Matan Schliserman

About Me

I'm a PhD student in the Department of Computer Science at Tel Aviv University, where I'm advised by Prof. Tomer Koren. I previously completed my MSc under his supervision, following a BSc in Computer Science and Mathematics from the Hebrew University of Jerusalem. My research focuses on optimization and generalization in machine learning.

Matan Schliserman

Preprints

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]

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification

Matan Schliserman, Tomer Koren

[arXiv]

From Continual Learning to SGD and Back: Better Rates for Continual Linear Models

Itay Evron*, Ran Levinstein*, Matan Schliserman*, Uri Sherman*, Tomer Koren, Daniel Soudry, Nathan Srebro

[arXiv]

Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization

Matan Schliserman, Tomer Koren

[arXiv]

Publications

The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization

Matan Schliserman, Uri Sherman, Tomer Koren

ALT 2025, Outstanding paper award

[arXiv]

Tight risk bounds for gradient descent on separable data

Matan Schliserman, Tomer Koren

NeurIPS 2023, Spotlight

[arXiv]

Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond

Matan Schliserman, Tomer Koren

COLT 2022

[arXiv]