Amit Attia

amitattia at mail dot tau dot ac dot il

About

I'm a PhD student at the Department of Computer Science at Tel Aviv University, advised by Prof. Tomer Koren. I completed my MSc under the supervision of Tomer and before that, obtained a BSc in Computer Science and a minor in Physics from the Hebrew University of Jerusalem. My research focuses on optimization for machine learning, and in particular on convergence and generalization of first-order methods.

For a list of publications see below or on my google scholar profile.

• Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
  Amit Attia*, Matan Schliserman*, Uri Sherman, Tomer Koren

[arXiv]

• Optimal Rates in Continual Linear Regression via Increasing Regularization
  Ran Levinstein*, Amit Attia*, Matan Schliserman*, Uri Sherman*, Tomer Koren, Daniel Soudry, Itay Evron

[arXiv]

• Benefits of Learning Rate Annealing for Tuning-Robustness in Stochastic Optimization
  Amit Attia, Tomer Koren

[arXiv]

• A General Reduction for High-Probability Analysis with General Light-Tailed Distributions
  Amit Attia, Tomer Koren

[arXiv]

• Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching
  Amit Attia, Ofir Gaash, Tomer Koren
  ICML 2025

[arXiv]

• How Free is Parameter-Free Stochastic Optimization?
  Amit Attia, Tomer Koren
  ICML 2024 (Spotlight)

[arXiv]

• SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance
  Amit Attia, Tomer Koren
  ICML 2023

[arXiv]

• Uniform Stability for First-Order Empirical Risk Minimization
  Amit Attia, Tomer Koren
  COLT 2022

[arXiv]

• Algorithmic Instabilities of Accelerated Gradient Descent
  Amit Attia, Tomer Koren
  NeurIPS 2021

[arXiv]