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

389 papers, page 4 of 8

151. ICLR 2025When narrower is better: the narrow width limit of Bayesian parallel branching neural networks
152. ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
153. ICML 2025A Generalization Theory for Zero-Shot Prediction
154. ICML 2025A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning
155. ICML 2025A Parametric Contextual Online Learning Theory of Brokerage
156. ICML 2025A Theory for Conditional Generative Modeling on Multiple Data Sources
157. ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
158. ICML 2025A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features
159. ICML 2025A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
160. ICML 2025A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games
161. ICML 2025Adversarial Robust Generalization of Graph Neural Networks
162. ICML 2025Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
163. ICML 2025Algorithms with Calibrated Machine Learning Predictions
164. ICML 2025All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance
165. ICML 2025An analytic theory of creativity in convolutional diffusion models
166. ICML 2025An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
167. ICML 2025An Error Analysis of Flow Matching for Deep Generative Modeling
168. ICML 2025Anytime-Constrained Equilibria in Polynomial Time
169. ICML 2025Approximation to Smooth Functions by Low-Rank Swish Networks
170. ICML 2025Batch List-Decodable Linear Regression via Higher Moments
171. ICML 2025BCE vs. CE in Deep Feature Learning
172. ICML 2025Best of Both Worlds: Regret Minimization versus Minimax Play
173. ICML 2025Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
174. ICML 2025Compact Matrix Quantum Group Equivariant Neural Networks
175. ICML 2025Consensus Is All You Get: The Role of Attention in Transformers
176. ICML 2025Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
177. ICML 2025Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions
178. ICML 2025Design Considerations in Offline Preference-based RL
179. ICML 2025Dimension-Independent Rates for Structured Neural Density Estimation
180. ICML 2025Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
181. ICML 2025Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal
182. ICML 2025Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
183. ICML 2025Ehrenfeucht-Haussler Rank and Chain of Thought
184. ICML 2025Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
185. ICML 2025Equivariant Neural Tangent Kernels
186. ICML 2025Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
187. ICML 2025Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
188. ICML 2025Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices
189. ICML 2025Fully Dynamic Embedding into $\ell_p$ Spaces
190. ICML 2025Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
191. ICML 2025Generalization Analysis for Controllable Learning
192. ICML 2025Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings
193. ICML 2025Generalization and Robustness of the Tilted Empirical Risk
194. ICML 2025Generalization in Federated Learning: A Conditional Mutual Information Framework
195. ICML 2025Generation from Noisy Examples
196. ICML 2025GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
197. ICML 2025Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models
198. ICML 2025Grokking at the Edge of Linear Separability
199. ICML 2025Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
200. ICML 2025How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias

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.