Skip to main content

News

New preprint on differentially private Clipped-SGD

A new preprint studies high-probability convergence with an arbitrary clipping level.

arXiv:2507.23512

ICLR and ICML 2025 papers, new preprints, and MBZUAI appointment

New preprints, talks, and ICML presentation

  • New preprints on gradient clipping under heavy-tailed noise and personalized federated learning.
  • Talks at PODC 2024, INSAIT, and EURO 2024 covered Byzantine-robust learning and last-iterate convergence.
  • ICML oral presentation with slides, poster, and paper.

Research Scientist appointment, conference updates, and a new preprint

  • I started as a Research Scientist at MBZUAI on April 1, 2024.
  • AISTATS 2024 presentations covered heavy-tailed noise and Byzantine robust learning.
  • One paper was accepted to ICML 2024 for oral presentation, and a new preprint on Jacobian inexactness in variational inequalities was posted.

Two new preprints and a FLOW talk

  • New preprints on median clipping for zeroth-order optimization and adaptive client aggregation in federated learning.
  • FLOW talk: Variance Reduction for Byzantine-Robust Distributed Optimization. Slides and video.

New preprints, a talk, and NeurIPS 2023 papers

Seven new preprints were added, including work on intermediate gradient methods, heavy-tailed stochastic minimization, Byzantine robust learning, and distributed variational inequalities.

  • Talk at TES Conference on Mathematical Optimization for Machine Learning.
  • Three papers were accepted to NeurIPS 2023 on stochastic extragradient methods, accelerated zeroth-order methods, and Byzantine-tolerant distributed variational inequalities.
Earlier updates8 updates, 2022-2023

New preprints, Hamburg talk, and ICML posters

  • Three new preprints covered heavy-tailed bandits, partial personalization in federated learning, and distributed gradient clipping.
  • Talk at the LT Group Oberseminar, University of Hamburg, on heavy-tailed stochastic optimization.
  • ICML posters were added to the talks and posters archive.

ICML 2023 papers

Two papers were accepted to ICML 2023.

  1. Convergence beyond monotonicity for proximal point and extragradient-based methods.
  2. High-probability bounds for stochastic optimization and variational inequalities with unbounded variance.

AISTATS, ICLR, PEP talk, and new preprints

  • One paper was accepted to AISTATS 2023 and one paper was accepted to ICLR 2023.
  • Talk at PEP talks in Belgium.
  • Five new preprints were posted, including work on stochastic variational inequalities and Byzantine-robust optimization.

Preprint on negative comonotonicity

New preprint on convergence of proximal point and extragradient-based methods beyond monotonicity.

Talk at MBZUAI Collaborative Learning Workshop

Presentation on variance reduction for Byzantine-robust distributed optimization.

Outstanding Reviewer Award, NeurIPS 2022

Outstanding Reviewer Award at NeurIPS 2022.

NeurIPS 2022 papers

Two papers were accepted to NeurIPS 2022.

  1. Clipped stochastic methods for variational inequalities with heavy-tailed noise.
  2. Last-iterate convergence of optimistic gradient method for monotone variational inequalities.