works on

From the 1 of 9 linked papers with an AI index.

activity
20242026
most citedThe Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication

1 citations · 1 across the 3 of their papers we have counts for

collaborators

9 papers

cs.LG20261 cited

The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication

Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari +5

The paper analyzes the theoretical limits of Local SGD for distributed learning with heterogeneous data, showing existing heterogeneity assumptions are insufficient for proving its…

cs.LG2026

On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials

Rotem Mulayoff, Sebastian U. Stich

The dynamical stability of the iterates during training plays a key role in determining the minima obtained by optimization algorithms. For example, stable solutions of gradient de…

cs.LG2026

Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning

Polina Dolgova, Sebastian U. Stich

Certified unlearning based on differential privacy offers strong guarantees but remains largely impractical: the noisy fine-tuning approaches proposed so far achieve these guarante…

cs.GT2025

Monotone Near-Zero-Sum Games: A Generalization of Convex-Concave Minimax

Ruichen Luo, Sebastian U. Stich, Krishnendu Chatterjee

Zero-sum and non-zero-sum (aka general-sum) games are relevant in a wide range of applications. While general non-zero-sum games are computationally hard, researchers focus on the…

cs.CV2025

Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts

Yasin Esfandiari, Stefan Bauer, Sebastian U. Stich +1

Diffusion models for image generation often exhibit a trade-off between perceptual sample quality and data likelihood: training objectives emphasizing high-noise denoising steps yi…

math.OC2025

Monotone and nonmonotone linearized block coordinate descent methods for nonsmooth composite optimization problems

Yassine Nabou, Lahcen El Bourkhissi, Sebastian U. Stich +1

In this paper, we introduce both monotone and nonmonotone variants of LiBCoD, a \textbf{Li}nearized \textbf{B}lock \textbf{Co}ordinate \textbf{D}escent method for solving composite…