Cover Image

Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Yunbei, Yuan, Yuzhe, Zhan, Ruohan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Statistical Properties of Robust Satisficing
by: Li, Zhiyi, et al.
Published: (2024)

Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits
by: Xu, Yunbei, et al.
Published: (2020)

Sharp Lower Bounds for Linearized ReLU^k Approximation on the Sphere
by: Mao, Tong, et al.
Published: (2025)

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

Data-dependent and Oracle Bounds on Forgetting in Continual Learning
by: Friedman, Lior, et al.
Published: (2024)

Finite-Time Minimax Bounds and an Optimal Lyapunov Policy in Queueing Control
by: Liu, Yujie, et al.
Published: (2025)

Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles
by: Ji, Kaiyi
Published: (2025)

Sharp Structure-Agnostic Lower Bounds for General Linear Functional Estimation
by: Jin, Jikai, et al.
Published: (2025)

Sharp Bounds for Sequential Federated Learning on Heterogeneous Data
by: Li, Yipeng, et al.
Published: (2024)

Better-than-KL PAC-Bayes Bounds
by: Kuzborskij, Ilja, et al.
Published: (2024)

Information Theoretic Lower Bounds for Information Theoretic Upper Bounds
by: Livni, Roi
Published: (2023)

Lower Bounds for Time-Varying Kernelized Bandits
by: Cai, Xu, et al.
Published: (2024)

Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning
by: Liu, Zhishuai, et al.
Published: (2024)

Towards Sharp Minimax Risk Bounds for Operator Learning
by: Adcock, Ben, et al.
Published: (2025)

Lower Bounds for the Algorithmic Complexity of Learned Indexes
by: Croquevielle, Luis Alberto, et al.
Published: (2026)

Post Reinforcement Learning Inference
by: Syrgkanis, Vasilis, et al.
Published: (2023)

Is Multi-Distribution Learning as Easy as PAC Learning: Sharp Rates with Bounded Label Noise
by: Hanashiro, Rafael, et al.
Published: (2026)

Bayesian Design Principles for Frequentist Sequential Learning
by: Xu, Yunbei, et al.
Published: (2023)

Reliable Abstention under Adversarial Injections: Tight Lower Bounds and New Upper Bounds
by: Edelman, Ezra, et al.
Published: (2026)

Towards Robust Out-of-Distribution Generalization Bounds via Sharpness
by: Zou, Yingtian, et al.
Published: (2024)

Statistical Query Lower Bounds for Smoothed Agnostic Learning
by: Diakonikolas, Ilias, et al.
Published: (2026)

Achieving Upper Bound Accuracy of Joint Training in Continual Learning
by: Momeni, Saleh, et al.
Published: (2025)

Optimal Lower Bounds for Online Multicalibration
by: Collina, Natalie, et al.
Published: (2026)

On the Natural Gradient of the Evidence Lower Bound
by: Ay, Nihat, et al.
Published: (2023)

Sharp Bounds for Poly-GNNs and the Effect of Graph Noise
by: Vinas, Luciano, et al.
Published: (2024)

Lower Bounds for Public-Private Learning under Distribution Shift
by: Setlur, Amrith, et al.
Published: (2025)

Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems
by: Ziemann, Ingvar, et al.
Published: (2022)

Rising Rested Bandits: Lower Bounds and Efficient Algorithms
by: Fiandri, Marco, et al.
Published: (2024)

Lower Bounds on the MMSE of Adversarially Inferring Sensitive Features
by: Welfert, Monica, et al.
Published: (2025)

Lower Bounds on Learning Pauli Channels with Individual Measurements
by: Fawzi, Omar, et al.
Published: (2023)

Noise Sensitivity and Learning Lower Bounds for Hierarchical Functions
by: Li, Rupert, et al.
Published: (2025)

Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
by: Chen, Shulun, et al.
Published: (2025)

Smart Predict-then-Optimize Method with Dependent Data: Risk Bounds and Calibration of Autoregression
by: Liu, Jixian, et al.
Published: (2024)

Improving Autoregressive Training with Dynamic Oracles
by: Yang, Jianing, et al.
Published: (2024)

Lower Bounds on the Size of Markov Equivalence Classes
by: Jahn, Erik, et al.
Published: (2025)

Statistical Query Lower Bounds for Learning Truncated Gaussians
by: Diakonikolas, Ilias, et al.
Published: (2024)

Sharp Risk Bounds for Early-Stopping in Gaussian Linear Regression
by: Wegel, Tobias, et al.
Published: (2025)

A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces
by: Sinen, Tim
Published: (2026)

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
by: Zhao, Heyang, et al.
Published: (2024)

Approximation Error Upper and Lower Bounds for Hölder Class with Transformers
by: He, Xin, et al.
Published: (2026)