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

540 papers, page 1 of 11

1. NeurIPS 2026A dynamical systems theory of reward-modulated learning in linear recurrent networks
2. NeurIPS 2026A Mechanistic Investigation of Theory of Mind in a Large Language Model
3. NeurIPS 2026A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces
4. NeurIPS 2026A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts
5. NeurIPS 2026A Theory of Adversary-Directed Online Learning
6. NeurIPS 2026A Theory of Spatial Continuous Attractors in Hopfield Energy Landscapes
7. NeurIPS 2026A Theory of Training Profit-Optimal LLMs
8. NeurIPS 2026A Theory on Flow Matching with Neural Networks
9. NeurIPS 2026A Unified Spectral Theory of Multimodal Losses
10. NeurIPS 2026Adaptive Calibration in Non-Stationary Environments
11. NeurIPS 2026An exact information theory of generalization phase transitions in Bayesian diffusion models
12. NeurIPS 2026Approximate Envy-Free Allocations up to any k Goods
13. NeurIPS 2026Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds
14. NeurIPS 2026Avoiding Obfuscation with Prover-Estimator Debate
15. NeurIPS 2026Best Arm Identification for Bandits with Shifting Means
16. NeurIPS 2026Bilinear Matching Bandits
17. NeurIPS 2026Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
18. NeurIPS 2026Borda-Based Fair Multi-User Dueling Bandit in Tabular and Generalized Linear Settings
19. NeurIPS 2026Canonical Predictive Quotients: A Theory of Prediction under Hidden Predictive State Uncertainty with ICL Implications
20. NeurIPS 2026Chain of Dual Structures in Transformer Attention
21. NeurIPS 2026Characterizing Learning in Deep Neural Networks using a Tractable Algorithmic Complexity Estimator
22. NeurIPS 2026Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machine
23. NeurIPS 2026Constrained MDPs with Trajectory Constraints
24. NeurIPS 2026Curvature-Dependent Lower Bounds for Riemannian Online Convex Optimization
25. NeurIPS 2026Data-Free Metrics Are Not Invariant Under Functionality-Preserving Reparametrisations
26. NeurIPS 2026Decentralized Coupled Representation Learning
27. NeurIPS 2026Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics
28. NeurIPS 2026Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
29. NeurIPS 2026Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits
30. NeurIPS 2026Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence
31. NeurIPS 2026Estimating Implicit Regularization in Deep Learning
32. NeurIPS 2026Estimating the expected output of wide random MLPs more efficiently than sampling
33. NeurIPS 2026Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
34. NeurIPS 2026Fast Learning Rates for Physics-Informed Kernel Methods
35. NeurIPS 2026Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design
36. NeurIPS 2026First-Order Regret for Online Convex Optimization with Memory and Online Nonstochastic Control
37. NeurIPS 2026Fixed Universal Transformers
38. NeurIPS 2026Foundations of Categorical Equivariant Deep Learning
39. NeurIPS 2026From POMDP Theory to Deep RL with Particle Filters
40. NeurIPS 2026Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems
41. NeurIPS 2026Generalization Bounds for Neural Networks with Sparse Connectivity
42. NeurIPS 2026Generating in the Limit with Infinitely Many Hallucinations
43. NeurIPS 2026Global Convergence in Deep Networks via the Second Law of Thermodynamics
44. NeurIPS 2026Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
45. NeurIPS 2026High dimensional theory of two-phase optimizers
46. NeurIPS 2026High-arity Sample Compression
47. NeurIPS 2026How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization
48. NeurIPS 2026Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data Attribution
49. NeurIPS 2026Improved Algorithms for Online Classification with Surrogate Losses
50. NeurIPS 2026Inference and Uncertainty Quantification for Streaming $r$-PCA

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.