Ali Zindari — accepted AI-conference papers

2025

Decoupled SGDA for Games with Intermittent Strategy Communication

Ali Zindari, Parham Yazdkhasti, Anton Rodomanov, Tatjana Chavdarova, Sebastian U Stich

ICML 2025poster

We introduce *Decoupled SGDA*, a novel adaptation of Stochastic Gradient Descent Ascent (SGDA) tailored for multiplayer games with intermittent strategy communication. Unlike prior methods, Decoupled SGDA enables players to update strategies locally using outdated opponent strategies, significantly…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Revisiting Consensus Error: A Fine-grained Analysis of Local SGD under Second-order Data Heterogeneity

Kumar Kshitij Patel, Ali Zindari, Sebastian U Stich, Lingxiao Wang

NeurIPS 2025poster

Local SGD, or Federated Averaging, is one of the most widely used algorithms for distributed optimization. Although it often outperforms alternatives such as mini-batch SGD, existing theory has not fully explained this advantage under realistic assumptions about data heterogeneity. Recent work has s…

Cited by 0 Source ↗Scholar ↗