No article text was recorded for this version.
high-probability regret bounds
Version 2 of 2135 papers157 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
- Blog: Discussion of "Contextual Bandit Algorithms with Supervised Learning Guarantees"
- Blog: Online learning over a finite action set with limited switching
- Blog: Small-loss bounds for online learning with partial information
- Blog: Adversarial Contextual Bandits Go Kernelized
- Blog: A Regret-Variance Trade-Off in Online Learning
- Blog: First-Order Bayesian Regret Analysis of Thompson Sampling
- Blog: Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds
- Blog: Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
- Blog: Online learning over a finite action set with limited switching
- Blog: A Parameter-Free Algorithm for Misspecified Linear Contextual Bandits
- Blog: Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
- Blog: Beyond Bandit Feedback in Online Multiclass Classification
- Blog: High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions
- Blog: Online Convex Optimization in Adversarial Markov Decision Processes
- Blog: Bandit Principal Component Analysis
- Blog: Prediction with expert advice under additive noise
- Blog: Online Learning over a Finite Action Set with Limited Switching
- Blog: Adapting to Delays and Data in Adversarial Multi-Armed Bandits
- Blog: High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions
- Blog: An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits
- Blog: No-regret incentive-compatible online learning under exact truthfulness with non-myopic experts
- Blog: Logarithmic Regret for Online Gradient Descent Beyond Strong Convexity
- Blog: Exploiting the Surrogate Gap in Online Multiclass Classification
- Blog: Return of the bias: Almost minimax optimal high probability bounds for adversarial linear bandits
- Blog: Regret Analysis for Continuous Dueling Bandit
- Blog: Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards
- Blog: Online Regularized Learning Algorithm for Functional Data
- Blog: Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
- Blog: Efficient Projection-Free Online Methods with Stochastic Recursive Gradient
- Blog: An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
- Blog: Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs
- Blog: A Polynomial-time Algorithm for Online Sparse Linear Regression with Improved Regret Bound under Weaker Conditions
- Blog: Advice-Efficient Prediction with Expert Advice
- Blog: Projection-Free Online Optimization with Stochastic Gradient: From\n Convexity to Submodularity
- Blog: Understanding the Role of Feedback in Online Learning with Switching Costs
- Blog: Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
- Blog: First- and Second-Order Bounds for Adversarial Linear Contextual Bandits
- Blog: Bayesian Design Principles for Frequentist Sequential Learning
- Blog: Safe Online Convex Optimization with Heavy-Tailed Observation Noises
- Blog: Anytime optimal algorithms in stochastic multi-armed bandits
- Blog: Efficient improper learning for online logistic regression
- Blog: No Internal Regret via Neighborhood Watch
- Blog: An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits
- Blog: Optimistic Planning by Regularized Dynamic Programming
- Blog: Online Linear Programming: Dual Convergence, New Algorithms, and Regret Bounds
- Blog: Prediction by random-walk perturbation
- Blog: Contextual Bandit Algorithms with Supervised Learning Guarantees
- Blog: Refined Lower Bounds for Adversarial Bandits
- Blog: Best of Both Worlds Model Selection
- Blog: Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs
- Blog: Nonstochastic Bandits and Experts with Arm-Dependent Delays
- Blog: Understanding the Role of Feedback in Online Learning with Switching Costs
- Blog: Towards Provably Efficient Learning of Imperfect Information Extensive-Form Games with Linear Function Approximation
- Blog: Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits
- Blog: Towards Minimax Policies for Online Linear Optimization with Bandit Feedback
- Blog: From exp-concavity to variance control: O(1/n) rates and online-to-batch conversion with high probability
- Blog: Parameter-free Online Convex Optimization with Sub-Exponential Noise
- Blog: Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games
- Blog: Adapting to Online Label Shift with Provable Guarantees
Showing 60 of 135 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_high_probability_regret_bounds_8a54cec5,
title = {high-probability regret bounds},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/high-probability-regret-bounds/rdr_8a54cec5f00c438fb4f05fbff0d27f87},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_high_probability_regret_bounds_8a54cec5_v2,
title = {high-probability regret bounds},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/high-probability-regret-bounds/rdr_8a54cec5f00c438fb4f05fbff0d27f87/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}