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 8 of 8

351. NeurIPS 2024Testably Learning Polynomial Threshold Functions
352. NeurIPS 2024The Benefits of Balance: From Information Projections to Variance Reduction
353. NeurIPS 2024The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
354. NeurIPS 2024The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
355. NeurIPS 2024The Implicit Bias of Gradient Descent on Separable Multiclass Data
356. NeurIPS 2024The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
357. NeurIPS 2024The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
358. NeurIPS 2024The Many Faces of Optimal Weak-to-Strong Learning
359. NeurIPS 2024The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
360. NeurIPS 2024The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective
361. NeurIPS 2024The Power of Resets in Online Reinforcement Learning
362. NeurIPS 2024The Price of Implicit Bias in Adversarially Robust Generalization
363. NeurIPS 2024The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems
364. NeurIPS 2024The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
365. NeurIPS 2024Theoretical Foundations of Deep Selective State-Space Models
366. NeurIPS 2024Tight Bounds for Learning RUMs from Small Slates
367. NeurIPS 2024Tolerant Algorithms for Learning with Arbitrary Covariate Shift
368. NeurIPS 2024Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
369. NeurIPS 2024Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models
370. NeurIPS 2024Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
371. NeurIPS 2024Towards a theory of how the structure of language is acquired by deep neural networks
372. NeurIPS 2024Towards the Dynamics of a DNN Learning Symbolic Interactions
373. NeurIPS 2024Trade-Offs of Diagonal Fisher Information Matrix Estimators
374. NeurIPS 2024Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification
375. NeurIPS 2024Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
376. NeurIPS 2024Transductive Learning is Compact
377. NeurIPS 2024Transfer Learning for Latent Variable Network Models
378. NeurIPS 2024Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
379. NeurIPS 2024Transformers are Minimax Optimal Nonparametric In-Context Learners
380. NeurIPS 2024Understanding Model Selection for Learning in Strategic Environments
381. NeurIPS 2024Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
382. NeurIPS 2024Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
383. NeurIPS 2024Understanding the Gains from Repeated Self-Distillation
384. NeurIPS 2024Understanding the Role of Equivariance in Self-supervised Learning
385. NeurIPS 2024Universal Rates for Active Learning
386. NeurIPS 2024Universal Rates of Empirical Risk Minimization
387. NeurIPS 2024Universality in Transfer Learning for Linear Models
388. NeurIPS 2024Unravelling in Collaborative Learning
389. NeurIPS 2024Unrolled denoising networks provably learn to perform optimal Bayesian inference
390. NeurIPS 2024Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
391. NeurIPS 2024Variance estimation in compound decision theory under boundedness
392. NeurIPS 2024Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds
393. NeurIPS 2024Wide Two-Layer Networks can Learn from Adversarial Perturbations

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.