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 4 of 8

151. NeurIPS 2024Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
152. NeurIPS 2024Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering
153. NeurIPS 2024AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
154. NeurIPS 2024An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
155. NeurIPS 2024Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
156. NeurIPS 2024Analysis of Corrected Graph Convolutions
157. NeurIPS 2024Approximation Rate of the Transformer Architecture for Sequence Modeling
158. NeurIPS 2024Are Multiple Instance Learning Algorithms Learnable for Instances?
159. NeurIPS 2024Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
160. NeurIPS 2024Average gradient outer product as a mechanism for deep neural collapse
161. NeurIPS 2024Bayes-optimal learning of an extensive-width neural network from quadratically many samples
162. NeurIPS 2024Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
163. NeurIPS 2024Benign overfitting in leaky ReLU networks with moderate input dimension
164. NeurIPS 2024Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
165. NeurIPS 2024Breaking the curse of dimensionality in structured density estimation
166. NeurIPS 2024Building a stable classifier with the inflated argmax
167. NeurIPS 2024Can neural operators always be continuously discretized?
168. NeurIPS 2024Cardinality-Aware Set Prediction and Top-$k$ Classification
169. NeurIPS 2024Clustering in Causal Attention Masking
170. NeurIPS 2024Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding
171. NeurIPS 2024Clustering with Non-adaptive Subset Queries
172. NeurIPS 2024Communication Bounds for the Distributed Experts Problem
173. NeurIPS 2024Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond
174. NeurIPS 2024Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
175. NeurIPS 2024Contextual Decision-Making with Knapsacks Beyond the Worst Case
176. NeurIPS 2024Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound
177. NeurIPS 2024Credal Learning Theory
178. NeurIPS 2024Credit Attribution and Stable Compression
179. NeurIPS 2024Cryptographic Hardness of Score Estimation
180. NeurIPS 2024Data subsampling for Poisson regression with pth-root-link
181. NeurIPS 2024Derandomizing Multi-Distribution Learning
182. NeurIPS 2024Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
183. NeurIPS 2024Differentiable Quantum Computing for Large-scale Linear Control
184. NeurIPS 2024Dimension-free deterministic equivalents and scaling laws for random feature regression
185. NeurIPS 2024Distributed Least Squares in Small Space via Sketching and Bias Reduction
186. NeurIPS 2024Distribution Learning with Valid Outputs Beyond the Worst-Case
187. NeurIPS 2024Distributional regression: CRPS-error bounds for model fitting, model selection and convex aggregation
188. NeurIPS 2024Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
189. NeurIPS 2024Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
190. NeurIPS 2024ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
191. NeurIPS 2024Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
192. NeurIPS 2024Efficient Discrepancy Testing for Learning with Distribution Shift
193. NeurIPS 2024Efficient Graph Matching for Correlated Stochastic Block Models
194. NeurIPS 2024Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
195. NeurIPS 2024Entropy testing and its application to testing Bayesian networks
196. NeurIPS 2024Entrywise error bounds for low-rank approximations of kernel matrices
197. NeurIPS 2024Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game
198. NeurIPS 2024Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
199. NeurIPS 2024Euclidean distance compression via deep random features
200. NeurIPS 2024Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering

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.