Imagen de Portada

Thompson sampling: Precise arm-pull dynamics and adaptive inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Han, Qiyang
Formato:	Preprint
Publicado:	2026
Materias:	Statistics Theory Information Theory Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

UCB algorithms for multi-armed bandits: Precise regret and adaptive inference
por: Han, Qiyang, et al.
Publicado: (2024)

Long-time dynamics and universality of nonconvex gradient descent
por: Han, Qiyang
Publicado: (2025)

Gradient descent inference in empirical risk minimization
por: Han, Qiyang, et al.
Publicado: (2024)

Entrywise dynamics and universality of general first order methods
por: Han, Qiyang
Publicado: (2024)

Precise gradient descent training dynamics for finite-width multi-layer neural networks
por: Han, Qiyang, et al.
Publicado: (2025)

Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models
por: Zhang, Yihan, et al.
Publicado: (2022)

Precise analysis of ridge interpolators under heavy correlations -- a Random Duality Theory view
por: Stojnic, Mihailo
Publicado: (2024)

The distribution of Ridgeless least squares interpolators
por: Han, Qiyang, et al.
Publicado: (2023)

Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery
por: Kovačević, Filip, et al.
Publicado: (2025)

Gaussian random projections of convex cones: approximate kinematic formulae and applications
por: Han, Qiyang, et al.
Publicado: (2022)

Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits
por: Rajaraman, Nived, et al.
Publicado: (2023)

Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
por: Chen, Fan, et al.
Publicado: (2024)

On the sample complexity of parameter estimation in logistic regression with normal design
por: Hsu, Daniel, et al.
Publicado: (2023)

A leave-one-out approach to approximate message passing
por: Bao, Zhigang, et al.
Publicado: (2023)

Online selective conformal inference: adaptive scores, convergence rate and optimality
por: Humbert, Pierre, et al.
Publicado: (2025)

Information-Geometric Decomposition of Generalization Error in Unsupervised Learning
por: Kim, Gilhan
Publicado: (2026)

Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
por: Dmitriev, Daniil, et al.
Publicado: (2026)

Sample efficient inductive matrix completion with noise and inexact side information
por: Yang, Yuepeng, et al.
Publicado: (2026)

Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
por: Lovig, Max
Publicado: (2026)

Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes
por: Lau, Ivan, et al.
Publicado: (2026)

Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
por: Wu, Jingda, et al.
Publicado: (2026)

Breaking the Finite-Sample Barrier in Entropy Coupling
por: Asoodeh, Shahab, et al.
Publicado: (2026)

Orthogonal Approximate Message Passing Algorithms for Rectangular Spiked Matrix Models with Rotationally Invariant Noise
por: Chen, Haohua, et al.
Publicado: (2026)

Minimax optimal differentially private synthetic data for smooth queries
por: Ding, Rundong, et al.
Publicado: (2026)

Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
por: Miyagawa, Taiki, et al.
Publicado: (2026)

Minimax optimal submatrix detection: Sharp non-asymptotic rates
por: Knight, Parker, et al.
Publicado: (2026)

Adaptation to Intrinsic Dependence in Diffusion Language Models
por: Zhao, Yunxiao, et al.
Publicado: (2026)

Optimal training-conditional regret for online conformal prediction
por: Liang, Jiadong, et al.
Publicado: (2026)

On the Nonasymptotic Scaling Guarantee of Hyperparameter Estimation in Inhomogeneous, Weakly-Dependent Complex Network Dynamical Systems
por: Yu, Yi, et al.
Publicado: (2026)

Instance-Optimal Estimation with Multiple LLM Judges on a Budget
por: Lee, Junghyun, et al.
Publicado: (2026)

On Observation Time for Recovering Latent Hawkes Networks
por: Linkerhägner, Jonas, et al.
Publicado: (2026)

Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data
por: Chaabouni, Youssef, et al.
Publicado: (2026)

On the Sample Complexity of Robust Binary Hypothesis Testing
por: Vallinayagam, Shankar, et al.
Publicado: (2026)

Fine-Grained Uncertainty Quantification via Collisions
por: Friedbaum, Jesse, et al.
Publicado: (2024)

Statistical-Computational Trade-offs in Tensor PCA and Related Problems via Communication Complexity
por: Dudeja, Rishabh, et al.
Publicado: (2022)

Online Clustering of Data Sequences with Bandit Information
por: Chandran, G Dhinesh, et al.
Publicado: (2025)

Efficient Unbiased Sparsification
por: Barnes, Leighton, et al.
Publicado: (2024)

Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions
por: Zhang, Kaihong, et al.
Publicado: (2024)

Top-$K$ ranking with a monotone adversary
por: Yang, Yuepeng, et al.
Publicado: (2024)

Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of $Φ$-Mutual Information
por: Liang, Jiaming, et al.
Publicado: (2024)