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 5 of 11

201. NeurIPS 2025Spectral Analysis of Representational Similarity with Limited Neurons
202. NeurIPS 2025Spectral Estimation with Free Decompression
203. NeurIPS 2025State Size Independent Statistical Error Bound for Discrete Diffusion Models
204. NeurIPS 2025Streaming Attention Approximation via Discrepancy Theory
205. NeurIPS 2025Subsampled Ensemble Can Improve Generalization Tail Exponentially
206. NeurIPS 2025The Complexity of Finding Local Optima in Contrastive Learning
207. NeurIPS 2025The Computational Complexity of Counting Linear Regions in ReLU Neural Networks
208. NeurIPS 2025The Flood Complex: Large-Scale Persistent Homology on Millions of Points
209. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
210. NeurIPS 2025Tight Asymptotics of Extreme Order Statistics
211. NeurIPS 2025Tight Generalization Bounds for Large-Margin Halfspaces
212. NeurIPS 2025Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
213. NeurIPS 2025Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
214. NeurIPS 2025Two Heads are Better than One: Simulating Large Transformers with Small Ones
215. NeurIPS 2025Unbalanced Optimal Total Variation Transport: A Theoretical Approach to Spatial Resource Allocation Problems
216. NeurIPS 2025What Expressivity Theory Misses: Message Passing Complexity for GNNs
217. NeurIPS 2025When Does Curriculum Learning Help? A Theoretical Perspective
218. NeurIPS 2025Which Algorithms Have Tight Generalization Bounds?
219. NeurIPS 20244+3 Phases of Compute-Optimal Neural Scaling Laws
220. NeurIPS 2024A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers
221. NeurIPS 2024A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
222. NeurIPS 2024A Kernel Perspective on Distillation-based Collaborative Learning
223. NeurIPS 2024A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
224. NeurIPS 2024A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning
225. NeurIPS 2024A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
226. NeurIPS 2024A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness
227. NeurIPS 2024A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
228. NeurIPS 2024A Theory of Optimistically Universal Online Learnability for General Concept Classes
229. NeurIPS 2024A two-scale Complexity Measure for Deep Learning Models
230. NeurIPS 2024A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
231. NeurIPS 2024A Universal Growth Rate for Learning with Smooth Surrogate Losses
232. NeurIPS 2024Accelerating ERM for data-driven algorithm design using output-sensitive techniques
233. NeurIPS 2024Accelerating Relative Entropy Coding with Space Partitioning
234. NeurIPS 2024Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
235. NeurIPS 2024Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures
236. NeurIPS 2024Active Classification with Few Queries under Misspecification
237. NeurIPS 2024Active Learning of General Halfspaces: Label Queries vs Membership Queries
238. NeurIPS 2024Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
239. NeurIPS 2024Adversarially Robust Multi-task Representation Learning
240. NeurIPS 2024Algebraic Positional Encodings
241. NeurIPS 2024Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
242. NeurIPS 2024Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering
243. NeurIPS 2024AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
244. NeurIPS 2024An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
245. NeurIPS 2024Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
246. NeurIPS 2024Analysis of Corrected Graph Convolutions
247. NeurIPS 2024Approximation Rate of the Transformer Architecture for Sequence Modeling
248. NeurIPS 2024Are Multiple Instance Learning Algorithms Learnable for Instances?
249. NeurIPS 2024Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
250. NeurIPS 2024Average gradient outer product as a mechanism for deep neural collapse

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.