Theory · online learning papers, 2023–2026

Key findings

• Theory · online learning went from 164 papers in 2023 to 190 in 2026, roughly 1.2x in three years.
• NeurIPS publishes the most Theory · online learning work: 427 papers from 2023 to 2026, 56% of the four-venue total.
• The fastest-growing overlap is with Simulation for Driving: papers tagged with both rose from 1 in 2023 to 12 in 2026.
• Among the 5 topics under Theory and Statistics, it ranks #3 by 2026 paper count; the fastest grower in the group, Theory · learning theory, is up 5.6x versus 1.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming
• ICML 2026A Perturbation Approach to Unconstrained Linear Bandits
• ICLR 2026Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
• CVPR 2026An Optimal Transport-driven Approach for Cultivating Latent Space in Online
• NeurIPS 2025A Learning-Augmented Approach to Online Allocation Problems
• ICML 2025A Classification View on Meta Learning Bandits
• ICLR 2025Efficient Online Pruning and Abstraction for Imperfect Information Extensive-Form Games
• CVPR 2025InteractionMap: Improving Online Vectorized HDMap Construction with Interaction
• NeurIPS 2024A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
• ICML 2024On Online Experimentation without Device Identifiers
• ICLR 2024Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
• CVPR 2024Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning
• NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
• ICML 2023Applied Online Algorithms with Heterogeneous Predictors
• ICLR 2023Hebbian Deep Learning Without Feedback
• CVPR 2023VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos
• NeurIPS 2026A Theory of Adversary-Directed Online Learning
• ICML 2026A Two-Layer Framework for Joint Online Configuration Selection and Admission Control
• ICLR 2026A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers
• CVPR 2026Dynamic Momentum Recalibration in Online Gradient Learning

All Theory · online learning papers

224 papers, page 3 of 5

101. NeurIPS 2024Fair Online Bilateral Trade
102. NeurIPS 2024Fairness and Efficiency in Online Class Matching
103. NeurIPS 2024Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
104. NeurIPS 2024Fast Rates for Bandit PAC Multiclass Classification
105. NeurIPS 2024Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
106. NeurIPS 2024Fixed Confidence Best Arm Identification in the Bayesian Setting
107. NeurIPS 2024Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
108. NeurIPS 2024Fully Unconstrained Online Learning
109. NeurIPS 2024Generalized Linear Bandits with Limited Adaptivity
110. NeurIPS 2024Global Rewards in Restless Multi-Armed Bandits
111. NeurIPS 2024Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints
112. NeurIPS 2024Gradient-Variation Online Learning under Generalized Smoothness
113. NeurIPS 2024GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration
114. NeurIPS 2024Group-wise oracle-efficient algorithms for online multi-group learning
115. NeurIPS 2024HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting
116. NeurIPS 2024Honor Among Bandits: No-Regret Learning for Online Fair Division
117. NeurIPS 2024How Does Variance Shape the Regret in Contextual Bandits?
118. NeurIPS 2024Identifying Equivalent Training Dynamics
119. NeurIPS 2024Improved Algorithms for Contextual Dynamic Pricing
120. NeurIPS 2024Improved Analysis for Bandit Learning in Matching Markets
121. NeurIPS 2024Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
122. NeurIPS 2024Improved learning rates in multi-unit uniform price auctions
123. NeurIPS 2024Improved Regret for Bandit Convex Optimization with Delayed Feedback
124. NeurIPS 2024Improved Regret of Linear Ensemble Sampling
125. NeurIPS 2024Information-theoretic Limits of Online Classification with Noisy Labels
126. NeurIPS 2024Label Delay in Online Continual Learning
127. NeurIPS 2024Learning from Snapshots of Discrete and Continuous Data Streams
128. NeurIPS 2024Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
129. NeurIPS 2024Learning to Price Homogeneous Data
130. NeurIPS 2024Learning-Augmented Algorithms with Explicit Predictors
131. NeurIPS 2024Linear Causal Bandits: Unknown Graph and Soft Interventions
132. NeurIPS 2024Local and Adaptive Mirror Descents in Extensive-Form Games
133. NeurIPS 2024Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
134. NeurIPS 2024Localized Adaptive Risk Control
135. NeurIPS 2024Locally Private and Robust Multi-Armed Bandits
136. NeurIPS 2024Lookback Prophet Inequalities
137. NeurIPS 2024Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
138. NeurIPS 2024Maximizing utility in multi-agent environments by anticipating the behavior of other learners
139. NeurIPS 2024MetaCURL: Non-stationary Concave Utility Reinforcement Learning
140. NeurIPS 2024Mixture of Experts Meets Prompt-Based Continual Learning
141. NeurIPS 2024Multi-model Ensemble Conformal Prediction in Dynamic Environments
142. NeurIPS 2024Multiclass Transductive Online Learning
143. NeurIPS 2024Mutli-Armed Bandits with Network Interference
144. NeurIPS 2024Near-Optimality of Contrastive Divergence Algorithms
145. NeurIPS 2024Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
146. NeurIPS 2024Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
147. NeurIPS 2024No-Regret Bandit Exploration based on Soft Tree Ensemble Model
148. NeurIPS 2024No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
149. NeurIPS 2024No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
150. NeurIPS 2024Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset

FAQ

How many Theory · online learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

763 in total: 164 in 2023, 224 in 2024, 185 in 2025, 190 in 2026.

How many Theory · online learning papers are at NeurIPS 2026?

NeurIPS 2026 has 68 Theory · online learning papers, versus 89 the year before.

How many Theory · online learning papers are at ICLR 2026?

ICLR 2026 has 27 Theory · online learning papers, versus 18 the year before.

How many Theory · online learning papers are at ICML 2026?

ICML 2026 has 86 Theory · online learning papers, versus 74 the year before.

How many Theory · online learning papers are at CVPR 2026?

CVPR 2026 has 9 Theory · online learning papers, versus 4 the year before.

Which conference publishes the most Theory · online learning papers?

NeurIPS, with 427 papers from 2023 to 2026.