Image de couverture de livre

On Instability of Minimax Optimal Optimism-Based Bandit Algorithms

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Praharaj, Samya, Khamaru, Koulik
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Information Theory Statistics Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability
par: Praharaj, Samya, et autres
Publié: (2025)

UCB algorithms for multi-armed bandits: Precise regret and adaptive inference
par: Han, Qiyang, et autres
Publié: (2024)

Inference with the Upper Confidence Bound Algorithm
par: Khamaru, Koulik, et autres
Publié: (2024)

Semi-parametric inference based on adaptively collected data
par: Lin, Licong, et autres
Publié: (2023)

Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits
par: Rajaraman, Nived, et autres
Publié: (2023)

Design Stability in Adaptive Experiments: Implications for Treatment Effect Estimation
par: Sengupta, Saikat, et autres
Publié: (2025)

Minimax Optimality of the Probability Flow ODE for Diffusion Models
par: Cai, Changxiao, et autres
Publié: (2025)

Bandit Simulation for Average Reward Inference
par: Praharaj, Samya, et autres
Publié: (2026)

Minimax Rate-Optimal Algorithms for High-Dimensional Stochastic Linear Bandits
par: Liu, Jingyu, et autres
Publié: (2025)

Minimax Optimal Algorithms with Fixed-$k$-Nearest Neighbors
par: Ryu, J. Jon, et autres
Publié: (2022)

Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions
par: Zhang, Kaihong, et autres
Publié: (2024)

Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning
par: Li, Gen, et autres
Publié: (2023)

Efficient Inference after Directionally Stable Adaptive Experiments
par: Shen, Zikai, et autres
Publié: (2026)

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
par: Li, Gen, et autres
Publié: (2021)

Minimax Hypothesis Testing for the Bradley-Terry-Luce Model
par: Makur, Anuran, et autres
Publié: (2024)

Minimax optimal differentially private synthetic data for smooth queries
par: Ding, Rundong, et autres
Publié: (2026)

Minimax optimal submatrix detection: Sharp non-asymptotic rates
par: Knight, Parker, et autres
Publié: (2026)

Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm
par: Boudart, Pierre, et autres
Publié: (2025)

Optimal Regret of Bernoulli Bandits under Global Differential Privacy
par: Azize, Achraf, et autres
Publié: (2025)

Online Clustering of Data Sequences with Bandit Information
par: Chandran, G Dhinesh, et autres
Publié: (2025)

Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits
par: Xu, Yunbei, et autres
Publié: (2020)

Federated PCA and Estimation for Spiked Covariance Matrices: Optimal Rates and Efficient Algorithm
par: Li, Jingyang, et autres
Publié: (2024)

Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
par: Chen, Fan, et autres
Publié: (2024)

Asymptotically and Minimax Optimal Regret Bounds for Multi-Armed Bandits with Abstention
par: Yang, Junwen, et autres
Publié: (2024)

Optimality of Approximate Message Passing Algorithms for Spiked Matrix Models with Rotationally Invariant Noise
par: Dudeja, Rishabh, et autres
Publié: (2024)

Concentrated Differential Privacy for Bandits
par: Azize, Achraf, et autres
Publié: (2023)

Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms
par: Réveillard, William, et autres
Publié: (2025)

Optimal Anytime-Valid Tests for Composite Nulls
par: Shekhar, Shubhanshu
Publié: (2025)

$L^1$ Estimation: On the Optimality of Linear Estimators
par: Barnes, Leighton P., et autres
Publié: (2023)

Optimal training-conditional regret for online conformal prediction
par: Liang, Jiadong, et autres
Publié: (2026)

Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits
par: Zhou, Julien, et autres
Publié: (2024)

Instance-Optimal Estimation with Multiple LLM Judges on a Budget
par: Lee, Junghyun, et autres
Publié: (2026)

Sequential 1-bit Mean Estimation with Near-Optimal Sample Complexity
par: Lau, Ivan, et autres
Publié: (2025)

Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes
par: Lau, Ivan, et autres
Publié: (2026)

Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
par: Wu, Jingda, et autres
Publié: (2026)

Orthogonal Approximate Message Passing with Optimal Spectral Initializations for Rectangular Spiked Matrix Models
par: Chen, Haohua, et autres
Publié: (2025)

Fast Convergence of $Φ$-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler
par: Mitra, Siddharth, et autres
Publié: (2024)

Differentially Private Sliced Inverse Regression: Minimax Optimality and Algorithm
par: Xia, Xintao, et autres
Publié: (2024)

Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of $Φ$-Mutual Information
par: Liang, Jiaming, et autres
Publié: (2024)

Orthogonal Approximate Message Passing Algorithms for Rectangular Spiked Matrix Models with Rotationally Invariant Noise
par: Chen, Haohua, et autres
Publié: (2026)