Search

Self-play via online learning is one of the premier ways to solve large-scale two-player zero-sum games, both in theory and practice. Particularly popular algorithms include optimistic multiplicative weights update (OMWU) and optimistic gradient-descent-ascent (OGDA). While both algorithms enjoy $O(1/T)$ ergodic convergence to Nash equilibrium in two-player zero-sum games, OMWU offers several advantages including logarithmic dependence on the size of the payoff matrix and $\widetilde{O}(1/T)$ convergence to coarse correlated equilibria even in general-sum games. However, in terms of last-iterate convergence in two-player zero-sum games, an increasingly popular topic in this area, OGDA guarantees that the duality gap shrinks at a rate of $O(1/\sqrt{T})$, while the best existing last-iterate convergence for OMWU depends on some game-dependent constant that could be arbitrarily large. This begs the question: is this potentially slow last-iterate convergence an inherent disadvantage of OMWU, or is the current analysis too loose? Somewhat surprisingly, we show that the former is true. More generally, we prove that a broad class of algorithms that do not forget the past quickly all suffer the same issue: for any arbitrarily small $\delta>0$, there exists a $2\times 2$ matrix game such that the algorithm admits a constant duality gap even after $1/\delta$ rounds. This class of algorithms includes OMWU and other standard optimistic follow-the-regularized-leader algorithms., Comment: 27 pages, 4 figures

While Online Gradient Descent and other no-regret learning procedures are known to efficiently converge to a coarse correlated equilibrium in games where each agent's utility is concave in their own strategy, this is not the case when utilities are non-concave -- a common scenario in machine learning applications involving strategies parameterized by deep neural networks, or when agents' utilities are computed by neural networks, or both. Non-concave games introduce significant game-theoretic and optimization challenges: (i) Nash equilibria may not exist; (ii) local Nash equilibria, though existing, are intractable; and (iii) mixed Nash, correlated, and coarse correlated equilibria generally have infinite support and are intractable. To sidestep these challenges, we revisit the classical solution concept of $\Phi$-equilibria introduced by Greenwald and Jafari [2003], which is guaranteed to exist for an arbitrary set of strategy modifications $\Phi$ even in non-concave games [Stoltz and Lugosi, 2007]. However, the tractability of $\Phi$-equilibria in such games remains elusive. In this paper, we initiate the study of tractable $\Phi$-equilibria in non-concave games and examine several natural families of strategy modifications. We show that when $\Phi$ is finite, there exists an efficient uncoupled learning algorithm that converges to the corresponding $\Phi$-equilibria. Additionally, we explore cases where $\Phi$ is infinite but consists of local modifications, showing that Online Gradient Descent can efficiently approximate $\Phi$-equilibria in non-trivial regimes., Comment: 48 pages; Add new algorithmic and lower-bound results

This paper studies a joint design problem where a seller can design both the signal structures for the agents to learn their values, and the allocation and payment rules for selling the item. In his seminal work, Myerson (1981) shows how to design the optimal auction with exogenous signals. We show that the problem becomes NP-hard when the seller also has the ability to design the signal structures. Our main result is a polynomial-time approximation scheme (PTAS) for computing the optimal joint design with at most an $\epsilon$ multiplicative loss in expected revenue. Moreover, we show that in our joint design problem, the seller can significantly reduce the information rent of the agents by providing partial information, which ensures a revenue that is at least $1 - \frac{1}{e}$ of the optimal welfare for all valuation distributions.

Recently, MBConv blocks, initially designed for efficiency in resource-limited settings and later adapted for cutting-edge image classification performances, have demonstrated significant potential in image classification tasks. Despite their success, their application in semantic segmentation has remained relatively unexplored. This paper introduces a novel adaptation of MBConv blocks specifically tailored for semantic segmentation. Our modification stems from the insight that semantic segmentation requires the extraction of more detailed spatial information than image classification. We argue that to effectively perform multi-scale semantic segmentation, each branch of a U-Net architecture, regardless of its resolution, should possess equivalent segmentation capabilities. By implementing these changes, our approach achieves impressive mean Intersection over Union (IoU) scores of 84.5% and 84.0% on the Cityscapes test and validation datasets, respectively, demonstrating the efficacy of our proposed modifications in enhancing semantic segmentation performance.

We study policy optimization algorithms for computing correlated equilibria in multi-player general-sum Markov Games. Previous results achieve $O(T^{-1/2})$ convergence rate to a correlated equilibrium and an accelerated $O(T^{-3/4})$ convergence rate to the weaker notion of coarse correlated equilibrium. In this paper, we improve both results significantly by providing an uncoupled policy optimization algorithm that attains a near-optimal $\tilde{O}(T^{-1})$ convergence rate for computing a correlated equilibrium. Our algorithm is constructed by combining two main elements (i) smooth value updates and (ii) the optimistic-follow-the-regularized-leader algorithm with the log barrier regularizer., Comment: AISTATS 2024 Oral

Beam manipulation is of paramount importance in wave engineering, enabling diverse beam shapes like pencil beams, flat-top beams, and isoflux beams to cater to various application missions. Among the beams, shaping flat-top and isoflux beams remains challenging with the traditional synthesis approaches that mainly rely on optimization algorithms. Here, we develop modulated metasurfaces to efficiently generate flat-top and isoflux beams from the first principle of field superposition with negligible optimizations, by performing phase symmetry operations. The theoretical analysis not only facilitates the shaping of 1D and 2D flat-top and isoflux beams but also exhibits controllable beamwidths. Experimental validation confirms the efficacy of the phase symmetry operations in generating flat-top beams with adjustable beamwidths. The concept of phase symmetry operations can be extended to other vectorial components, offering potential applications for the manipulation of various wave types such as acoustic waves, water surface waves, and beyond, thereby advancing related applications.

Algorithms based on regret matching, specifically regret matching$^+$ (RM$^+$), and its variants are the most popular approaches for solving large-scale two-player zero-sum games in practice. Unlike algorithms such as optimistic gradient descent ascent, which have strong last-iterate and ergodic convergence properties for zero-sum games, virtually nothing is known about the last-iterate properties of regret-matching algorithms. Given the importance of last-iterate convergence for numerical optimization reasons and relevance as modeling real-word learning in games, in this paper, we study the last-iterate convergence properties of various popular variants of RM$^+$. First, we show numerically that several practical variants such as simultaneous RM$^+$, alternating RM$^+$, and simultaneous predictive RM$^+$, all lack last-iterate convergence guarantees even on a simple $3\times 3$ game. We then prove that recent variants of these algorithms based on a smoothing technique do enjoy last-iterate convergence: we prove that extragradient RM$^{+}$ and smooth Predictive RM$^+$ enjoy asymptotic last-iterate convergence (without a rate) and $1/\sqrt{t}$ best-iterate convergence. Finally, we introduce restarted variants of these algorithms, and show that they enjoy linear-rate last-iterate convergence.

We study revenue maximization in multi-item auctions, where bidders have subadditive valuations over independent items. Providing a simple mechanism that is approximately revenue-optimal in this setting is a major open problem in mechanism design. In this paper, we present the first \emph{simple mechanism} whose revenue is at least a \emph{constant fraction} of the optimal revenue in multi-item auctions with subadditive bidders. Our mechanism is a simultaneous auction that incorporates either a personalized entry fee or a personalized reserve price per item. We prove that for any simultaneous auction that satisfies c-efficiency -- a new property we propose, its revenue is at least an $O(c)$-approximation to the optimal revenue. We further show that both the \emph{simultaneous first-price} and the \emph{simultaneous all-pay auction} are $1\over 2$-efficient. Providing revenue guarantees for non-truthful simple mechanisms, e.g., simultaneous auctions, in multi-dimensional environments has been recognized by Roughgarden et al. as an important open question. Prior to our result, the only such revenue guarantees are due to Daskalakis et al. for bidders who have additive valuations over independent items. Our result significantly extends the revenue guarantees of these non-truthful simple auctions to settings where bidders have combinatorial valuations., Comment: To appear at FOCS 2023

We consider the problem of maximizing the gains from trade (GFT) in two-sided markets. The seminal impossibility result by Myerson and Satterthwaite shows that even for bilateral trade, there is no individually rational (IR), Bayesian incentive compatible (BIC) and budget balanced (BB) mechanism that can achieve the full GFT. Moreover, the optimal BIC, IR and BB mechanism that maximizes the GFT is known to be complex and heavily depends on the prior. In this paper, we pursue a Bulow-Klemperer-style question, i.e., does augmentation allow for prior-independent mechanisms to compete against the optimal mechanism? Our first main result shows that in the double auction setting with $m$ i.i.d. buyers and $n$ i.i.d. sellers, by augmenting $O(1)$ buyers and sellers to the market, the GFT of a simple, dominant strategy incentive compatible (DSIC), and prior-independent mechanism in the augmented market is at least the optimal in the original market, when the buyers' distribution first-order stochastically dominates the sellers' distribution. Next, we go beyond the i.i.d. setting and study the power of two-sided recruitment in more general markets. Our second main result is that for any $\epsilon > 0$ and any set of $O(1/\epsilon)$ buyers and sellers where the buyers' value exceeds the sellers' value with constant probability, if we add these additional agents into any market with arbitrary correlations, the Trade Reduction mechanism obtains a $(1-\epsilon)$-approximation of the GFT of the augmented market. Importantly, the newly recruited agents are agnostic to the original market.

Numerous applications in machine learning and data analytics can be formulated as equilibrium computation over Riemannian manifolds. Despite the extensive investigation of their Euclidean counterparts, the performance of Riemannian gradient-based algorithms remain opaque and poorly understood. We revisit the original scheme of Riemannian gradient descent (RGD) and analyze it under a geodesic monotonicity assumption, which includes the well-studied geodesically convex-concave min-max optimization problem as a special case. Our main contribution is to show that, despite the phenomenon of distance distortion, the RGD scheme, with a step size that is agnostic to the manifold's curvature, achieves a curvature-independent and linear last-iterate convergence rate in the geodesically strongly monotone setting. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence in the Riemannian setting has not been considered before.

We study the model of metric voting proposed by Feldman et al. [2020]. In this model, experts and candidates are located in a metric space, and each candidate possesses a quality that is independent of her location. An expert evaluates each candidate as the candidate's quality less a bias term--the distance between the candidate and the expert in the metric space. The expert then votes for her favorite candidate. The goal is to select a voting rule and a committee of experts to mitigate the bias. More specifically, given $m$ candidates, what is the minimum number of experts needed to ensure that the voting rule selects a candidate whose quality is at most $\varepsilon$ worse than the best one? Our first main result is a new way to select the committee using exponentially less experts compared to the method proposed in Feldman et al. [2020]. Our second main result is a novel construction that substantially improves the lower bound on the committee size. Indeed, our upper and lower bounds match in terms of $m$, the number of candidates, and $\varepsilon$, the desired accuracy, for general convex normed spaces, and differ by a multiplicative factor that only depends on the dimension of the underlying normed space but is independent of other parameters of the problem. We extend the nearly matching upper and lower bounds to the setting in which each expert returns a ranking of her top $k$ candidates and we wish to choose $\ell$ candidates with cumulative quality at most $\varepsilon$ worse than that of the best set of $\ell$ candidates, settling an open problem of Feldman et al. [2020]. Finally, we consider the setting where there are multiple rounds of voting. We show that by introducing another round of voting, the number of experts needed to guarantee the selection of an $\varepsilon$-optimal candidate becomes independent of the number of candidates.

We revisit the problem of learning in two-player zero-sum Markov games, focusing on developing an algorithm that is uncoupled, convergent, and rational, with non-asymptotic convergence rates. We start from the case of stateless matrix game with bandit feedback as a warm-up, showing an $O(t^{-\frac{1}{8}})$ last-iterate convergence rate. To the best of our knowledge, this is the first result that obtains finite last-iterate convergence rate given access to only bandit feedback. We extend our result to the case of irreducible Markov games, providing a last-iterate convergence rate of $O(t^{-\frac{1}{9+\varepsilon}})$ for any $\varepsilon>0$. Finally, we study Markov games without any assumptions on the dynamics, and show a path convergence rate, which is a new notion of convergence we defined, of $O(t^{-\frac{1}{10}})$. Our algorithm removes the coordination and prior knowledge requirement of [Wei et al., 2021], which pursued the same goals as us for irreducible Markov games. Our algorithm is related to [Chen et al., 2021, Cen et al., 2021] and also builds on the entropy regularization technique. However, we remove their requirement of communications on the entropy values, making our algorithm entirely uncoupled., Comment: To appear at NeurIPS 2023

We propose a new Markov Decision Process (MDP) model for ad auctions to capture the user response to the quality of ads, with the objective of maximizing the long-term discounted revenue. By incorporating user response, our model takes into consideration all three parties involved in the auction (advertiser, auctioneer, and user). The state of the user is modeled as a user-specific click-through rate (CTR) with the CTR changing in the next round according to the set of ads shown to the user in the current round. We characterize the optimal mechanism for this MDP as a Myerson's auction with a notion of modified virtual value, which relies on the value distribution of the advertiser, the current user state, and the future impact of showing the ad to the user. Leveraging this characterization, we design a sample-efficient and computationally-efficient algorithm which outputs an approximately optimal policy that requires only sample access to the true MDP and the value distributions of the bidders. Finally, we propose a simple mechanism built upon second price auctions with personalized reserve prices and show it can achieve a constant-factor approximation to the optimal long term discounted revenue.

We consider online learning in multi-player smooth monotone games. Existing algorithms have limitations such as (1) being only applicable to strongly monotone games; (2) lacking the no-regret guarantee; (3) having only asymptotic or slow $O(\frac{1}{\sqrt{T}})$ last-iterate convergence rate to a Nash equilibrium. While the $O(\frac{1}{\sqrt{T}})$ rate is tight for a large class of algorithms including the well-studied extragradient algorithm and optimistic gradient algorithm, it is not optimal for all gradient-based algorithms. We propose the accelerated optimistic gradient (AOG) algorithm, the first doubly optimal no-regret learning algorithm for smooth monotone games. Namely, our algorithm achieves both (i) the optimal $O(\sqrt{T})$ regret in the adversarial setting under smooth and convex loss functions and (ii) the optimal $O(\frac{1}{T})$ last-iterate convergence rate to a Nash equilibrium in multi-player smooth monotone games. As a byproduct of the accelerated last-iterate convergence rate, we further show that each player suffers only an $O(\log T)$ individual worst-case dynamic regret, providing an exponential improvement over the previous state-of-the-art $O(\sqrt{T})$ bound., Comment: Published at ICML 2023. V2 incorporates reviewers' feedback

We study the problem of social welfare maximization in bilateral trade, where two agents, a buyer and a seller, trade an indivisible item. We consider arguably the simplest form of mechanisms -- the fixed-price mechanisms, where the designer offers trade at a fixed price to the seller and buyer. Besides the simple form, fixed-price mechanisms are also the only DSIC and budget balanced mechanisms in bilateral trade. We obtain improved approximation ratios of fixed-price mechanisms in different settings. In the full prior information setting where the designer has access to the value distributions of both the seller and buyer, we show that the optimal fixed-price mechanism can achieve at least $0.72$ of the optimal welfare, and no fixed-price mechanism can achieve more than $0.7381$ of the optimal welfare. Prior to our result the state of the art approximation ratio was $1 - 1/e + 0.0001 \approx 0.632$. Interestingly, we further show that the optimal approximation ratio achievable with full prior information is identical to the optimal approximation ratio obtainable with only one-sided prior information. We further consider two limited information settings. In the first one, the designer is only given the mean of the buyer's (or the seller's) value. We show that with such minimal information, one can already design a fixed-price mechanism that achieves $2/3$ of the optimal social welfare, which surpasses the previous state of the art ratio even when the designer has access to the full prior information. Furthermore, $2/3$ is the optimal attainable ratio in this setting. In the second one, we assume that the designer has sample access to the value distributions. We propose a new family mechanisms called order statistic mechanisms and provide a complete characterization of their approximation ratios for any fixed number of samples., Comment: Abstract shortened to meet arXiv requirements; Updated version with new results

We study first-order methods for constrained min-max optimization. Existing methods either require two gradient calls or two projections in each iteration, which may be costly in some applications. In this paper, we first show that a variant of the Optimistic Gradient (OG) method, a single-call single-projection algorithm, has $O(\frac{1}{\sqrt{T}})$ best-iterate convergence rate for inclusion problems with operators that satisfy the weak Minty variation inequality (MVI). Our second result is the first single-call single-projection algorithm -- the Accelerated Reflected Gradient (ARG) method that achieves the optimal $O(\frac{1}{T})$ last-iterate convergence rate for inclusion problems that satisfy negative comonotonicity. Both the weak MVI and negative comonotonicity are well-studied assumptions and capture a rich set of non-convex non-concave min-max optimization problems. Finally, we show that the Reflected Gradient (RG) method, another single-call single-projection algorithm, has $O(\frac{1}{\sqrt{T}})$ last-iterate convergence rate for constrained convex-concave min-max optimization, answering an open problem of [Heish et al, 2019]. Our convergence rates hold for standard measures such as the tangent residual and the natural residual., Comment: Published as a conference paper at ICLR 2023

We study constrained comonotone min-max optimization, a structured class of nonconvex-nonconcave min-max optimization problems, and their generalization to comonotone inclusion. In our first contribution, we extend the Extra Anchored Gradient (EAG) algorithm, originally proposed by Yoon and Ryu (2021) for unconstrained min-max optimization, to constrained comonotone min-max optimization and comonotone inclusion, achieving an optimal convergence rate of $O\left(\frac{1}{T}\right)$ among all first-order methods. Additionally, we prove that the algorithm's iterations converge to a point in the solution set. In our second contribution, we extend the Fast Extra Gradient (FEG) algorithm, as developed by Lee and Kim (2021), to constrained comonotone min-max optimization and comonotone inclusion, achieving the same $O\left(\frac{1}{T}\right)$ convergence rate. This rate is applicable to the broadest set of comonotone inclusion problems yet studied in the literature. Our analyses are based on simple potential function arguments, which might be useful for analyzing other accelerated algorithms., Comment: Accepted to ICML 2024

Distributed computing (cloud) networks, e.g., mobile edge computing (MEC), are playing an increasingly important role in the efficient hosting, running, and delivery of real-time stream-processing applications such as industrial automation, immersive video, and augmented reality. While such applications require timely processing of real-time streams that are simultaneously useful for multiple users/devices, existing technologies lack efficient mechanisms to handle their increasingly multicast nature, leading to unnecessary traffic redundancy and associated network congestion. In this paper, we address the design of distributed packet processing, routing, and duplication policies for optimal control of multicast stream-processing services. We present a characterization of the enlarged capacity region that results from efficient packet duplication, and design the first fully distributed multicast traffic management policy that stabilizes any input rate in the interior of the capacity region while minimizing overall operational cost. Numerical results demonstrate the effectiveness of the proposed policy to achieve throughput- and cost-optimal delivery of stream-processing services over distributed computing networks.

The timely delivery of resource-intensive and latency-sensitive services (e.g., industrial automation, augmented reality) over distributed computing networks (e.g., mobile edge computing) is drawing increasing attention. Motivated by the insufficiency of average delay performance guarantees provided by existing studies, we focus on the critical goal of delivering next generation real-time services ahead of corresponding deadlines on a per-packet basis, while minimizing overall cloud network resource cost. We introduce a novel queuing system that is able to track data packets' lifetime and formalize the optimal cloud network control problem with strict deadline constraints. After illustrating the main challenges in delivering packets to their destinations before getting dropped due to lifetime expiry, we construct an equivalent formulation, where relaxed flow conservation allows leveraging Lyapunov optimization to derive a provably near-optimal fully distributed algorithm for the original problem. Numerical results validate the theoretical analysis and show the superior performance of the proposed control policy compared with state-of-the-art cloud network control., Comment: arXiv admin note: text overlap with arXiv:2205.02427

Next-generation distributed computing networks (e.g., edge and fog computing) enable the efficient delivery of delay-sensitive, compute-intensive applications by facilitating access to computation resources in close proximity to end users. Many of these applications (e.g., augmented/virtual reality) are also data-intensive: in addition to user-specific (live) data streams, they require access to (static) digital objects (e.g., image database) to complete the required processing tasks. When required objects are not available at the servers hosting the associated service functions, they must be fetched from other edge locations, incurring additional communication cost and latency. In such settings, overall service delivery performance shall benefit from jointly optimized decisions around (i) routing paths and processing locations for live data streams, together with (ii) cache selection and distribution paths for associated digital objects. In this paper, we address the problem of dynamic control of data-intensive services over edge cloud networks. We characterize the network stability region and design the first throughput-optimal control policy that coordinates processing and routing decisions for both live and static data-streams. Numerical results demonstrate the superior performance (e.g., throughput, delay, and resource consumption) obtained via the novel multi-pipeline flow control mechanism of the proposed policy, compared with state-of-the-art algorithms that lack integrated stream processing and data distribution control., Comment: arXiv admin note: substantial text overlap with arXiv:2205.01944

We are entering a rapidly unfolding future driven by the delivery of real-time computation services, such as industrial automation and augmented reality, collectively referred to as AgI services, over highly distributed cloud/edge computing networks. The interaction intensive nature of AgI services is accelerating the need for networking solutions that provide strict latency guarantees. In contrast to most existing studies that can only characterize average delay performance, we focus on the critical goal of delivering AgI services ahead of corresponding deadlines on a per-packet basis, while minimizing overall cloud network operational cost. To this end, we design a novel queuing system able to track data packets' lifetime and formalize the delay-constrained least-cost dynamic network control problem. To address this challenging problem, we first study the setting with average capacity (or resource budget) constraints, for which we characterize the delay-constrained stability region and design a near-optimal control policy leveraging Lyapunov optimization theory on an equivalent virtual network. Guided by the same principle, we tackle the peak capacity constrained scenario by developing the reliable cloud network control (RCNC) algorithm, which employs a two-way optimization method to make actual and virtual network flow solutions converge in an iterative manner. Extensive numerical results show the superior performance of the proposed control policy compared with the state-of-the-art cloud network control algorithm, and the value of guaranteeing strict end-to-end deadlines for the delivery of next-generation AgI services.

Emerging Metaverse applications, designed to deliver highly interactive and immersive experiences that seamlessly blend physical reality and digital virtuality, are accelerating the need for distributed compute platforms with unprecedented storage, computation, and communication requirements. To this end, the integrated evolution of next-generation networks (e.g., 5G and beyond) and distributed cloud technologies (e.g., fog and mobile edge computing), have emerged as a promising paradigm to address the interaction- and resource-intensive nature of Metaverse applications. In this paper, we focus on the design of control policies for the joint orchestration of compute, caching, and communication (3C) resources in next-generation distributed cloud networks for the efficient delivery of Metaverse applications that require the real-time aggregation, processing, and distribution of multiple live media streams and pre-stored digital assets. We describe Metaverse applications via directed acyclic graphs able to model the combination of real-time stream-processing and content distribution pipelines. We design the first throughput-optimal control policy that coordinates joint decisions around (i) routing paths and processing locations for live data streams, together with (ii) cache selection and distribution paths for associated data objects. We then extend the proposed solution to include a max-throughput database placement policy and two efficient replacement policies. In addition, we characterize the network stability regions for all studied scenarios. Numerical results demonstrate the superior performance obtained via the novel multi-pipeline flow control and 3C resource orchestration mechanisms of the proposed policy, compared with state-of-the-art algorithms that lack full 3C integrated control.

The monotone variational inequality is a central problem in mathematical programming that unifies and generalizes many important settings such as smooth convex optimization, two-player zero-sum games, convex-concave saddle point problems, etc. The extragradient algorithm by Korpelevich [1976] and the optimistic gradient descent-ascent algorithm by Popov [1980] are arguably the two most classical and popular methods for solving monotone variational inequalities. Despite their long histories, the following major problem remains open. What is the last-iterate convergence rate of the extragradient algorithm or the optimistic gradient descent-ascent algorithm for monotone and Lipschitz variational inequalities with constraints? We resolve this open problem by showing that both the extragradient algorithm and the optimistic gradient descent-ascent algorithm have a tight $O\left(\frac{1}{\sqrt{T}}\right)$ last-iterate convergence rate for arbitrary convex feasible sets, which matches the lower bound by Golowich et al. [2020a,b]. Our rate is measured in terms of the standard gap function. At the core of our results lies a non-standard performance measure -- the tangent residual, which can be viewed as an adaptation of the norm of the operator that takes the local constraints into account. We use the tangent residual (or a slight variation of the tangent residual) as the the potential function in our analysis of the extragradient algorithm (or the optimistic gradient descent-ascent algorithm) and prove that it is non-increasing between two consecutive iterates., Comment: We are including the OGDA result for unconstrained and constrained settings in this version. We further simplified the proof for EG and OGDA algorithm

Emerging distributed cloud architectures, e.g., fog and mobile edge computing, are playing an increasingly important role in the efficient delivery of real-time stream-processing applications (also referred to as augmented information services), such as industrial automation and metaverse experiences (e.g., extended reality, immersive gaming). While such applications require processed streams to be shared and simultaneously consumed by multiple users/devices, existing technologies lack efficient mechanisms to deal with their inherent multicast nature, leading to unnecessary traffic redundancy and network congestion. In this paper, we establish a unified framework for distributed cloud network control with generalized (mixed-cast) traffic flows that allows optimizing the distributed execution of the required packet processing, forwarding, and replication operations. We first characterize the enlarged multicast network stability region under the new control framework (with respect to its unicast counterpart). We then design a novel queuing system that allows scheduling data packets according to their current destination sets, and leverage Lyapunov drift-plus-penalty control theory to develop the first fully decentralized, throughput- and cost-optimal algorithm for multicast flow control. Numerical experiments validate analytical results and demonstrate the performance gain of the proposed design over existing network control policies.

The worlds of computing, communication, and storage have for a long time been treated separately, and even the recent trends of cloud computing, distributed computing, and mobile edge computing have not fundamentally changed the role of networks, still designed to move data between end users and pre-determined computation nodes, without true optimization of the end-to-end compute-communication process. However, the emergence of Metaverse applications, where users consume multimedia experiences that result from the real-time combination of distributed live sources and stored digital assets, has changed the requirements for, and possibilities of, systems that provide distributed caching, computation, and communication. We argue that the real-time interactive nature and high demands on data storage, streaming rates, and processing power of Metaverse applications will accelerate the merging of the cloud into the network, leading to highly-distributed tightly-integrated compute- and data-intensive networks becoming universal compute platforms for next-generation digital experiences. In this paper, we first describe the requirements of Metaverse applications and associated supporting infrastructure, including relevant use cases. We then outline a comprehensive cloud network flow mathematical framework, designed for the end-to-end optimization and control of such systems, and show numerical results illustrating its promising role for the efficient operation of Metaverse-ready networks.

We study the problem of selling information to a data-buyer who faces a decision problem under uncertainty. We consider the classic Bayesian decision-theoretic model pioneered by [Blackwell, 1951, 1953]. Initially, the data buyer has only partial information about the payoff-relevant state of the world. A data seller offers additional information about the state of the world. The information is revealed through signaling schemes, also referred to as experiments. In the single-agent setting, any mechanism can be represented as a menu of experiments. [Bergemann et al., 2018] present a complete characterization of the revenue-optimal mechanism in a binary state and binary action environment. By contrast, no characterization is known for the case with more actions. In this paper, we consider more general environments and study arguably the simplest mechanism, which only sells the fully informative experiment. In the environment with binary state and $m\geq 3$ actions, we provide an $O(m)$-approximation to the optimal revenue by selling only the fully informative experiment and show that the approximation ratio is tight up to an absolute constant factor. An important corollary of our lower bound is that the size of the optimal menu must grow at least linearly in the number of available actions, so no universal upper bound exists for the size of the optimal menu in the general single-dimensional setting. For multi-dimensional environments, we prove that even in arguably the simplest matching utility environment with 3 states and 3 actions, the ratio between the optimal revenue and the revenue by selling only the fully informative experiment can grow immediately to a polynomial of the number of agent types. Nonetheless, if the distribution is uniform, we show that selling only the fully informative experiment is indeed the optimal mechanism.

We study revenue maximization in multi-item multi-bidder auctions under the natural item-independence assumption - a classical problem in Multi-Dimensional Bayesian Mechanism Design. One of the biggest challenges in this area is developing algorithms to compute (approximately) optimal mechanisms that are not brute-force in the size of the bidder type space, which is usually exponential in the number of items in multi-item auctions. Unfortunately, such algorithms were only known for basic settings of our problem when bidders have unit-demand [CHMS10,CMS15] or additive valuations [Yao15]. In this paper, we significantly improve the previous results and design the first algorithm that runs in time polynomial in the number of items and the number of bidders to compute mechanisms that are $O(1)$-approximations to the optimal revenue when bidders have XOS valuations, resolving an open problem raised in [CM16,CZ17]. Moreover, the computed mechanism has a simple structure: It is either a posted price mechanism or a two-part tariff mechanism. As a corollary of our result, we show how to compute an approximately optimal and simple mechanism efficiently using only sample access to the bidders' value distributions. Our algorithm builds on two innovations that allow us to search over the space of mechanisms efficiently: (i) a new type of succinct representation of mechanisms - the marginal reduced forms, and (ii) a novel Lift-and-Round procedure that concavifies the problem.