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

328 papers, page 7 of 7

301. ICML 2025When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
302. ICML 2025When do neural networks learn world models?
303. ICML 2024A sampling theory perspective on activations for implicit neural representations
304. ICML 2024A Statistical Theory of Regularization-Based Continual Learning
305. ICML 2024A Theory of Fault-Tolerant Learning
306. ICML 2024A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
307. ICML 2024Critical windows: non-asymptotic theory for feature emergence in diffusion models
308. ICML 2024Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
309. ICML 2024Matrix Information Theory for Self-Supervised Learning
310. ICML 2024Minimum Norm Interpolation Meets The Local Theory of Banach Spaces
311. ICML 2024On Statistical Learning Theory for Distributional Inputs
312. ICML 2024Open Ad Hoc Teamwork with Cooperative Game Theory
313. ICML 2024PIDformer: Transformer Meets Control Theory
314. ICML 2024Position: Categorical Deep Learning is an Algebraic Theory of All Architectures
315. ICML 2024Position: Future Directions in the Theory of Graph Machine Learning
316. ICML 2024Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity Theory
317. ICML 2024Random matrix theory improved Fréchet mean of symmetric positive definite matrices
318. ICML 2024Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
319. ICML 2024Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction
320. ICML 2024Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
321. ICML 2024Theory of Consistency Diffusion Models: Distribution Estimation Meets Fast Sampling
322. ICML 2024Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms
323. ICML 2024Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models
324. ICML 2023Certifying Ensembles: A General Certification Theory with S-Lipschitzness
325. ICML 2023Fast Federated Machine Unlearning with Nonlinear Functional Theory
326. ICML 2023Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
327. ICML 2023Robust Collaborative Learning with Linear Gradient Overhead
328. ICML 2023Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search

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.