Gabriel Mancino-Ball — accepted AI-conference papers

2024

Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization

Xuan Zhang, Gabriel Mancino-Ball, Necdet Serhat Aybat, Yangyang Xu

AAAI 2024technical

We propose a novel single-loop decentralized algorithm, DGDA-VR, for solving the stochastic nonconvex strongly-concave minimax problems over a connected network of agents, which are equipped with stochastic first-order oracles to estimate their local gradients. DGDA-VR, incorporating variance reduct…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2023

Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimization

Gabriel Mancino-Ball, Shengnan Miao, Yangyang Xu, Jie Chen

AAAI 2023technical

Consider a network of N decentralized computing agents collaboratively solving a nonconvex stochastic composite problem. In this work, we propose a single-loop algorithm, called DEEPSTORM, that achieves optimal sample complexity for this setting. Unlike double-loop algorithms that require a large ba…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗