Search Results for author:
Found 9 papers, 1 papers with code
DASA: Delay-Adaptive Multi-Agent Stochastic Approximation
We consider a setting in which $N$ agents aim to speedup a common Stochastic Approximation (SA) problem by acting in parallel and communicating with a central server.
Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling
Motivated by applications in large-scale and multi-agent reinforcement learning, we study the non-asymptotic performance of stochastic approximation (SA) schemes with delayed updates under Markovian sampling.
Score-Based Methods for Discrete Optimization in Deep Learning
One class of these problems involve objective functions which depend on neural networks, but optimization variables which are discrete.
Min-Max Optimization under Delays
Motivated by this gap, we examine the performance of standard min-max optimization algorithms with delayed gradient updates.
Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds
We consider a linear stochastic bandit problem involving $M$ agents that can collaborate via a central server to minimize regret.
Distributed Statistical Min-Max Learning in the Presence of Byzantine Agents
Recent years have witnessed a growing interest in the topic of min-max optimization, owing to its relevance in the context of generative adversarial networks (GANs), robust control and optimization, and reinforcement learning.
Minimax Optimization: The Case of Convex-Submodular
Prior literature has thus far mainly focused on studying such problems in the continuous domain, e. g., convex-concave minimax optimization is now understood to a significant extent.
Submodular Meta-Learning
Motivated by this terminology, we propose a novel meta-learning framework in the discrete domain where each task is equivalent to maximizing a set function under a cardinality constraint.
Optimal Algorithms for Submodular Maximization with Distributed Constraints
Given this distributed setting, we develop Constraint-Distributed Continuous Greedy (CDCG), a message passing algorithm that converges to the tight $(1-1/e)$ approximation factor of the optimum global solution using only local computation and communication.
