Tomer Koren

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

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

Optimal Rates in Continual Linear Regression via Increasing Regularization

Nearly Optimal Sample Complexity for Learning with Label Proportions

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation

Dueling Convex Optimization with General Preferences

Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization

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

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

Fast Rates for Bandit PAC Multiclass Classification

Private Online Learning via Lazy Algorithms

Optimal Rates for Convex Optimization with Multiway Preferences

Locally Optimal Descent for Adaptive Stepsize Scheduling