Search

Dataset Distillation is used to create a concise, yet informative, synthetic dataset that can replace the original dataset for training purposes. Some leading methods in this domain prioritize long-range matching, involving the unrolling of training trajectories with a fixed number of steps (NS) on the synthetic dataset to align with various expert training trajectories. However, traditional long-range matching methods possess an overfitting-like problem, the fixed step size NS forces synthetic dataset to distortedly conform seen expert training trajectories, resulting in a loss of generality-especially to those from unencountered architecture. We refer to this as the Accumulated Mismatching Problem (AMP), and propose a new approach, Automatic Training Trajectories (ATT), which dynamically and adaptively adjusts trajectory length NS to address the AMP. Our method outperforms existing methods particularly in tests involving cross-architectures. Moreover, owing to its adaptive nature, it exhibits enhanced stability in the face of parameter variations., Comment: The paper is accepted at ECCV 2024

Particles of non-zero spin produced in non-central heavy-ion collisions are expected to be polarized along the direction perpendicular to the reaction plane because of their spin-orbit interactions in the produced matter, and this has indeed been observed for many hyperons and vector mesons. Here, we show that the hypertriton ($^3_\Lambda\text{H}$), which is the lightest hypernucleus, is also polarized in these collisions. Using the coalescence model based on the kinetic freezeout baryons for light (hyper-)nuclei production, we find that the angular distribution of the decay product of polarized $^3_\Lambda\text{H}$ is highly sensitive to the spin configuration of its wavefunction, providing a novel way to determine its spin structure. We also predict the beam energy dependence of $^3_\Lambda\text{H}$ and ${^3_{\bar{\Lambda}}}\overline{\rm H}$ polarizations in heavy-ion collisions from a few GeV to several TeV based on the measured $\Lambda$ and $\bar{\Lambda}$ polarizations. We further discuss the possibility of studying the spin correlations among nucleons and $\Lambda$ hyperons in the produced hadronic matter from the measured $^3_\Lambda\text{H}$ polarization in non-central heavy-ion collisions., Comment: 6 pages, 2 figures

GPU-based heterogeneous architectures are now commonly used in HPC clusters. Due to their architectural simplicity specialized for data-level parallelism, GPUs can offer much higher computational throughput and memory bandwidth than CPUs in the same generation do. However, as the available resources in GPUs have increased exponentially over the past decades, it has become increasingly difficult for a single program to fully utilize them. As a consequence, the industry has started supporting several resource partitioning features in order to improve the resource utilization by co-scheduling multiple programs on the same GPU die at the same time. Driven by the technological trend, this paper focuses on hierarchical resource partitioning on modern GPUs, and as an example, we utilize a combination of two different features available on recent NVIDIA GPUs in a hierarchical manner: MPS (Multi-Process Service), a finer-grained logical partitioning; and MIG (Multi-Instance GPU), a coarse-grained physical partitioning. We propose a method for comprehensively co-optimizing the setup of hierarchical partitioning and the selection of co-scheduling groups from a given set of jobs, based on reinforcement learning using their profiles. Our thorough experimental results demonstrate that our approach can successfully set up job concurrency, partitioning, and co-scheduling group selections simultaneously. This results in a maximum throughput improvement by a factor of 1.87 compared to the time-sharing scheduling., Comment: Published in: 2023 IEEE International Conference on Cluster Computing (CLUSTER)

CPU-GPU heterogeneous architectures are now commonly used in a wide variety of computing systems from mobile devices to supercomputers. Maximizing the throughput for multi-programmed workloads on such systems is indispensable as one single program typically cannot fully exploit all available resources. At the same time, power consumption is a key issue and often requires optimizing power allocations to the CPU and GPU while enforcing a total power constraint, in particular when the power/thermal requirements are strict. The result is a system-wide optimization problem with several knobs. In particular we focus on (1) co-scheduling decisions, i.e., selecting programs to co-locate in a space sharing manner; (2) resource partitioning on both CPUs and GPUs; and (3) power capping on both CPUs and GPUs. We solve this problem using predictive performance modeling using machine learning in order to coordinately optimize the above knob setups. Our experiential results using a real system show that our approach achieves up to 67% of speedup compared to a time-sharing-based scheduling with a naive power capping that evenly distributes power budgets across components.

Understanding the properties of hypernuclei helps to constrain the interaction between hyperon and nucleon, which is known to play an essential role in determining the properties of neutron stars. Experimental measurements have suggested that the hypertriton ($^3_\Lambda \text{H}$), the lightest hypernucleus, exhibits a halo structure with a deuteron core encircled by a $\Lambda$ hyperon at a distance of about 10 fm. This large $\Lambda-d$ distance in $^3_\Lambda \text{H}$ wave function is found to cause a suppressed $^3_\Lambda \text{H}$ yield and a softening of its transverse momentum ($p_T$) spectrum in relativistic heavy-ion collisions. Within the coalescence model based on nucleons and $\Lambda$ hyperons from a microscopic hybrid hydro model with a hadronic afterburner for nuclear cluster production in Pb-Pb collisions at $\sqrt{s_{NN}}$= 5.02 TeV, we show how this softening of the hypertriton $p_T$ spectrum appears and leads to a smaller mean $p_T$ for $^3_\Lambda \text{H}$ than for helium-3 ($^3$He). The latter is opposite to the predictions from the blast-wave model which assumes that $^3_\Lambda \text{H}$ and $^3$He are thermally produced at the kinetic freeze-out of heavy-ion collisions. The discovered quantum mechanical softening of the (anti-)hypertriton spectrum can be experimentally tested in relativistic heavy-ion collisions at different collision energies and centralities and used to obtain valuable insights into the mechanisms for light (hyper-)nuclei production in these collisions., Comment: 6 pages, 4 figures

In federated learning, all networked clients contribute to the model training cooperatively. However, with model sizes increasing, even sharing the trained partial models often leads to severe communication bottlenecks in underlying networks, especially when communicated iteratively. In this paper, we introduce a federated learning framework FedD3 requiring only one-shot communication by integrating dataset distillation instances. Instead of sharing model updates in other federated learning approaches, FedD3 allows the connected clients to distill the local datasets independently, and then aggregates those decentralized distilled datasets (e.g. a few unrecognizable images) from networks for model training. Our experimental results show that FedD3 significantly outperforms other federated learning frameworks in terms of needed communication volumes, while it provides the additional benefit to be able to balance the trade-off between accuracy and communication cost, depending on usage scenario or target dataset. For instance, for training an AlexNet model on CIFAR-10 with 10 clients under non-independent and identically distributed (Non-IID) setting, FedD3 can either increase the accuracy by over 71% with a similar communication volume, or save 98% of communication volume, while reaching the same accuracy, compared to other one-shot federated learning approaches., Comment: Accepted at IJCNN 2023