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

1,350 papers, page 21 of 27

1001. NeurIPS 2024A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers
1002. NeurIPS 2024A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
1003. NeurIPS 2024A Kernel Perspective on Distillation-based Collaborative Learning
1004. NeurIPS 2024A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
1005. NeurIPS 2024A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning
1006. NeurIPS 2024A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
1007. NeurIPS 2024A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness
1008. NeurIPS 2024A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
1009. NeurIPS 2024A Theory of Optimistically Universal Online Learnability for General Concept Classes
1010. NeurIPS 2024A two-scale Complexity Measure for Deep Learning Models
1011. NeurIPS 2024A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
1012. NeurIPS 2024A Universal Growth Rate for Learning with Smooth Surrogate Losses
1013. NeurIPS 2024Accelerating ERM for data-driven algorithm design using output-sensitive techniques
1014. NeurIPS 2024Accelerating Relative Entropy Coding with Space Partitioning
1015. NeurIPS 2024Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
1016. NeurIPS 2024Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures
1017. NeurIPS 2024Active Classification with Few Queries under Misspecification
1018. NeurIPS 2024Active Learning of General Halfspaces: Label Queries vs Membership Queries
1019. NeurIPS 2024Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
1020. NeurIPS 2024Adversarially Robust Multi-task Representation Learning
1021. NeurIPS 2024Algebraic Positional Encodings
1022. NeurIPS 2024Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
1023. NeurIPS 2024Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering
1024. NeurIPS 2024AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
1025. NeurIPS 2024An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
1026. NeurIPS 2024Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
1027. NeurIPS 2024Analysis of Corrected Graph Convolutions
1028. NeurIPS 2024Approximation Rate of the Transformer Architecture for Sequence Modeling
1029. NeurIPS 2024Are Multiple Instance Learning Algorithms Learnable for Instances?
1030. NeurIPS 2024Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
1031. NeurIPS 2024Average gradient outer product as a mechanism for deep neural collapse
1032. NeurIPS 2024Bayes-optimal learning of an extensive-width neural network from quadratically many samples
1033. NeurIPS 2024Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
1034. NeurIPS 2024Benign overfitting in leaky ReLU networks with moderate input dimension
1035. NeurIPS 2024Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
1036. NeurIPS 2024Breaking the curse of dimensionality in structured density estimation
1037. NeurIPS 2024Building a stable classifier with the inflated argmax
1038. NeurIPS 2024Can neural operators always be continuously discretized?
1039. NeurIPS 2024Cardinality-Aware Set Prediction and Top-$k$ Classification
1040. NeurIPS 2024Clustering in Causal Attention Masking
1041. NeurIPS 2024Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding
1042. NeurIPS 2024Clustering with Non-adaptive Subset Queries
1043. NeurIPS 2024Communication Bounds for the Distributed Experts Problem
1044. NeurIPS 2024Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond
1045. NeurIPS 2024Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
1046. NeurIPS 2024Contextual Decision-Making with Knapsacks Beyond the Worst Case
1047. NeurIPS 2024Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound
1048. NeurIPS 2024Credal Learning Theory
1049. NeurIPS 2024Credit Attribution and Stable Compression
1050. NeurIPS 2024Cryptographic Hardness of Score Estimation

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.