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

389 papers, page 8 of 8

351. NeurIPS 2025On Transferring Transferability: Towards a Theory for Size Generalization
352. NeurIPS 2025On Universality Classes of Equivariant Networks
353. NeurIPS 2025Online Learning in the Repeated Mediated Newsvendor Problem
354. NeurIPS 2025Online Learning of Neural Networks
355. NeurIPS 2025Optimism Without Regularization: Constant Regret in Zero-Sum Games
356. NeurIPS 2025Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
357. NeurIPS 2025Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
358. NeurIPS 2025Price of Parsimony: Complexity of Fourier Sparsity Testing
359. NeurIPS 2025Product Distribution Learning with Imperfect Advice
360. NeurIPS 2025Regularized least squares learning with heavy-tailed noise is minimax optimal
361. NeurIPS 2025Replicable Distribution Testing
362. NeurIPS 2025Revisiting Agnostic Boosting
363. NeurIPS 2025Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
364. NeurIPS 2025Robust learning of halfspaces under log-concave marginals
365. NeurIPS 2025Robustly Learning Monotone Single-Index Models
366. NeurIPS 2025Safely Learning Controlled Stochastic Dynamics
367. NeurIPS 2025Sample-Conditional Coverage in Split-Conformal Prediction
368. NeurIPS 2025Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
369. NeurIPS 2025Sharp Matrix Empirical Bernstein Inequalities
370. NeurIPS 2025Small Singular Values Matter: A Random Matrix Analysis of Transformer Models
371. NeurIPS 2025Smoothed Agnostic Learning of Halfspaces over the Hypercube
372. NeurIPS 2025Spectral Analysis of Representational Similarity with Limited Neurons
373. NeurIPS 2025Spectral Estimation with Free Decompression
374. NeurIPS 2025State Size Independent Statistical Error Bound for Discrete Diffusion Models
375. NeurIPS 2025Streaming Attention Approximation via Discrepancy Theory
376. NeurIPS 2025Subsampled Ensemble Can Improve Generalization Tail Exponentially
377. NeurIPS 2025The Complexity of Finding Local Optima in Contrastive Learning
378. NeurIPS 2025The Computational Complexity of Counting Linear Regions in ReLU Neural Networks
379. NeurIPS 2025The Flood Complex: Large-Scale Persistent Homology on Millions of Points
380. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
381. NeurIPS 2025Tight Asymptotics of Extreme Order Statistics
382. NeurIPS 2025Tight Generalization Bounds for Large-Margin Halfspaces
383. NeurIPS 2025Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
384. NeurIPS 2025Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
385. NeurIPS 2025Two Heads are Better than One: Simulating Large Transformers with Small Ones
386. NeurIPS 2025Unbalanced Optimal Total Variation Transport: A Theoretical Approach to Spatial Resource Allocation Problems
387. NeurIPS 2025What Expressivity Theory Misses: Message Passing Complexity for GNNs
388. NeurIPS 2025When Does Curriculum Learning Help? A Theoretical Perspective
389. NeurIPS 2025Which Algorithms Have Tight Generalization Bounds?

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.