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

427 papers, page 2 of 9

51. NeurIPS 2026OWCE: Revealing Language Model Complementarity via Online Weakness-Conditioned Evaluation
52. NeurIPS 2026Personalized and Collaborative Online LQR via Thompson Sampling
53. NeurIPS 2026Posterior Sampling-based Online Learning for Episodic POMDPs
54. NeurIPS 2026Propagation of Chaos in Contextual Flow Maps
55. NeurIPS 2026Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
56. NeurIPS 2026Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning
57. NeurIPS 2026Replicable Constrained Bandits
58. NeurIPS 2026Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees
59. NeurIPS 2026RL-Inf: Tracking Non-local Training Data Influence for Online Reinforcement Learning
60. NeurIPS 2026Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
61. NeurIPS 2026Speed Predictions for Online Energy-Efficient Scheduling
62. NeurIPS 2026Strongly Adaptive Online Learning with Time-Varying Movement Cost
63. NeurIPS 2026Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
64. NeurIPS 2026The Minimax Rate of Online Isotonic Regression on Product Orders
65. NeurIPS 2026The Power of a Random Sample in Online Algorithms
66. NeurIPS 2026Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference
67. NeurIPS 2026Toward Online Robust Zero-Sum Markov Games with Function Approximation
68. NeurIPS 2026When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon
69. NeurIPS 2025A Learning-Augmented Approach to Online Allocation Problems
70. NeurIPS 2025Agnostic Continuous-Time Online Learning
71. NeurIPS 2025An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
72. NeurIPS 2025Asymptotic theory of SGD with a general learning-rate
73. NeurIPS 2025Bandit and Delayed Feedback in Online Structured Prediction
74. NeurIPS 2025Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization
75. NeurIPS 2025Computable universal online learning
76. NeurIPS 2025Conformal Online Learning of Deep Koopman Linear Embeddings
77. NeurIPS 2025Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning
78. NeurIPS 2025Consistency of the $k_n$-nearest neighbor rule under adaptive sampling
79. NeurIPS 2025Contextual Online Pricing with (Biased) Offline Data
80. NeurIPS 2025Dynamic Regret Reduces to Kernelized Static Regret
81. NeurIPS 2025Efficient Last-Iterate Convergence in Solving Extensive-Form Games
82. NeurIPS 2025Efficient Spectral Control of Partially Observed Linear Dynamical Systems
83. NeurIPS 2025Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
84. NeurIPS 2025Explaining the Law of Supply and Demand via Online Learning
85. NeurIPS 2025Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
86. NeurIPS 2025Exploring the Noise Robustness of Online Conformal Prediction
87. NeurIPS 2025Fair Matroid Selection
88. NeurIPS 2025Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control
89. NeurIPS 2025From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
90. NeurIPS 2025Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
91. NeurIPS 2025Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
92. NeurIPS 2025Gradient-Guided Epsilon Constraint Method for Online Continual Learning
93. NeurIPS 2025High-Dimensional Calibration from Swap Regret
94. NeurIPS 2025HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location
95. NeurIPS 2025Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
96. NeurIPS 2025Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
97. NeurIPS 2025Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints
98. NeurIPS 2025Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
99. NeurIPS 2025Kernel conditional tests from learning-theoretic bounds
100. NeurIPS 2025Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria

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.