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 5 of 7

201. ICML 2025Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
202. ICML 2025Ehrenfeucht-Haussler Rank and Chain of Thought
203. ICML 2025Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
204. ICML 2025Equivariant Neural Tangent Kernels
205. ICML 2025Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
206. ICML 2025Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
207. ICML 2025Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices
208. ICML 2025Fully Dynamic Embedding into $\ell_p$ Spaces
209. ICML 2025Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
210. ICML 2025Generalization Analysis for Controllable Learning
211. ICML 2025Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings
212. ICML 2025Generalization and Robustness of the Tilted Empirical Risk
213. ICML 2025Generalization in Federated Learning: A Conditional Mutual Information Framework
214. ICML 2025Generation from Noisy Examples
215. ICML 2025GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
216. ICML 2025Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models
217. ICML 2025Grokking at the Edge of Linear Separability
218. ICML 2025Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
219. ICML 2025How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
220. ICML 2025Hypothesis Testing for Generalized Thurstone Models
221. ICML 2025Identifying Metric Structures of Deep Latent Variable Models
222. ICML 2025Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
223. ICML 2025Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
224. ICML 2025Incorporating Arbitrary Matrix Group Equivariance into KANs
225. ICML 2025Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
226. ICML 2025Learning Configurations for Data-Driven Multi-Objective Optimization
227. ICML 2025Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points
228. ICML 2025Learning Parametric Distributions from Samples and Preferences
229. ICML 2025Learning to Steer Learners in Games
230. ICML 2025Learning Utilities from Demonstrations in Markov Decision Processes
231. ICML 2025Learning with Exact Invariances in Polynomial Time
232. ICML 2025Learning-Augmented Hierarchical Clustering
233. ICML 2025Limitations of measure-first protocols in quantum machine learning
234. ICML 2025LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
235. ICML 2025Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
236. ICML 2025Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
237. ICML 2025Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
238. ICML 2025Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
239. ICML 2025Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
240. ICML 2025Model Uncertainty Quantification by Conformal Prediction in Continual Learning
241. ICML 2025Models of Heavy-Tailed Mechanistic Universality
242. ICML 2025Modular Duality in Deep Learning
243. ICML 2025Nearly Optimal Sample Complexity for Learning with Label Proportions
244. ICML 2025No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
245. ICML 2025Non-Asymptotic Length Generalization
246. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
247. ICML 2025Nonlinear transformers can perform inference-time feature learning
248. ICML 2025On Learning Parallel Pancakes with Mostly Uniform Weights
249. ICML 2025On the Convergence of Continuous Single-timescale Actor-critic
250. ICML 2025On the Emergence of Position Bias in Transformers

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.