arXiv research

New algorithm reduces regret in asynchronous multiplayer bandits to constant or logarithmic levels.

Survey on multiplayer bandits, highlighting theoretical gaps and future directions.

New algorithms improve dueling bandit performance in multiplayer settings.

The paper tackles multi-player information asymmetry bandits in metric spaces.

We consider the problem of learning in single-player and multiplayer multiarmed bandit models. Bandit problems are classes of online learning problems that capture exploration versus exploitation tradeoffs. In a multiarmed bandit model, players can pick among many arms, and each play of an arm generates an i.i.d. rewar…

Paper develops efficient algorithms for learning rationalizable equilibria in multiplayer games.

Algorithm optimizes multi-player learning with noisy rewards without direct communication.

The paper addresses the Multiplayer Multi-Armed Bandit (MMAB) problem, where $M$ decision makers or players collaborate to maximize their cumulative reward. When several players select the same arm, a collision occurs and no reward is collected on this arm. Players involved in a collision are informed about this collis…

We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider the challenging heterogeneous setting, in which different arms may have different means for differe…

Motivated by cognitive radio networks, we consider the stochastic multiplayer multi-armed bandit problem, where several players pull arms simultaneously and collisions occur if one of them is pulled by several players at the same stage. We present a decentralized algorithm that achieves the same performance as a centra…

We study multiplayer stochastic multi-armed bandit problems in which the players cannot communicate and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider two feedback models: a model in which the players can observe whether a collision has occurred an…

ODC protocol improves learning in asynchronous multi-agent bandits.

A simple algorithm reduces federated contextual linear bandits' regret efficiently.

New algorithm for multi-player bandits in decentralized, asynchronous systems.

High-throughput 3D control training system achieves 100,000 FPS.

This paper considers the multi-armed thresholding bandit problem -- identifying all arms whose expected rewards are above a predefined threshold via as few pulls (or rounds) as possible -- proposed by Locatelli et al. [2016] recently. Although the proposed algorithm in Locatelli et al. [2016] achieves the optimal round…

Paper introduces Decentralized Non-stationary Competing Bandits ( exttt{DNCB}) for dynamic matching markets.

Paper tackles multiplayer symmetric games, securing equal share for n players.

Coop-FTPL algorithm minimizes network regret in semi-bandit settings.

ALMAB-DC optimizes expensive black-box experiments using active learning and distributed computing.

We consider the decentralized exploration problem: a set of players collaborate to identify the best arm by asynchronously interacting with the same stochastic environment. The objective is to insure privacy in the best arm identification problem between asynchronous, collaborative, and thrifty players. In the context …

MpFL models clients as strategic players to reach equilibrium with less communication.

Study Whittle index learning algorithms for restless bandits with constant stepsizes.

A federated learning algorithm tackles linear bandits with adversarial actions, achieving optimal regret bounds.

Unified framework for scalable black-box optimization.

Ringmaster ASGD improves Asynchronous SGD's efficiency under varying worker times.

A new algorithm for personalized recommendations adapts to changing user interests.

We consider an ad hoc network where multiple users access the same set of channels. The channel characteristics are unknown and could be different for each user (heterogeneous). No controller is available to coordinate channel selections by the users, and if multiple users select the same channel, they collide and none…

AEGiS optimizes expensive function evaluations asynchronously.

Secure aggregation for buffered asynchronous federated learning without TEEs.

Standard acquisition functions are sufficient for asynchronous Bayesian optimization.

Batch Bayesian optimisation (BO) has been successfully applied to hyperparameter tuning using parallel computing, but it is wasteful of resources: workers that complete jobs ahead of others are left idle. We address this problem by developing an approach, Penalising Locally for Asynchronous Bayesian Optimisation on $k$…

Asynchronous method for hyperparameter and neural architecture search.

This work tackles resource allocation in asynchronous and stochastic systems.

Advances in asynchronous optimization methods for machine learning.

As datasets continue to increase in size and multi-core computer architectures are developed, asynchronous parallel optimization algorithms become more and more essential to the field of Machine Learning. Unfortunately, conducting the theoretical analysis asynchronous methods is difficult, notably due to the introducti…

FedBuff improves federated learning scalability with asynchronous updates.

The asymptotic pseudo-trajectory approach to stochastic approximation of Benaim, Hofbauer and Sorin is extended for asynchronous stochastic approximations with a set-valued mean field. The asynchronicity of the process is incorporated into the mean field to produce convergence results which remain similar to those of a…

We show that asymptotically, completely asynchronous stochastic gradient procedures achieve optimal (even to constant factors) convergence rates for the solution of convex optimization problems under nearly the same conditions required for asymptotic optimality of standard stochastic gradient procedures. Roughly, the n…

Distributed asynchronous SGD has become widely used for deep learning in large-scale systems, but remains notorious for its instability when increasing the number of workers. In this work, we study the dynamics of distributed asynchronous SGD under the lens of Lagrangian mechanics. Using this description, we introduce …

This paper describes Plumbing for Optimization with Asynchronous Parallelism (POAP) and the Python Surrogate Optimization Toolbox (pySOT). POAP is an event-driven framework for building and combining asynchronous optimization strategies, designed for global optimization of expensive functions where concurrent function …

In machine learning, asynchronous parallel stochastic gradient descent (APSGD) is broadly used to speed up the training process through multi-workers. Meanwhile, the time delay of stale gradients in asynchronous algorithms is generally proportional to the total number of workers, which brings additional deviation from …

Unified analysis of asynchronous-SGD algorithms for distributed learning.

Paper proves CLTs for Q-learning with asynchronous updates.

Accelerates optimization in asynchronous systems with sparse updates.

Improves asynchronous federated learning with queuing dynamics.

We study optimization algorithms based on variance reduction for stochastic gradient descent (SGD). Remarkable recent progress has been made in this direction through development of algorithms like SAG, SVRG, SAGA. These algorithms have been shown to outperform SGD, both theoretically and empirically. However, asynchro…

Background: Recent developments have made it possible to accelerate neural networks training significantly using large batch sizes and data parallelism. Training in an asynchronous fashion, where delay occurs, can make training even more scalable. However, asynchronous training has its pitfalls, mainly a degradation in…