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

185 papers, page 2 of 4

51. ICML 2025Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
52. ICML 2025Learning Adversarial MDPs with Stochastic Hard Constraints
53. ICML 2025Learning With Multi-Group Guarantees For Clusterable Subpopulations
54. ICML 2025Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors
55. ICML 2025Leveraging Offline Data in Linear Latent Contextual Bandits
56. ICML 2025Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
57. ICML 2025Linear Bandits with Partially Observable Features
58. ICML 2025Logarithmic Regret for Online KL-Regularized Reinforcement Learning
59. ICML 2025Maintaining Proportional Committees with Dynamic Candidate Sets
60. ICML 2025Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
61. ICML 2025Near Optimal Non-asymptotic Sample Complexity of 1-Identification
62. ICML 2025Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems
63. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
64. ICML 2025Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback
65. ICML 2025Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
66. ICML 2025Offline Learning for Combinatorial Multi-armed Bandits
67. ICML 2025On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
68. ICML 2025Online Clustering of Dueling Bandits
69. ICML 2025Online Conformal Prediction via Online Optimization
70. ICML 2025Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting
71. ICML 2025Online Episodic Convex Reinforcement Learning
72. ICML 2025Online Laplacian-Based Representation Learning in Reinforcement Learning
73. ICML 2025Online Learning in Risk Sensitive constrained MDP
74. ICML 2025Online Learning in the Random-Order Model
75. ICML 2025Online Learning with Unknown Constraints
76. ICML 2025Online Linear Classification with Massart Noise
77. ICML 2025Online Pre-Training for Offline-to-Online Reinforcement Learning
78. ICML 2025Online Sparsification of Bipartite-Like Clusters in Graphs
79. ICML 2025Optimal Algorithm for Max-Min Fair Bandit
80. ICML 2025Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
81. ICML 2025Partially Observable Reinforcement Learning with Memory Traces
82. ICML 2025Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity
83. ICML 2025Revisiting Differentially Private Algorithms for Decentralized Online Learning
84. ICML 2025Revisiting the Predictability of Performative, Social Events
85. ICML 2025Reward-free World Models for Online Imitation Learning
86. ICML 2025Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction
87. ICML 2025Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
88. ICML 2025Sleeping Reinforcement Learning
89. ICML 2025Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
90. ICML 2025Stochastic Online Conformal Prediction with Semi-Bandit Feedback
91. ICML 2025The Batch Complexity of Bandit Pure Exploration
92. ICML 2025The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
93. ICML 2025Tracking Most Significant Shifts in Infinite-Armed Bandits
94. ICML 2025Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
95. ICML 2025Value-Based Deep RL Scales Predictably
96. ICML 2025Zero-Inflated Bandits
97. NeurIPS 2025A Learning-Augmented Approach to Online Allocation Problems
98. NeurIPS 2025Agnostic Continuous-Time Online Learning
99. NeurIPS 2025An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
100. NeurIPS 2025Asymptotic theory of SGD with a general learning-rate

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.