No article text was recorded for this version.
first-order regret bounds
Version 1 of 138 papers50 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Minimizing Wide Range Regret with Time Selection Functions
- Blog: Adaptive Regret of Convex and Smooth Functions
- Blog: Beyond Logarithmic Bounds in Online Learning
- Blog: On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits
- Blog: Small-loss bounds for online learning with partial information
- Blog: Unconstrained Online Learning with Unbounded Losses
- Blog: Adapting to Smoothness: A More Universal Algorithm for Online Convex Optimization
- Blog: Open Problem: First-Order Regret Bounds for Contextual Bandits
- Blog: Conservative Contextual Bandits: Beyond Linear Representations
- Blog: Dynamic Regret of Convex and Smooth Functions
- Blog: Weighted Last-Step Min-Max Algorithm with Improved Sub-Logarithmic Regret
- Blog: Optimistic Information Directed Sampling
- Blog: The SMART approach to instance-optimal online learning
- Blog: Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
- Blog: Data-Dependent Regret Bounds for Constrained MABs
- 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: Improved Regret Bounds for Online Kernel Selection under Bandit Feedback
- Blog: A Blackbox Approach to Best of Both Worlds in Bandits and Beyond
- Blog: First-Order Bayesian Regret Analysis of Thompson Sampling
- Blog: Adaptive Oracle-Efficient Online Learning
- Blog: Improved Algorithms for Adversarial Bandits with Unbounded Losses
- Blog: Small-loss Adaptive Regret for Online Convex Optimization
- Blog: Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses
- Blog: Contextual Bandits with Online Neural Regression
- Blog: First-order regret bounds for combinatorial semi-bandits
- Blog: Improved Regret Guarantees for Online Smooth Convex Optimization with Bandit Feedback
- Blog: A Parameter-free Hedging Algorithm
- Blog: A Closer Look at Small-loss Bounds for Bandits with Graph Feedback
- Blog: UCB-based Algorithms for Multinomial Logistic Regression Bandits
- Blog: ZigZag: A New Approach to Adaptive Online Learning
- Blog: Online mirror descent and dual averaging: keeping pace in the dynamic case
- Blog: Universal Caching
- Blog: Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds
- Blog: A Simple yet Universal Strategy for Online Convex Optimization
- Blog: Adversarial Linear Contextual Bandits with Graph-Structured Side Observations
- Blog: Tracking the Best Expert
- Blog: Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints
History & citation
Current · Permanent link
- This direction split from Small Loss Bounds for Adaptive Online Learning (79% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_first_order_regret_bounds_1c087536,
title = {first-order regret bounds},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/first-order-regret-bounds/rdr_1c087536ebfd4895bff3fac56a01d793},
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_first_order_regret_bounds_1c087536_v1,
title = {first-order regret bounds},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/first-order-regret-bounds/rdr_1c087536ebfd4895bff3fac56a01d793/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}