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

393 papers, page 1 of 8

1. CVPR 2024Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
2. ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
3. ICLR 2024A path-norm toolkit for modern networks: consequences, promises and challenges
4. ICLR 2024A Policy Gradient Method for Confounded POMDPs
5. ICLR 2024A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data
6. ICLR 2024A Sublinear Adversarial Training Algorithm
7. ICLR 2024Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
8. ICLR 2024Adaptive Regret for Bandits Made Possible: Two Queries Suffice
9. ICLR 2024Algorithms for Caching and MTS with reduced number of predictions
10. ICLR 2024An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
11. ICLR 2024An Efficient Tester-Learner for Halfspaces
12. ICLR 2024Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
13. ICLR 2024Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning
14. ICLR 2024Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
15. ICLR 2024BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
16. ICLR 2024Beating Price of Anarchy and Gradient Descent without Regret in Potential Games
17. ICLR 2024Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
18. ICLR 2024Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
19. ICLR 2024Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
20. ICLR 2024Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback
21. ICLR 2024Convergence of Bayesian Bilevel Optimization
22. ICLR 2024Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
23. ICLR 2024Distinguished In Uniform: Self-Attention Vs. Virtual Nodes
24. ICLR 2024Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
25. ICLR 2024Enhancing Neural Training via a Correlated Dynamics Model
26. ICLR 2024Fantastic Generalization Measures are Nowhere to be Found
27. ICLR 2024Feature Collapse
28. ICLR 2024Feature emergence via margin maximization: case studies in algebraic tasks
29. ICLR 2024Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem
30. ICLR 2024General Stability Analysis for Zeroth-Order Optimization Algorithms
31. ICLR 2024Generalization error of spectral algorithms
32. ICLR 2024Generalization of Scaled Deep ResNets in the Mean-Field Regime
33. ICLR 2024Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
34. ICLR 2024Harnessing Density Ratios for Online Reinforcement Learning
35. ICLR 2024High-dimensional SGD aligns with emerging outlier eigenspaces
36. ICLR 2024Horizon-Free Regret for Linear Markov Decision Processes
37. ICLR 2024How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
38. ICLR 2024How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
39. ICLR 2024How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
40. ICLR 2024Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
41. ICLR 2024Implicit regularization of deep residual networks towards neural ODEs
42. ICLR 2024Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
43. ICLR 2024Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
44. ICLR 2024Incentivized Truthful Communication for Federated Bandits
45. ICLR 2024Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
46. ICLR 2024Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
47. ICLR 2024Koopman-based generalization bound: New aspect for full-rank weights
48. ICLR 2024Learning Conditional Invariances through Non-Commutativity
49. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
50. ICLR 2024Learning Hierarchical Polynomials with Three-Layer Neural Networks

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.