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 8 of 11

351. NeurIPS 2024Linear Regression using Heterogeneous Data Batches
352. NeurIPS 2024Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
353. NeurIPS 2024Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
354. NeurIPS 2024Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
355. NeurIPS 2024Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input
356. NeurIPS 2024Metric Transforms and Low Rank Representations of Kernels for Fast Attention
357. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
358. NeurIPS 2024Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
359. NeurIPS 2024Model Collapse Demystified: The Case of Regression
360. NeurIPS 2024Multi-Label Learning with Stronger Consistency Guarantees
361. NeurIPS 2024Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
362. NeurIPS 2024Nature-Inspired Local Propagation
363. NeurIPS 2024Near-Optimality of Contrastive Divergence Algorithms
364. NeurIPS 2024Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
365. NeurIPS 2024Neural Collapse To Multiple Centers For Imbalanced Data
366. NeurIPS 2024Neural Conditional Probability for Uncertainty Quantification
367. NeurIPS 2024Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
368. NeurIPS 2024NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
369. NeurIPS 2024Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
370. NeurIPS 2024Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits
371. NeurIPS 2024Non-asymptotic Convergence of Training Transformers for Next-token Prediction
372. NeurIPS 2024Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
373. NeurIPS 2024Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
374. NeurIPS 2024On $f$-Divergence Principled Domain Adaptation: An Improved Framework
375. NeurIPS 2024On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
376. NeurIPS 2024On the Ability of Developers' Training Data Preservation of Learnware
377. NeurIPS 2024On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
378. NeurIPS 2024On the Computational Landscape of Replicable Learning
379. NeurIPS 2024On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
380. NeurIPS 2024On the Efficiency of ERM in Feature Learning
381. NeurIPS 2024On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
382. NeurIPS 2024On the Limitations of Fractal Dimension as a Measure of Generalization
383. NeurIPS 2024On the Power of Decision Trees in Auto-Regressive Language Modeling
384. NeurIPS 2024On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
385. NeurIPS 2024On the Role of Attention Masks and LayerNorm in Transformers
386. NeurIPS 2024On the Saturation Effects of Spectral Algorithms in Large Dimensions
387. NeurIPS 2024On the Sparsity of the Strong Lottery Ticket Hypothesis
388. NeurIPS 2024On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
389. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
390. NeurIPS 2024Online Consistency of the Nearest Neighbor Rule
391. NeurIPS 2024Online Weighted Paging with Unknown Weights
392. NeurIPS 2024Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
393. NeurIPS 2024Optimal Algorithms for Augmented Testing of Discrete Distributions
394. NeurIPS 2024Optimal Algorithms for Learning Partitions with Faulty Oracles
395. NeurIPS 2024Optimal deep learning of holomorphic operators between Banach spaces
396. NeurIPS 2024Optimal Hypothesis Selection in (Almost) Linear Time
397. NeurIPS 2024Optimal Parallelization of Boosting
398. NeurIPS 2024Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
399. NeurIPS 2024Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
400. NeurIPS 2024Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality

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.