Cover Image

The Hidden Cost of Approximation in Online Mirror Descent

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schlisselberg, Ofir, Sherman, Uri, Koren, Tomer, Mansour, Yishay
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
by: Sherman, Uri, et al.
Published: (2025)

Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning
by: Sherman, Uri, et al.
Published: (2025)

Online Learning in MDPs with Partially Adversarial Transitions and Losses
by: Schlisselberg, Ofir, et al.
Published: (2026)

Rate-Optimal Policy Optimization for Linear Markov Decision Processes
by: Sherman, Uri, et al.
Published: (2023)

Collaborating in Multi-Armed Bandits with Strategic Agents
by: Barnea, Idan, et al.
Published: (2026)

Regret Minimization and Convergence to Equilibria in General-sum Markov Games
by: Erez, Liad, et al.
Published: (2022)

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
by: Schlisselberg, Ofir, et al.
Published: (2025)

Delay as Payoff in MAB
by: Schlisselberg, Ofir, et al.
Published: (2024)

Cost-Aware Learning
by: Mohri, Clara, et al.
Published: (2026)

The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
by: Schliserman, Matan, et al.
Published: (2024)

Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
by: Attia, Amit, et al.
Published: (2025)

The impact of allocation strategies in subset learning on the expressive power of neural networks
by: Schlisselberg, Ofir, et al.
Published: (2025)

The Real Price of Bandit Information in Multiclass Classification
by: Erez, Liad, et al.
Published: (2024)

Fast Rates for Bandit PAC Multiclass Classification
by: Erez, Liad, et al.
Published: (2024)

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
by: Schliserman, Matan, et al.
Published: (2025)

Faster Stochastic Optimization with Arbitrary Delays via Asynchronous Mini-Batching
by: Attia, Amit, et al.
Published: (2024)

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
by: Lancewicki, Tal, et al.
Published: (2025)

Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back
by: Cohen, Alon, et al.
Published: (2025)

The Sample Complexity of Multiclass and Sparse Contextual Bandits
by: Erez, Liad, et al.
Published: (2026)

Bayesian Perspective on Memorization and Reconstruction
by: Kaplan, Haim, et al.
Published: (2025)

Optimal Rates in Continual Linear Regression via Increasing Regularization
by: Levinstein, Ran, et al.
Published: (2025)

From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
by: Evron, Itay, et al.
Published: (2025)

Probably Approximately Precision and Recall Learning
by: Cohen, Lee, et al.
Published: (2024)

Rapid Overfitting of Multi-Pass Stochastic Gradient Descent in Stochastic Convex Optimization
by: Vansover-Hager, Shira, et al.
Published: (2025)

Rising Rested MAB with Linear Drift
by: Amichay, Omer, et al.
Published: (2025)

Optimal Regret for Policy Optimization in Contextual Bandits
by: Levy, Orin, et al.
Published: (2026)

Non-stochastic Bandits With Evolving Observations
by: Bar-On, Yogev, et al.
Published: (2024)

Online Set Learning from Precision and Recall Feedback
by: Cohen, Lee, et al.
Published: (2026)

Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
by: Levy, Orin, et al.
Published: (2025)

Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation
by: Levy, Orin, et al.
Published: (2026)

Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization
by: Schliserman, Matan, et al.
Published: (2024)

How to Boost Any Loss Function
by: Nock, Richard, et al.
Published: (2024)

Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization
by: Attia, Amit, et al.
Published: (2025)

From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
by: Erez, Liad, et al.
Published: (2025)

How Free is Parameter-Free Stochastic Optimization?
by: Attia, Amit, et al.
Published: (2024)

The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
by: Barnea, Idan, et al.
Published: (2026)

Batch Ensemble for Variance Dependent Regret in Stochastic Bandits
by: Cassel, Asaf, et al.
Published: (2024)

Individual Regret in Cooperative Stochastic Multi-Armed Bandits
by: Barnea, Idan, et al.
Published: (2024)

Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning
by: Dann, Christoph, et al.
Published: (2026)

A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability
by: Attias, Idan, et al.
Published: (2022)