Image de couverture de livre

Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dann, Christoph, Mansour, Yishay, Mohri, Mehryar
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rate-Preserving Reductions for Blackwell Approachability
par: Dann, Christoph, et autres
Publié: (2024)

Mind the Gap: Structure-Aware Consistency in Preference Learning
par: Mohri, Mehryar, et autres
Publié: (2026)

Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms
par: Mao, Anqi, et autres
Publié: (2023)

Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning
par: Mohri, Mehryar, et autres
Publié: (2026)

Cost-Aware Learning
par: Mohri, Clara, et autres
Publié: (2026)

Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention
par: Mao, Anqi, et autres
Publié: (2023)

Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data
par: Cortes, Corinna, et autres
Publié: (2025)

Rational Transductors
par: Mohri, Mehryar
Publié: (2026)

A Theoretical Framework for Modular Learning of Robust Generative Models
par: Cortes, Corinna, et autres
Publié: (2026)

Improved Balanced Classification with Theoretically Grounded Loss Functions
par: Cortes, Corinna, et autres
Publié: (2025)

Algorithms for Learning Kernels Based on Centered Alignment
par: Cortes, Corinna, et autres
Publié: (2012)

Swap Regret and Correlated Equilibria Beyond Normal-Form Games
par: Arunachaleswaran, Eshwar Ram, et autres
Publié: (2025)

Principled Algorithms for Optimizing Generalized Metrics in Binary Classification
par: Mao, Anqi, et autres
Publié: (2025)

Top-$k$ Classification and Cardinality-Aware Prediction
par: Mao, Anqi, et autres
Publié: (2024)

Cardinality-Aware Set Prediction and Top-$k$ Classification
par: Cortes, Corinna, et autres
Publié: (2024)

Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
par: Mohri, Mehryar, et autres
Publié: (2026)

Beyond Tsybakov: Model Margin Noise and $\mathcal{H}$-Consistency Bounds
par: Mohri, Mehryar, et autres
Publié: (2025)

Optimal Regret for Policy Optimization in Contextual Bandits
par: Levy, Orin, et autres
Publié: (2026)

Principled Approaches for Learning to Defer with Multiple Experts
par: Mao, Anqi, et autres
Publié: (2023)

Multi-Label Learning with Stronger Consistency Guarantees
par: Mao, Anqi, et autres
Publié: (2024)

Differentially Private Domain Adaptation with Theoretical Guarantees
par: Bassily, Raef, et autres
Publié: (2023)

A Universal Growth Rate for Learning with Smooth Surrogate Losses
par: Mao, Anqi, et autres
Publié: (2024)

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
par: Lancewicki, Tal, et autres
Publié: (2025)

Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
par: Mao, Anqi, et autres
Publié: (2024)

Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
par: Mao, Anqi, et autres
Publié: (2025)

Fast Inference via Hierarchical Speculative Decoding
par: Mohri, Clara, et autres
Publié: (2025)

Budgeted Multiple-Expert Deferral
par: DeSalvo, Giulia, et autres
Publié: (2025)

Generalized Distributional Alignment Games for Unbiased Answer-Level Fine-Tuning
par: Mohri, Mehryar, et autres
Publié: (2026)

Regression with Multi-Expert Deferral
par: Mao, Anqi, et autres
Publié: (2024)

$H$-Consistency Guarantees for Regression
par: Mao, Anqi, et autres
Publié: (2024)

Coherence Mechanisms for Provable Self-Improvement
par: Mohri, Mehryar, et autres
Publié: (2025)

Enhanced $H$-Consistency Bounds
par: Mao, Anqi, et autres
Publié: (2024)

Learning-Augmented Algorithms with Explicit Predictors
par: Elias, Marek, et autres
Publié: (2024)

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
par: Sherman, Uri, et autres
Publié: (2025)

Rising Rested MAB with Linear Drift
par: Amichay, Omer, et autres
Publié: (2025)

Non-stochastic Bandits With Evolving Observations
par: Bar-On, Yogev, et autres
Publié: (2024)

Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization
par: Jiang, Ruichen, et autres
Publié: (2026)

Distributional Alignment Games for Answer-Level Fine-Tuning
par: Mohri, Mehryar, et autres
Publié: (2026)

A Theoretical Framework for Statistical Evaluability of Generative Models
par: Aiyer, Shashaank, et autres
Publié: (2026)

Online Learning in MDPs with Partially Adversarial Transitions and Losses
par: Schlisselberg, Ofir, et autres
Publié: (2026)