No article text was recorded for this version.
best-of-both-worlds adaptation
Version 2 of 2339 papers619 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Best of Both Worlds: Stochastic and Adversarial Bandits
- Blog: An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits
- Blog: Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs
- Blog: A Blackbox Approach to Best of Both Worlds in Bandits and Beyond
- Blog: Bidding Strategies for Proportional Representation in Advertisement Campaigns
- Blog: Best of both worlds: Stochastic & adversarial best-arm identification
- Blog: Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
- Blog: Best-of-Both-Worlds Linear Contextual Bandits
- Blog: An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
- Blog: Pareto Regret Analyses in Multi-objective Multi-armed Bandit
- Blog: Best-of-Both-Worlds Algorithms for Partial Monitoring
- Blog: Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
- Blog: An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
- Blog: An Optimal Algorithm for Stochastic and Adversarial Bandits
- Blog: Online Learning with Knapsacks: the Best of Both Worlds
- Blog: An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
- Blog: Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
- Blog: An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits
- Blog: Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
- Blog: An Optimal Algorithm for Stochastic and Adversarial Bandits
- Blog: Unifying the stochastic and the adversarial Bandits with Knapsack
- Blog: Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
- Blog: The best of both worlds: stochastic and adversarial bandits
- Blog: A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds
- Blog: Towards Optimal Adaptive Wireless Communications in Unknown Environments
- Blog: Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems
- Blog: Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
- Blog: Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
- Blog: Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits
- Blog: A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints
- Blog: A Unifying Framework for Online Optimization with Long-Term Constraints
- Blog: Better Best of Both Worlds Bounds for Bandits with Switching Costs
- Blog: Open Problem: Shifting Experts on Easy Data
- Blog: An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits
- Blog: Competitive Analysis with a Sample and the Secretary Problem
- Blog: Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
- Blog: Pareto Regret Analyses in Multi-objective Multi-armed Bandit
- Blog: Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments
- Blog: Simultaneously Learning Stochastic and Adversarial Markov Decision Process with Linear Function Approximation
- Blog: Best of Both Worlds Model Selection
- Blog: On the optimality of the Hedge algorithm in the stochastic regime
- Blog: uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
- Blog: Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition
- Blog: Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
- Blog: A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs
- Blog: Improved Analysis of Robustness of the Tsallis-INF Algorithm to Adversarial Corruptions in Stochastic Multiarmed Bandits
- Blog: A Unifying Framework for Online Safe Optimization
- Blog: An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits
- Blog: Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
- Blog: Online Bidding in Repeated Non-Truthful Auctions under Budget and ROI Constraints
- Blog: Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning
- Blog: Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
- Blog: Regularized Online Allocation Problems: Fairness and Beyond
- Blog: One Practical Algorithm for Both Stochastic and Adversarial Bandits
- Blog: Online Resource Allocation with Non-Stationary Customers
- Blog: Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
- Blog: Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
- Blog: Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
- Blog: Best of many worlds: Robust model selection for online supervised learning
- Blog: Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model
Showing 60 of 339 papers.
History & citation
Current · Permanent link
- Optimal Bandit Learning via Heavy-Tailed Perturbations merged into this direction (62% overlap)
- Unified Regret Optimality for Stochastic and Adversarial Environments merged into this direction (87% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_best_of_both_worlds_adaptation_01065b88,
title = {best-of-both-worlds adaptation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/best-of-both-worlds-adaptation/rdr_01065b88eeb446b9b9e0f2a02097ef6f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_best_of_both_worlds_adaptation_01065b88_v2,
title = {best-of-both-worlds adaptation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/best-of-both-worlds-adaptation/rdr_01065b88eeb446b9b9e0f2a02097ef6f/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}