← Back to all news
arXiv Machine Learning By M Yashwanth, Sharannya Ghosh, Saikiran Bulusu, Anirban Chakraborty

Personalized Projected Ascent for Federated Stackelberg Optimization

Read the original on arXiv Machine Learning →

The paper introduces a federated minimax framework where the minimization variable is shared across clients while each client retains a personalized maximization variable. It proposes a projected ascent method for the personalized variables and shows that in nonconvex-concave settings it achieves a sublinear convergence rate, but in nonconvex-PL settings it suffers from a noise floor. To overcome this, the authors develop VR-SGDA, a variance‑reduced algorithm that eliminates the noise floor through a two‑timescale update scheme, and demonstrate its effectiveness on subpopulation‑robustness and NLP adversarial training tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 14

High-Probability Convergence of SGD via Batched Updates

The paper introduces Batched SGD, a variant that groups online samples into epochs and performs a single update per epoch using a low‑variance gradient estimate. This batching approach allows a straightforward high‑probability analysis without restrictive assumptions or auxiliary sequences, yielding near‑optimal rates for both strongly convex and non‑convex objectives under standard smoothness and sub‑Gaussian noise conditions. The authors also extend the method to federated learning, providing the first high‑probability guarantees with logarithmic communication complexity, linear speedup in the number of agents, and robustness to data heterogeneity.

By Feng Zhu, Robert W. Heath Jr., Aritra Mitra
agents
More like this →
arXiv Machine Learning
Sep 30

Byzantine-Robust Federated Representation Learning

arXiv:2609.36660v1 Announce Type: new Abstract: We study federated learning (FL) with adversarial clients, where the goal is to minimize the average loss of the honest (non-adversarial) clients witho...

By Leonardo F. Toso, James Anderson, Rafael Pinot, Nirupam Gupta
safety
More like this →