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

74 papers, page 1 of 2

1. ICML 2025A Classification View on Meta Learning Bandits
2. ICML 2025A Online Statistical Framework for Out-of-Distribution Detection
3. ICML 2025A Parametric Contextual Online Learning Theory of Brokerage
4. ICML 2025A Trichotomy for List Transductive Online Learning
5. ICML 2025AKORN: Adaptive Knots generated Online for RegressioN splines
6. ICML 2025Algorithms with Calibrated Machine Learning Predictions
7. ICML 2025Avoiding Catastrophe in Online Learning by Asking for Help
8. ICML 2025Best of Both Worlds: Regret Minimization versus Minimax Play
9. ICML 2025Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
10. ICML 2025Clustering Items through Bandit Feedback: Finding the Right Feature out of Many
11. ICML 2025Competitively Consistent Clustering
12. ICML 2025Constrained Online Convex Optimization with Polyak Feasibility Steps
13. ICML 2025Constrained Pareto Set Identification with Bandit Feedback
14. ICML 2025Contextual Bandits for Unbounded Context Distributions
15. ICML 2025Contextual Linear Bandits with Delay as Payoff
16. ICML 2025Contextual Online Decision Making with Infinite-Dimensional Functional Regression
17. ICML 2025DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models
18. ICML 2025Dimension-Free Adaptive Subgradient Methods with Frequent Directions
19. ICML 2025Exploiting Curvature in Online Convex Optimization with Delayed Feedback
20. ICML 2025Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
21. ICML 2025Fixed-Confidence Multiple Change Point Identification under Bandit Feedback
22. ICML 2025Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
23. ICML 2025Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems
24. ICML 2025Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
25. ICML 2025Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
26. ICML 2025High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions
27. ICML 2025High-Dimensional Prediction for Sequential Decision Making
28. ICML 2025Improved Online Confidence Bounds for Multinomial Logistic Bandits
29. ICML 2025Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
30. ICML 2025Learning Adversarial MDPs with Stochastic Hard Constraints
31. ICML 2025Learning With Multi-Group Guarantees For Clusterable Subpopulations
32. ICML 2025Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors
33. ICML 2025Leveraging Offline Data in Linear Latent Contextual Bandits
34. ICML 2025Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
35. ICML 2025Linear Bandits with Partially Observable Features
36. ICML 2025Logarithmic Regret for Online KL-Regularized Reinforcement Learning
37. ICML 2025Maintaining Proportional Committees with Dynamic Candidate Sets
38. ICML 2025Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
39. ICML 2025Near Optimal Non-asymptotic Sample Complexity of 1-Identification
40. ICML 2025Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems
41. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
42. ICML 2025Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback
43. ICML 2025Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
44. ICML 2025Offline Learning for Combinatorial Multi-armed Bandits
45. ICML 2025On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
46. ICML 2025Online Clustering of Dueling Bandits
47. ICML 2025Online Conformal Prediction via Online Optimization
48. ICML 2025Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting
49. ICML 2025Online Episodic Convex Reinforcement Learning
50. ICML 2025Online Laplacian-Based Representation Learning in 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.