Theory · learning theory papers, 2023–2026

Key findings

• Theory · learning theory went from 86 papers in 2023 to 482 in 2026, roughly 5.6x in three years.
• NeurIPS publishes the most Theory · learning theory work: 540 papers from 2023 to 2026, 40% of the four-venue total.
• The fastest-growing overlap is with Social aspects · accountability transparency and interpretability: papers tagged with both rose from 0 in 2023 to 33 in 2026.
• Among the 5 topics under Theory and Statistics, it ranks #2 by 2026 paper count; the fastest grower in the group, Theory · optimization, is up 4.7x versus 5.6x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A dynamical systems theory of reward-modulated learning in linear recurrent networks
• ICML 2026A Fine-Grained Understanding of Uniform Convergence for Halfspaces
• ICLR 2026A Law of Data Reconstruction for Random Features (And Beyond)
• NeurIPS 2025A Geometric Analysis of PCA
• ICML 2025A Generalization Theory for Zero-Shot Prediction
• ICLR 2025A Solvable Attention for Neural Scaling Laws
• CVPR 2025Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation
• NeurIPS 20244+3 Phases of Compute-Optimal Neural Scaling Laws
• ICML 2024A Statistical Theory of Regularization-Based Continual Learning
• ICLR 2024A Sublinear Adversarial Training Algorithm
• CVPR 2024Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
• NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
• ICML 2023Robust Collaborative Learning with Linear Gradient Overhead
• ICLR 2023Bispectral Neural Networks
• NeurIPS 2026A Mechanistic Investigation of Theory of Mind in a Large Language Model
• ICML 2026A Random Matrix Theory of Masked Self-Supervised Learning
• ICLR 2026A New Approach to Controlling Linear Dynamical Systems
• NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
• ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
• ICLR 2025A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

All Theory · learning theory papers

57 papers, page 1 of 2

1. NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
2. NeurIPS 2023A Measure-Theoretic Axiomatisation of Causality
3. NeurIPS 2023A Theory of Multimodal Learning
4. NeurIPS 2023A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
5. NeurIPS 2023Accelerating Value Iteration with Anchoring
6. NeurIPS 2023Agnostic Multi-Group Active Learning
7. NeurIPS 2023Alternation makes the adversary weaker in two-player games
8. NeurIPS 2023Bandit Social Learning under Myopic Behavior
9. NeurIPS 2023Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
10. NeurIPS 2023Bridging RL Theory and Practice with the Effective Horizon
11. NeurIPS 2023Characterization of Overfitting in Robust Multiclass Classification
12. NeurIPS 2023Common Ground in Cooperative Communication
13. NeurIPS 2023Delegated Classification
14. NeurIPS 2023Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback
15. NeurIPS 2023Equivariant Neural Operator Learning with Graphon Convolution
16. NeurIPS 2023Estimating the Rate-Distortion Function by Wasserstein Gradient Descent
17. NeurIPS 2023Faster Relative Entropy Coding with Greedy Rejection Coding
18. NeurIPS 2023Feature Selection in the Contrastive Analysis Setting
19. NeurIPS 2023Finding Safe Zones of Markov Decision Processes Policies
20. NeurIPS 2023Generalized Belief Transport
21. NeurIPS 2023Information Theoretic Lower Bounds for Information Theoretic Upper Bounds
22. NeurIPS 2023Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
23. NeurIPS 2023Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning
24. NeurIPS 2023Max-Sliced Mutual Information
25. NeurIPS 2023Nash Regret Guarantees for Linear Bandits
26. NeurIPS 2023Near-Linear Time Algorithm for the Chamfer Distance
27. NeurIPS 2023New Bounds for Hyperparameter Tuning of Regression Problems Across Instances
28. NeurIPS 2023No-regret Algorithms for Fair Resource Allocation
29. NeurIPS 2023On Generalization Bounds for Projective Clustering
30. NeurIPS 2023On kernel-based statistical learning theory in the mean field limit
31. NeurIPS 2023On Slicing Optimality for Mutual Information
32. NeurIPS 2023On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm
33. NeurIPS 2023Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games
34. NeurIPS 2023Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
35. NeurIPS 2023Provable benefits of score matching
36. NeurIPS 2023Provably Safe Reinforcement Learning with Step-wise Violation Constraints
37. NeurIPS 2023Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework
38. NeurIPS 2023Reliable learning in challenging environments
39. NeurIPS 2023Replicability in Reinforcement Learning
40. NeurIPS 2023Replicable Clustering
41. NeurIPS 2023Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning
42. NeurIPS 2023Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms
43. NeurIPS 2023Sharp Spectral Rates for Koopman Operator Learning
44. NeurIPS 2023Similarity-based cooperative equilibrium
45. NeurIPS 2023Smoothed Analysis of Sequential Probability Assignment
46. NeurIPS 2023Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory
47. NeurIPS 2023Strategic Data Sharing between Competitors
48. NeurIPS 2023Structured Prediction with Stronger Consistency Guarantees
49. NeurIPS 2023Temporally Disentangled Representation Learning under Unknown Nonstationarity
50. NeurIPS 2023The Crucial Role of Normalization in Sharpness-Aware Minimization

FAQ

How many Theory · learning theory papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,350 in total: 86 in 2023, 393 in 2024, 389 in 2025, 482 in 2026.

How many Theory · learning theory papers are at NeurIPS 2026?

NeurIPS 2026 has 112 Theory · learning theory papers, versus 106 the year before.

How many Theory · learning theory papers are at ICLR 2026?

ICLR 2026 has 200 Theory · learning theory papers, versus 147 the year before.

How many Theory · learning theory papers are at ICML 2026?

ICML 2026 has 170 Theory · learning theory papers, versus 132 the year before.

How many Theory · learning theory papers are at CVPR 2025?

CVPR 2025 has 4 Theory · learning theory papers, versus 1 the year before.

Which conference publishes the most Theory · learning theory papers?

NeurIPS, with 540 papers from 2023 to 2026.