Optimizing for Generalization in Machine Learning

Project Information

OPTGEN

Grant agreement ID: 101078075

DOI

10.3030/101078075

EC signature date 7 December 2022

Start date 1 October 2023

End date 30 September 2028

Funded under

• European Research Council (ERC)

Total cost

€ 1 494 375,00

EU contribution

€ 1 494 375,00

Coordinated by

TEL AVIV UNIVERSITY
Israel

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (15)

Fast Rates for Bandit PAC Multiclass Classification

Author(s): Liad Erez, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran
Published in: NeurIPS 2024, 2024
Publisher: Advances in Neural Information Processing Systems

The Real Price of Bandit Information in Multiclass Classification

Author(s): Liad Erez, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran
Published in: COLT 2024, 2024
Publisher: Annual Conference on Learning Theory

Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching

Author(s): Amit Attia, Tomer Koren
Published in: ICML 2025, 2025
Publisher: International Conference on Machine Learning

Optimal Rates in Continual Linear Regression via Increasing Regularization

Author(s): Ran Levinstein, Amit Attia, Matan Schliserman, Uri Sherman, Tomer Koren, Daniel Soudry, Itay Evron
Published in: NeurIPS 2025, 2025
Publisher: Advances in Neural Information Processing Systems

How Free is Parameter-Free Stochastic Optimization?

Author(s): Amit Attia, Tomer Koren
Published in: ICML 2024, 2024
Publisher: International Conference on Machine Learning

Faster Convergence with Multiway Preferences

Author(s): Aadirupa Saha, Vitaly Feldman, Tomer Koren, Yishay Mansour
Published in: AISTATS 2024, 2024
Publisher: International Conference on Artificial Intelligence and Statistics

Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime

Author(s): Amit Attia, Matan Schliserman, Uri Sherman, Tomer Koren
Published in: NeurIPS 2025, 2025
Publisher: Advances in Neural Information Processing Systems

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

Author(s): Matan Schliserman, Tomer Koren
Published in: NeurIPS 2025, 2025
Publisher: Advances in Neural Information Processing Systems

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

Author(s): Matan Schliserman, Uri Sherman, Tomer Koren
Published in: ALT 2025, 2025
Publisher: Annual Conference on Algorithmic Learning Theory

Rate-Optimal Policy Optimization for Linear Markov Decision Processes

Author(s): Uri Sherman, Alon Cohen, Tomer Koren, Yishay Mansour
Published in: ICML 2024, 2024
Publisher: International Conference on Machine Learning

From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards

Author(s): Liad Erez, Tomer Koren
Published in: NeurIPS 2025, 2025
Publisher: Advances in Neural Information Processing Systems

Dueling Convex Optimization with General Preferences

Author(s): Aadirupa Saha, Tomer Koren, Yishay Mansour
Published in: ICML 2025, 2025
Publisher: International Conference on Machine Learning

Tight Risk Bounds for Gradient Descent on Separable Data

Author(s): Matan Schliserman, Tomer Koren
Published in: NeurIPS 2023, 2023
Publisher: Advances in Neural Information Processing Systems

Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization

Author(s): Shira Vansover-Hager, Tomer Koren, Roi Livni
Published in: ICML 2025, 2025
Publisher: International Conference on Machine Learning

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation

Author(s): Uri Sherman, Tomer Koren, Yishay Mansour
Published in: ICML 2025, 2025
Publisher: International Conference on Machine Learning