No article text was recorded for this version.
second-order regret bounds
Version 1 of 1128 papers175 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A simple multi-armed bandit algorithm with optimal variation-bounded regret
- Blog: A second order regret bound for NormalHedge
- Blog: Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds
- Blog: Improved Second-Order Bounds for Prediction with Expert Advice
- Blog: Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach
- Blog: Temporal Variability in Implicit Online Learning
- Blog: Open Problem: Second order regret bounds based on scaling time
- Blog: On Stochastic and Worst-case Models for Investing
- Blog: Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
- Blog: Variance-aware decision making with linear function approximation under heavy-tailed rewards
- Blog: Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
- Blog: Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications
- Blog: Improved Path-length Regret Bounds for Bandits
- Blog: Corruption-Robust Variance-aware Algorithms for Generalized Linear Bandits under Heavy-tailed Rewards
- Blog: Extracting certainty from uncertainty: regret bounded by variation in costs
- Blog: Online Learning Problems against Dynamic Strategies in Gradually Evolving Worlds
- Blog: More Adaptive Algorithms for Adversarial Bandits
- Blog: How Does Variance Shape the Regret in Contextual Bandits?
- Blog: Gradient-Variation Bound for Online Convex Optimization with Constraints
- Blog: Online Learning with Predictable Sequences
- Blog: Learning the Learning Rate for Prediction with Expert Advice
- Blog: Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning
- Blog: Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning
- Blog: Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm
- Blog: Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
- Blog: Parameter-free Algorithms for the Stochastically Extended Adversarial Model
- Blog: Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds
- Blog: Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
- Blog: Accelerated Rates between Stochastic and Adversarial Online Convex Optimization
- Blog: Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP
- Blog: Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits
- Blog: Online Optimization with Gradual Variations
- Blog: Bandit Regret Scaling with the Effective Loss Range
- Blog: Improved Online Confidence Bounds for Multinomial Logistic Bandits
- Blog: Multi-Play Combinatorial Semi-Bandit Problem
- Blog: Modifying Squint for Prediction with Expert Advice in a Changing Environment
- Blog: Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs
- Blog: Tracking the Best Expert in Non-stationary Stochastic Environments
- Blog: Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits
- Blog: Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
- Blog: Beating Bandits in Gradually Evolving Worlds
- Blog: Adaptation to Easy Data in Prediction with Limited Advice
- Blog: On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit
- Blog: Online Learning: Stochastic and Constrained Adversaries
- Blog: Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions
- Blog: Dynamic Regret of Online Markov Decision Processes
- Blog: Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variation
- Blog: On Optimal Robustness to Adversarial Corruption in Online Decision Problems
- Blog: Gradient-Variation Bound for Online Convex Optimization with Constraints
- Blog: Fast Convergence of Regularized Learning in Games
- Blog: Online Learning with Feedback Graphs: Beyond Bandits
- Blog: Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
- Blog: Second-order Quantile Methods for Experts and Combinatorial Games
- Blog: On Adaptivity in Information-constrained Online Learning
- Blog: Adversarial Blocking Bandits
- Blog: Sparsity, variance and curvature in multi-armed bandits
- Blog: Higher-Order Regret Bounds with Switching Costs
- Blog: Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
- Blog: A Regret-Variance Trade-Off in Online Learning
- Blog: Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency
Showing 60 of 128 papers.
History & citation
Current · Permanent link
- Variance Adaptive Online Learning merged into this direction (92% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_second_order_regret_bounds_53648034,
title = {second-order regret bounds},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/second-order-regret-bounds/rdr_5364803473d040bdbd4f119af4c0ed07},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_second_order_regret_bounds_53648034_v1,
title = {second-order regret bounds},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/second-order-regret-bounds/rdr_5364803473d040bdbd4f119af4c0ed07/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}