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

1,350 papers, page 26 of 27

1251. NeurIPS 2024Understanding Model Selection for Learning in Strategic Environments
1252. NeurIPS 2024Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
1253. NeurIPS 2024Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
1254. NeurIPS 2024Understanding the Gains from Repeated Self-Distillation
1255. NeurIPS 2024Understanding the Role of Equivariance in Self-supervised Learning
1256. NeurIPS 2024Universal Rates for Active Learning
1257. NeurIPS 2024Universal Rates of Empirical Risk Minimization
1258. NeurIPS 2024Universality in Transfer Learning for Linear Models
1259. NeurIPS 2024Unravelling in Collaborative Learning
1260. NeurIPS 2024Unrolled denoising networks provably learn to perform optimal Bayesian inference
1261. NeurIPS 2024Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
1262. NeurIPS 2024Variance estimation in compound decision theory under boundedness
1263. NeurIPS 2024Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds
1264. NeurIPS 2024Wide Two-Layer Networks can Learn from Adversarial Perturbations
1265. ICLR 2023A Theory of Dynamic Benchmarks
1266. ICLR 2023Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation
1267. ICLR 2023Bispectral Neural Networks
1268. ICLR 2023Computational Language Acquisition with Theory of Mind
1269. ICLR 2023D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory
1270. ICLR 2023Disentanglement with Biological Constraints: A Theory of Functional Cell Types
1271. ICLR 2023Humanly Certifying Superhuman Classifiers
1272. ICLR 2023Learning in temporally structured environments
1273. ICLR 2023Learning Probabilistic Topological Representations Using Discrete Morse Theory
1274. ICLR 2023Learning ReLU networks to high uniform accuracy is intractable
1275. ICLR 2023Long-Tailed Learning Requires Feature Learning
1276. ICLR 2023Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence
1277. ICLR 2023Pitfalls of Gaussians as a noise distribution in NCE
1278. ICLR 2023Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks
1279. ICLR 2023Provable Memorization Capacity of Transformers
1280. ICLR 2023Sharper Bounds for Uniformly Stable Algorithms with Stationary Mixing Process
1281. ICLR 2023Spacetime Representation Learning
1282. ICLR 2023Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms
1283. ICLR 2023Strong inductive biases provably prevent harmless interpolation
1284. ICLR 2023Systematic Rectification of Language Models via Dead-end Analysis
1285. ICLR 2023The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
1286. ICLR 2023Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs
1287. ICLR 2023Transformers Learn Shortcuts to Automata
1288. ICLR 2023Why adversarial training can hurt robust accuracy
1289. ICML 2023Certifying Ensembles: A General Certification Theory with S-Lipschitzness
1290. ICML 2023Fast Federated Machine Unlearning with Nonlinear Functional Theory
1291. ICML 2023Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
1292. ICML 2023Robust Collaborative Learning with Linear Gradient Overhead
1293. ICML 2023Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
1294. NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
1295. NeurIPS 2023A Measure-Theoretic Axiomatisation of Causality
1296. NeurIPS 2023A Theory of Multimodal Learning
1297. NeurIPS 2023A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
1298. NeurIPS 2023Accelerating Value Iteration with Anchoring
1299. NeurIPS 2023Agnostic Multi-Group Active Learning
1300. NeurIPS 2023Alternation makes the adversary weaker in two-player games

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.