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 2 of 5

51. ICML 2024Position: Machine Learning-powered Assessments of the EU Digital Services Act Aid Quantify Policy Impacts on Online Harms
52. ICML 2024Predictive Linear Online Tracking for Unknown Targets
53. ICML 2024Rethinking Momentum Knowledge Distillation in Online Continual Learning
54. ICML 2024Scalable Online Exploration via Coverability
55. ICML 2024Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
56. NeurIPS 2024A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
57. NeurIPS 2024A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
58. NeurIPS 2024A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds
59. NeurIPS 2024A Simple and Optimal Approach for Universal Online Learning with Gradient Variations
60. NeurIPS 2024A Theory of Optimistically Universal Online Learnability for General Concept Classes
61. NeurIPS 2024A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
62. NeurIPS 2024Accelerated Regularized Learning in Finite N-Person Games
63. NeurIPS 2024Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
64. NeurIPS 2024Adaptive Experimentation When You Can't Experiment
65. NeurIPS 2024Adaptive Passive-Aggressive Framework for Online Regression with Side Information
66. NeurIPS 2024Adaptive Sampling for Efficient Softmax Approximation
67. NeurIPS 2024Addressing Bias in Online Selection with Limited Budget of Comparisons
68. NeurIPS 2024Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
69. NeurIPS 2024Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
70. NeurIPS 2024An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints
71. NeurIPS 2024An engine not a camera: Measuring performative power of online search
72. NeurIPS 2024An Equivalence Between Static and Dynamic Regret Minimization
73. NeurIPS 2024Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
74. NeurIPS 2024Bandits with Abstention under Expert Advice
75. NeurIPS 2024Bandits with Preference Feedback: A Stackelberg Game Perspective
76. NeurIPS 2024Bandits with Ranking Feedback
77. NeurIPS 2024Barely Random Algorithms and Collective Metrical Task Systems
78. NeurIPS 2024Bayesian Online Natural Gradient (BONG)
79. NeurIPS 2024Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
80. NeurIPS 2024Beyond task diversity: provable representation transfer for sequential multitask linear bandits
81. NeurIPS 2024Can large language models explore in-context?
82. NeurIPS 2024Communication Bounds for the Distributed Experts Problem
83. NeurIPS 2024Contextual Active Model Selection
84. NeurIPS 2024Contextual Decision-Making with Knapsacks Beyond the Worst Case
85. NeurIPS 2024Contextual Multinomial Logit Bandits with General Value Functions
86. NeurIPS 2024Continual Learning with Global Alignment
87. NeurIPS 2024Continual learning with the neural tangent ensemble
88. NeurIPS 2024CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
89. NeurIPS 2024Convergence of No-Swap-Regret Dynamics in Self-Play
90. NeurIPS 2024Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
91. NeurIPS 2024Dealing with Synthetic Data Contamination in Online Continual Learning
92. NeurIPS 2024Disentangling and mitigating the impact of task similarity for continual learning
93. NeurIPS 2024Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms
94. NeurIPS 2024Dueling over Dessert, Mastering the Art of Repeated Cake Cutting
95. NeurIPS 2024Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition
96. NeurIPS 2024Efficient Prompt Optimization Through the Lens of Best Arm Identification
97. NeurIPS 2024Enhancing Preference-based Linear Bandits via Human Response Time
98. NeurIPS 2024Ensemble sampling for linear bandits: small ensembles suffice
99. NeurIPS 2024Extensive-Form Game Solving via Blackwell Approachability on Treeplexes
100. NeurIPS 2024F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental 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.