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

265 papers, page 3 of 6

101. NeurIPS 2024Implicit Regularization Paths of Weighted Neural Representations
102. NeurIPS 2024Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
103. NeurIPS 2024Improved Sample Complexity Bounds for Diffusion Model Training
104. NeurIPS 2024Improved Sample Complexity for Multiclass PAC Learning
105. NeurIPS 2024Improving Adaptivity via Over-Parameterization in Sequence Models
106. NeurIPS 2024Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
107. NeurIPS 2024In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
108. NeurIPS 2024In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
109. NeurIPS 2024Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
110. NeurIPS 2024Information-theoretic Generalization Analysis for Expected Calibration Error
111. NeurIPS 2024Information-theoretic Limits of Online Classification with Noisy Labels
112. NeurIPS 2024Invariant subspaces and PCA in nearly matrix multiplication time
113. NeurIPS 2024Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions
114. NeurIPS 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
115. NeurIPS 2024Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance?
116. NeurIPS 2024Is O(log N) practical? Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL
117. NeurIPS 2024Label Noise: Ignorance Is Bliss
118. NeurIPS 2024Language Generation in the Limit
119. NeurIPS 2024Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
120. NeurIPS 2024Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
121. NeurIPS 2024Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks
122. NeurIPS 2024Learning from Noisy Labels via Conditional Distributionally Robust Optimization
123. NeurIPS 2024Learning from Snapshots of Discrete and Continuous Data Streams
124. NeurIPS 2024Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
125. NeurIPS 2024Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
126. NeurIPS 2024Learning Partitions from Context
127. NeurIPS 2024Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
128. NeurIPS 2024Learning the Infinitesimal Generator of Stochastic Diffusion Processes
129. NeurIPS 2024Learning via Surrogate PAC-Bayes
130. NeurIPS 2024Learning-Augmented Algorithms with Explicit Predictors
131. NeurIPS 2024Least Squares Regression Can Exhibit Under-Parameterized Double Descent
132. NeurIPS 2024Length Optimization in Conformal Prediction
133. NeurIPS 2024Linear Regression using Heterogeneous Data Batches
134. NeurIPS 2024Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
135. NeurIPS 2024Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
136. NeurIPS 2024Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
137. NeurIPS 2024Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input
138. NeurIPS 2024Metric Transforms and Low Rank Representations of Kernels for Fast Attention
139. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
140. NeurIPS 2024Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
141. NeurIPS 2024Model Collapse Demystified: The Case of Regression
142. NeurIPS 2024Multi-Label Learning with Stronger Consistency Guarantees
143. NeurIPS 2024Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
144. NeurIPS 2024Nature-Inspired Local Propagation
145. NeurIPS 2024Near-Optimality of Contrastive Divergence Algorithms
146. NeurIPS 2024Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
147. NeurIPS 2024Neural Collapse To Multiple Centers For Imbalanced Data
148. NeurIPS 2024Neural Conditional Probability for Uncertainty Quantification
149. NeurIPS 2024Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
150. NeurIPS 2024NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory

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.