of a central server. Neural network training algorithms for emerging environments, e.g., smart cities, have many design considerations that are difficult to tune in deployment settings -- such as neural network architectures and hyperparameters. This presents a critical need for characterizing the training dynamics of distributed optimization algorithms used to train highly nonconvex neural networks in peer-to-peer learning environments. In this work, we provide an explicit, non-asymptotic characterization of the learning dynamics of wide neural networks trained using popular distributed gradient descent (DGD) algorithms. Our results leverage both recent advancements in neural tangent kernel (NTK) theory and extensive previous work on distributed learning and consensus. We validate our analytical results by accurately predicting the parameter and error dynamics of wide neural networks trained for classification tasks.

Efficient network management in optical backbone networks is crucial for handling continuous traffic growth. In this work, we address the challenges of managing dynamic traffic in C- and C+L-band optical backbone networks while exploring application flexibility, namely the compressibility and delayability metrics. We propose a strategy, named Delay-Aware and Compression-Aware (DACA) provisioning algorithm, which reduces blocking probability, thereby increasing information-carrying capacity of the network compared to baseline strategies.

The Dark Energy Spectroscopic Instrument (DESI) collaboration measured a tight relation between the Hubble constant ($H_0$) and the distance to the Coma cluster using the fundamental plane (FP) relation of the deepest, most homogeneous sample of early-type galaxies. To determine $H_0$, we measure the distance to Coma by several independent routes each with its own geometric reference. We measure the most precise distance to Coma from 12 Type Ia Supernovae (SNe Ia) in the cluster with mean standardized brightness of $m_B^0=15.712\pm0.041$ mag. Calibrating the absolute magnitude of SNe Ia with the HST distance ladder yields $D_{\textrm Coma}=98.5\pm2.2$ Mpc, consistent with its canonical value of 95--100 Mpc. This distance results in $H_0=76.5 \pm 2.2$ km/s/Mpc from the DESI FP relation. Inverting the DESI relation by calibrating it instead to the Planck+$\Lambda$CDM value of $H_0=67.4$ km/s/Mpc implies a much greater distance to Coma, $D_{\textrm Coma}=111.8\pm1.8$ Mpc, $4.6\sigma$ beyond a joint, direct measure. Independent of SNe Ia, the HST Key Project FP relation as calibrated by Cepheids, Tip of the Red Giant Branch from JWST, or HST NIR surface brightness fluctuations all yield $D_{\textrm Coma}<$ 100 Mpc, in joint tension themselves with the Planck-calibrated route at $>3\sigma$. From a broad array of distance estimates compiled back to 1990, it is hard to see how Coma could be located as far as the Planck+$\Lambda$CDM expectation of $>$110 Mpc. By extending the Hubble diagram to Coma, a well-studied location in our own backyard whose distance was in good accord well before the Hubble Tension, DESI indicates a more pervasive conflict between our knowledge of local distances and cosmological expectations. We expect future programs to refine the distance to Coma and nearer clusters to help illuminate this new, local window on the Hubble Tension., Comment: v2 - team name fixed

The Laser Interferometer Space Antenna (LISA) will be capable of detecting gravitational waves (GWs) in the milli-Hertz band. Among various sources, LISA will detect the coalescence of supermassive black hole binaries (SMBHBs). Accurate and rapid inference of parameters for such sources will be important for potential electromagnetic follow-up efforts. Rapid Bayesian inference with LISA includes additional complexities as compared to current generation terrestrial detectors in terms of time and frequency dependent antenna response functions. In this work, we extend a recently developed, computationally efficient technique that uses meshfree interpolation methods to accelerate Bayesian reconstruction of compact binaries. Originally developed for second-generation terrestrial detectors, this technique is now adapted for LISA parameter estimation. Using the full inspiral, merger, and ringdown waveform (PhenomD) and assuming rigid adiabatic antenna response function, we show faithful inference of SMBHB parameters from GW signals embedded in stationary, Gaussian instrumental noise. We discuss the computational cost and performance of the meshfree approximation method in estimating the GW source parameters., Comment: 18 pages, 6 figure

Many biological microorganisms and artificial microswimmers react to external cues of environmental gradients by changing their swimming directions. We study here the behavior of eukarytic flagellated microswimmers in linear viscosity gradients. We employ a model of flagellum consisting of a semi-flexible filament with a travelling wave of spontaneous curvature to study viscotaxis of actively beating flagella in two spatial dimensions. The propulsion of the flagellum in a fluid due to a hydrodynamic friction anisotropy is described by resistive-force theory. Using numerical simulations and analytical theory, we show that beating flagella exhibit positive viscotaxis, reorienting themselves toward higher viscosity areas. We quantify this behavior by characterization of the dependence of the rotational velocity on beat amplitude, swimming speed, and wave length. We also examining the effects of asymmetric flagellar wave forms, which imply circular trajectories in the absence of viscosity gradients; here, large asymmetry leads to trochoid-like trajectories perpendicular to the gradient in the form drifting circles. The flagellar deformability strongly reduce the beat amplitude and the viscotatic response. The viscotatic response is shown to be captured by a universal function of the sperm number., Comment: 15 figures

We consider the problem of estimation from survey data gathered from strategic and boundedly-rational agents with heterogeneous objectives and available information. Particularly, we consider a setting where there are three different types of survey responders with varying levels of available information, strategicness, and cognitive hierarchy: i) a non-strategic agent with an honest response, ii) a strategic agent that believes everyone else is a non-strategic agent and that the decoder also believes the same, hence assumes a naive estimator, i.e., level-1 in cognitive hierarchy, iii) and strategic agent that believes the population is Poisson distributed over the previous types, and that the decoder believes the same. We model each of these scenarios as a strategic classification of a 2-dimensional source (possibly correlated source and bias components) with quadratic distortion measures and provide a design algorithm. Finally, we provide our numerical results and the code to obtain them for research purposes at https://github.com/strategic-quantization/bounded-rationality., Comment: This paper will be presented at the 5th IFAC Workshop on Cyber-Physical Human Systems on December 12-13, 2024 at Antalya, Turkiye

We present recent laboratory results demonstrating high-contrast coronagraphy for the future space-based large IR/Optical/Ultraviolet telescope recommended by the Decadal Survey. The High-contrast Imager for Complex Aperture Telescopes (HiCAT) testbed aims to implement a system-level hardware demonstration for segmented aperture coronagraphs with wavefront control. The telescope hardware simulator employs a segmented deformable mirror with 37 hexagonal segments that can be controlled in piston, tip, and tilt. In addition, two continuous deformable mirrors are used for high-order wavefront sensing and control. The low-order sensing subsystem includes a dedicated tip-tilt stage, a coronagraphic target acquisition camera, and a Zernike wavefront sensor that is used to measure and correct low-order aberration drifts. We explore the performance of a segmented aperture coronagraph both in static operations (limited by natural drifts and instabilities) and in dynamic operations (in the presence of artificial wavefront drifts added to the deformable mirrors), and discuss the estimation and control strategies used to reach and maintain the dark-zone contrast using our low-order wavefront sensing and control. We summarize experimental results that quantify the performance of the testbed in terms of contrast, inner/outer working angle and bandpass, and analyze limiting factors., Comment: 17 pages, 14 figures, SPIE Astronomical Telescopes + Instrumentation, 2022, Montr\'eal, Qu\'ebec, Canada

We present the final results of the Apodized Pupil Lyot Coronagraph (APLC) on the High-contrast imager for Complex Aperture Telescopes (HiCAT) testbed, under NASA's Strategic Astrophysics Technology program. The HiCAT testbed was developed over the past decade to enable a system-level demonstration of coronagraphy for exoplanet direct imaging with the future Habitable Wolds Observatory. HiCAT includes an active, segmented telescope simulator, a coronagraph, and metrology systems (Low-order and Mid-Order Zernike Wavefront Sensors, and Phase Retrieval camera). These results correspond to an off-axis (un-obscured) configuration, as was envisioned in the 2020 Decadal Survey Recommendations. Narrowband and broadband dark holes are generated using two continuous deformable mirrors (DM) to control high order wavefront aberrations, and low-order drifts can be further stabilized using the LOWFS loop. The APLC apodizers, manufactured using carbon nanotubes, were optimized for broadband performance and include the calibrated geometric aperture. HiCAT is, to this date, the only testbed facility able to demonstrate high-contrast coronagraphy with a truly segmented aperture, as is required for the Habitable World Observatory, albeit limited to ambient conditions. Results presented here include $6\times 10^{-8}$ (90% CI) contrast in 9% bandpass in a 360 deg dark hole with inner and outer working angles of $4.4 \lambda/D_{pupil}$ and $11 \lambda/D_{pupil}$ . Narrowband contrast (3% bandpass) reaches $2.4\times 10^{-8}$ (90% confidence interval)., Comment: 17 pages, 16 figures, SPIE Astronomical Telescopes + Instrumentation, 2024, Yokohama, Japan

Feeding the growing human population sustainably amidst climate change is one of the most important challenges in the 21st century. Current practices often lead to the overuse of agronomic inputs, such as synthetic fertilizers and water, resulting in environmental contamination and diminishing returns on crop productivity. The complexity of agricultural systems, involving plant-environment interactions and human management, presents significant scientific and technical challenges for developing sustainable practices. Addressing these challenges necessitates transdisciplinary research, involving intense collaboration among fields such as plant science, engineering, computer science, and social sciences. Here, we present five case studies from two research centers demonstrating successful transdisciplinary approaches toward more sustainable water and fertilizer use. These case studies span multiple scales. Starting from whole-plant signaling, we explore how reporter plants can transform our understanding of plant communication and enable efficient application of water and fertilizers. We then show how new fertilizer technologies could increase the availability of phosphorus in the soil. To accelerate advancements in breeding new cultivars, we discuss robotic technologies for high-throughput plant screening in different environments at a population scale. At the ecosystem scale, we investigate phosphorus recovery from aquatic systems and methods to minimize phosphorus leaching. Finally, as agricultural outputs affect all people, we show how to integrate stakeholder perspectives and needs into the research. With these case studies, we hope to encourage the scientific community to adopt transdisciplinary research and promote cross-training among biologists, engineers, and social scientists to drive discovery and innovation in advancing sustainable agricultural systems.

Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vector Quantization (VQ) in variational autoencoders (VQ-VAEs, VQ-GANs, etc.), which has demonstrated state-of-the-art performance in many modern generative modeling applications. Quantizing the latent space has been justified by the assumption that the data themselves are inherently discrete in the latent space (like pixel values). In this paper, we propose an alternative representation of the latent space by relaxing the structural assumption than the VQ formulation. Specifically, we assume that the latent space can be approximated by a union of subspaces model corresponding to a dictionary-based representation under a sparsity constraint. The dictionary is learned/updated during the training process. We apply this approach to look at two models: Dictionary Learning Variational Autoencoders (DL-VAEs) and DL-VAEs with Generative Adversarial Networks (DL-GANs). We show empirically that our more latent space is more expressive and has leads to better representations than the VQ approach in terms of reconstruction quality at the expense of a small computational overhead for the latent space computation. Our results thus suggest that the true benefit of the VQ approach might not be from discretization of the latent space, but rather the lossy compression of the latent space. We confirm this hypothesis by showing that our sparse representations also address the codebook collapse issue as found common in VQ-family models., Comment: Preprint, under review. Submitted to 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

GPUs are the heart of the latest generations of supercomputers. We efficiently accelerate a compressible multiphase flow solver via OpenACC on NVIDIA and AMD Instinct GPUs. Optimization is accomplished by specifying the directive clauses 'gang vector' and 'collapse'. Further speedups of six and ten times are achieved by packing user-defined types into coalesced multidimensional arrays and manual inlining via metaprogramming. Additional optimizations yield seven-times speedup in array packing and thirty-times speedup of select kernels on Frontier. Weak scaling efficiencies of 97% and 95% are observed when scaling to 50% of Summit and 95% of Frontier. Strong scaling efficiencies of 84% and 81% are observed when increasing the device count by a factor of 8 and 16 on V100 and MI250X hardware. The strong scaling efficiency of AMD's MI250X increases to 92% when increasing the device count by a factor of 16 when GPU-aware MPI is used for communication., Comment: 11 pages, 9 figures, 6 listings, WACCPD at SC24

In this letter we study the proximal gradient dynamics. This recently-proposed continuous-time dynamics solves optimization problems whose cost functions are separable into a nonsmooth convex and a smooth component. First, we show that the cost function decreases monotonically along the trajectories of the proximal gradient dynamics. We then introduce a new condition that guarantees exponential convergence of the cost function to its optimal value, and show that this condition implies the proximal Polyak-{\L}ojasiewicz condition. We also show that the proximal Polyak-{\L}ojasiewicz condition guarantees exponential convergence of the cost function. Moreover, we extend these results to time-varying optimization problems, providing bounds for equilibrium tracking. Finally, we discuss applications of these findings, including the LASSO problem, certain matrix based problems and a numerical experiment on a feed-forward neural network., Comment: Submitted to IEEE L-CSS and ACC, 7 pages, 1 figure

The use of multi-threading and file prioritization methods has accelerated the speed at which ransomware encrypts files. To minimize file loss during the ransomware attack, detecting file modifications at the earliest execution stage is considered very important. To achieve this, selecting files as traps and monitoring changes to them is a practical way to deal with modern ransomware variants. This approach minimizes overhead on the endpoint, facilitating early identification of ransomware. This paper evaluates various machine learning-based trap selection methods for reducing file loss, detection delay, and endpoint overhead. We specifically examine non-parametric clustering methods such as Affinity Propagation, Gaussian Mixture Models, Mean Shift, and Optics to assess their effectiveness in trap selection for ransomware detection. These methods select M files from a directory with N files (M

We show that the flip chain for non-crossing spanning trees of $n+1$ points in convex position mixes in time $O(n^8\log n)$., Comment: 19 pages, 6 figures

This study investigates the universal relation between Goon and Penco (GP) proposed within the frameworks of Power-Maxwell, Power-Yang-Mills, and Maxwell-Power-Yang-Mills black holes. We begin by analyzing these black holes' thermodynamics and then calculating the perturbed metric and thermodynamic quantities by perturbing the action. Our objective is to examine the consistency of the GP relation across various power-law terms in the field equations, aiming to gain deeper insights into the nature of these black holes. The GP connection remains robust across different power spacetimes, indicating that this relation is a universal feature of black holes., Comment: Comments are Welcome

Scientific applications in fields such as high energy physics, computational fluid dynamics, and climate science generate vast amounts of data at high velocities. This exponential growth in data production is surpassing the advancements in computing power, network capabilities, and storage capacities. To address this challenge, data compression or reduction techniques are crucial. These scientific datasets have underlying data structures that consist of structured and block structured multidimensional meshes where each grid point corresponds to a tensor. It is important that data reduction techniques leverage strong spatial and temporal correlations that are ubiquitous in these applications. Additionally, applications such as CFD, process tensors comprising hundred plus species and their attributes at each grid point. Reduction techniques should be able to leverage interrelationships between the elements in each tensor. In this paper, we propose an attention-based hierarchical compression method utilizing a block-wise compression setup. We introduce an attention-based hyper-block autoencoder to capture inter-block correlations, followed by a block-wise encoder to capture block-specific information. A PCA-based post-processing step is employed to guarantee error bounds for each data block. Our method effectively captures both spatiotemporal and inter-variable correlations within and between data blocks. Compared to the state-of-the-art SZ3, our method achieves up to 8 times higher compression ratio on the multi-variable S3D dataset. When evaluated on single-variable setups using the E3SM and XGC datasets, our method still achieves up to 3 times and 2 times higher compression ratio, respectively.

Recent advancements in text-to-speech (TTS) synthesis show that large-scale models trained with extensive web data produce highly natural-sounding output. However, such data is scarce for Indian languages due to the lack of high-quality, manually subtitled data on platforms like LibriVox or YouTube. To address this gap, we enhance existing large-scale ASR datasets containing natural conversations collected in low-quality environments to generate high-quality TTS training data. Our pipeline leverages the cross-lingual generalization of denoising and speech enhancement models trained on English and applied to Indian languages. This results in IndicVoices-R (IV-R), the largest multilingual Indian TTS dataset derived from an ASR dataset, with 1,704 hours of high-quality speech from 10,496 speakers across 22 Indian languages. IV-R matches the quality of gold-standard TTS datasets like LJSpeech, LibriTTS, and IndicTTS. We also introduce the IV-R Benchmark, the first to assess zero-shot, few-shot, and many-shot speaker generalization capabilities of TTS models on Indian voices, ensuring diversity in age, gender, and style. We demonstrate that fine-tuning an English pre-trained model on a combined dataset of high-quality IndicTTS and our IV-R dataset results in better zero-shot speaker generalization compared to fine-tuning on the IndicTTS dataset alone. Further, our evaluation reveals limited zero-shot generalization for Indian voices in TTS models trained on prior datasets, which we improve by fine-tuning the model on our data containing diverse set of speakers across language families. We open-source all data and code, releasing the first TTS model for all 22 official Indian languages., Comment: Accepted to NeurIPS 2024 Datasets and Benchmarks track

We present new Galactic reddening maps of the high Galactic latitude sky using DESI imaging and spectroscopy. We directly measure the reddening of 2.6 million stars by comparing the observed stellar colors in $g-r$ and $r-z$ from DESI imaging with the synthetic colors derived from DESI spectra from the first two years of the survey. The reddening in the two colors is on average consistent with the \cite{fitzpatrick_correcting_1999} extinction curve with $R_\mathrm{V}=3.1$. We find that our reddening maps differ significantly from the commonly used \cite{schlegel_maps_1998} (SFD) reddening map (by up to 80 mmag in $E(B-V)$), and we attribute most of this difference to systematic errors in the SFD map. To validate the reddening map, we select a galaxy sample with extinction correction based on our reddening map, and this yields significantly better uniformity than the SFD extinction correction. Finally, we discuss the potential systematic errors in the DESI reddening measurements, including the photometric calibration errors that are the limiting factor on our accuracy. The $E(g-r)$ and $E(g-r)$ maps presented in this work, and for convenience their corresponding $E(B-V)$ maps with SFD calibration, are publicly available., Comment: Submitted to the Open Journal of Astrophysics. Associated data files: https://data.desi.lbl.gov/public/papers/mws/desi_dust/y2/v1/maps/

In this work, we study the robust phase retrieval problem where the task is to recover an unknown signal $\theta^* \in \mathbb{R}^d$ in the presence of potentially arbitrarily corrupted magnitude-only linear measurements. We propose an alternating minimization approach that incorporates an oracle solver for a non-convex optimization problem as a subroutine. Our algorithm guarantees convergence to $\theta^*$ and provides an explicit polynomial dependence of the convergence rate on the fraction of corrupted measurements. We then provide an efficient construction of the aforementioned oracle under a sparse arbitrary outliers model and offer valuable insights into the geometric properties of the loss landscape in phase retrieval with corrupted measurements. Our proposed oracle avoids the need for computationally intensive spectral initialization, using a simple gradient descent algorithm with a constant step size and random initialization instead. Additionally, our overall algorithm achieves nearly linear sample complexity, $\mathcal{O}(d \, \mathrm{polylog}(d))$.

The transport across a Kondo-correlated quantum dot coupled to two leads with independent temperatures and chemical potentials is studied using a controlled non-perturbative, and in this sense exact numeric treatment based on a hybrid numerical renormalization group combined with time-dependent density matrix renormalization group (NRG-tDMRG). We find a peak in the conductance at finite voltage bias vs. the temperature gradient $\Delta T = T_R - T_L$ across left and right lead. We then focus predominantly on zero voltage bias but finite $\Delta T$ far beyond linear response. We reveal the dependence of the characteristic zero-bias conductance on the individual lead temperatures. We find that the finite-$\Delta T$ data behaves quantitatively similar to linear response with an effective equilibrium temperature derived from the different lead temperatures. The regime of sign changes in the Seebeck coefficient, signaling the presence of Kondo correlations, and its dependence on the individual lead temperatures provide a complete picture of the Kondo regime in the presence of finite temperature gradients. The results from the zero-bias conductance and Seebeck coefficient studies unveil an approximate `Kondo circle' in the $T_L/T_R$ plane as the regime within which the Kondo correlations dominate. We also study the heat current and the corresponding heat conductance vs. finite $\Delta T$. We provide a polynomial fit for our numerical results for the thermocurrent as a function of the individual lead temperatures which may be used to fit experimental data in the Kondo regime., Comment: 15 pages, 11 figures