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

169 papers, page 3 of 4

101. NeurIPS 2024On Weak Regret Analysis for Dueling Bandits
102. NeurIPS 2024Online Adaptation of Language Models with a Memory of Amortized Contexts
103. NeurIPS 2024Online Bayesian Persuasion Without a Clue
104. NeurIPS 2024Online Budgeted Matching with General Bids
105. NeurIPS 2024Online Classification with Predictions
106. NeurIPS 2024Online Composite Optimization Between Stochastic and Adversarial Environments
107. NeurIPS 2024Online Consistency of the Nearest Neighbor Rule
108. NeurIPS 2024Online Control in Population Dynamics
109. NeurIPS 2024Online Control with Adversarial Disturbance for Continuous-time Linear Systems
110. NeurIPS 2024Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously
111. NeurIPS 2024Online Estimation via Offline Estimation: An Information-Theoretic Framework
112. NeurIPS 2024Online Learning of Delayed Choices
113. NeurIPS 2024Online Learning with Sublinear Best-Action Queries
114. NeurIPS 2024Online Non-convex Learning in Dynamic Environments
115. NeurIPS 2024Online Posterior Sampling with a Diffusion Prior
116. NeurIPS 2024Online Weighted Paging with Unknown Weights
117. NeurIPS 2024Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
118. NeurIPS 2024Optimal Batched Best Arm Identification
119. NeurIPS 2024Optimal Multi-Fidelity Best-Arm Identification
120. NeurIPS 2024Optimal Multiclass U-Calibration Error and Beyond
121. NeurIPS 2024Optimal Top-Two Method for Best Arm Identification and Fluid Analysis
122. NeurIPS 2024Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits
123. NeurIPS 2024Overcoming Brittleness in Pareto-Optimal Learning Augmented Algorithms
124. NeurIPS 2024Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits
125. NeurIPS 2024Piecewise-Stationary Bandits with Knapsacks
126. NeurIPS 2024Preference-based Pure Exploration
127. NeurIPS 2024Private Online Learning via Lazy Algorithms
128. NeurIPS 2024PRODuctive bandits: Importance Weighting No More
129. NeurIPS 2024Provably Efficient Interactive-Grounded Learning with Personalized Reward
130. NeurIPS 2024Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning
131. NeurIPS 2024Queueing Matching Bandits with Preference Feedback
132. NeurIPS 2024RanDumb: Random Representations Outperform Online Continually Learned Representations
133. NeurIPS 2024Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training
134. NeurIPS 2024Reciprocal Learning
135. NeurIPS 2024REDUCR: Robust Data Downsampling using Class Priority Reweighting
136. NeurIPS 2024Regret Minimization in Stackelberg Games with Side Information
137. NeurIPS 2024Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
138. NeurIPS 2024RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
139. NeurIPS 2024Robust Neural Contextual Bandit against Adversarial Corruptions
140. NeurIPS 2024Saliency-driven Experience Replay for Continual Learning
141. NeurIPS 2024Sample Complexity of Posted Pricing for a Single Item
142. NeurIPS 2024Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning
143. NeurIPS 2024Sample-efficient Bayesian Optimisation Using Known Invariances
144. NeurIPS 2024Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
145. NeurIPS 2024Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
146. NeurIPS 2024Smoothed Online Classification can be Harder than Batch Classification
147. NeurIPS 2024Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
148. NeurIPS 2024Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling
149. NeurIPS 2024Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language Tasks
150. NeurIPS 2024State-free Reinforcement Learning

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.