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 4 of 7

151. ICML 2026Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
152. ICML 2026Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets
153. ICML 2026Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
154. ICML 2026To Grok Grokking: Provable Grokking in Ridge Regression
155. ICML 2026Token Sample Complexity of Attention
156. ICML 2026Towards Atoms of Large Language Models
157. ICML 2026Towards Spectroscopy: Susceptibility Clusters in Language Models
158. ICML 2026Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
159. ICML 2026Towards Understanding Generalization of Federated Adversarial Learning: Perspective of Algorithmic Stability
160. ICML 2026Trajectory Seriation via Spectral Tangent Alignment and Global Embedding
161. ICML 2026Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent
162. ICML 2026Understanding Generalization from Embedding Dimension and Distributional Convergence
163. ICML 2026Understanding Private Learning From Feature Perspective
164. ICML 2026Unifying Low Dimensional Spectra in Deep Learning
165. ICML 2026Universal Learning of Nonlinear Dynamics
166. ICML 2026Universal Multiclass Transductive Online Learning
167. ICML 2026What Does Preference Learning Recover from Pairwise Comparison Data?
168. ICML 2026Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models
169. ICML 2026Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
170. ICML 2026Why Self-Distillation Helps and Hurts: Denoising vs. Signal Forgetting
171. ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
172. ICML 2025A Generalization Theory for Zero-Shot Prediction
173. ICML 2025A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning
174. ICML 2025A Parametric Contextual Online Learning Theory of Brokerage
175. ICML 2025A Theory for Conditional Generative Modeling on Multiple Data Sources
176. ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
177. ICML 2025A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features
178. ICML 2025A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
179. ICML 2025A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games
180. ICML 2025Adversarial Robust Generalization of Graph Neural Networks
181. ICML 2025Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
182. ICML 2025Algorithms with Calibrated Machine Learning Predictions
183. ICML 2025All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance
184. ICML 2025An analytic theory of creativity in convolutional diffusion models
185. ICML 2025An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
186. ICML 2025An Error Analysis of Flow Matching for Deep Generative Modeling
187. ICML 2025Anytime-Constrained Equilibria in Polynomial Time
188. ICML 2025Approximation to Smooth Functions by Low-Rank Swish Networks
189. ICML 2025Batch List-Decodable Linear Regression via Higher Moments
190. ICML 2025BCE vs. CE in Deep Feature Learning
191. ICML 2025Best of Both Worlds: Regret Minimization versus Minimax Play
192. ICML 2025Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
193. ICML 2025Compact Matrix Quantum Group Equivariant Neural Networks
194. ICML 2025Consensus Is All You Get: The Role of Attention in Transformers
195. ICML 2025Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
196. ICML 2025Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions
197. ICML 2025Design Considerations in Offline Preference-based RL
198. ICML 2025Dimension-Independent Rates for Structured Neural Density Estimation
199. ICML 2025Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
200. ICML 2025Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal

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.