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 18 of 27

851. NeurIPS 2025Sharp Matrix Empirical Bernstein Inequalities
852. NeurIPS 2025Small Singular Values Matter: A Random Matrix Analysis of Transformer Models
853. NeurIPS 2025Smoothed Agnostic Learning of Halfspaces over the Hypercube
854. NeurIPS 2025Spectral Analysis of Representational Similarity with Limited Neurons
855. NeurIPS 2025Spectral Estimation with Free Decompression
856. NeurIPS 2025State Size Independent Statistical Error Bound for Discrete Diffusion Models
857. NeurIPS 2025Streaming Attention Approximation via Discrepancy Theory
858. NeurIPS 2025Subsampled Ensemble Can Improve Generalization Tail Exponentially
859. NeurIPS 2025The Complexity of Finding Local Optima in Contrastive Learning
860. NeurIPS 2025The Computational Complexity of Counting Linear Regions in ReLU Neural Networks
861. NeurIPS 2025The Flood Complex: Large-Scale Persistent Homology on Millions of Points
862. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
863. NeurIPS 2025Tight Asymptotics of Extreme Order Statistics
864. NeurIPS 2025Tight Generalization Bounds for Large-Margin Halfspaces
865. NeurIPS 2025Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
866. NeurIPS 2025Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
867. NeurIPS 2025Two Heads are Better than One: Simulating Large Transformers with Small Ones
868. NeurIPS 2025Unbalanced Optimal Total Variation Transport: A Theoretical Approach to Spatial Resource Allocation Problems
869. NeurIPS 2025What Expressivity Theory Misses: Message Passing Complexity for GNNs
870. NeurIPS 2025When Does Curriculum Learning Help? A Theoretical Perspective
871. NeurIPS 2025Which Algorithms Have Tight Generalization Bounds?
872. CVPR 2024Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
873. ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
874. ICLR 2024A path-norm toolkit for modern networks: consequences, promises and challenges
875. ICLR 2024A Policy Gradient Method for Confounded POMDPs
876. ICLR 2024A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data
877. ICLR 2024A Sublinear Adversarial Training Algorithm
878. ICLR 2024Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
879. ICLR 2024Adaptive Regret for Bandits Made Possible: Two Queries Suffice
880. ICLR 2024Algorithms for Caching and MTS with reduced number of predictions
881. ICLR 2024An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
882. ICLR 2024An Efficient Tester-Learner for Halfspaces
883. ICLR 2024Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
884. ICLR 2024Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning
885. ICLR 2024Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
886. ICLR 2024BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
887. ICLR 2024Beating Price of Anarchy and Gradient Descent without Regret in Potential Games
888. ICLR 2024Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
889. ICLR 2024Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
890. ICLR 2024Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
891. ICLR 2024Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback
892. ICLR 2024Convergence of Bayesian Bilevel Optimization
893. ICLR 2024Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
894. ICLR 2024Distinguished In Uniform: Self-Attention Vs. Virtual Nodes
895. ICLR 2024Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
896. ICLR 2024Enhancing Neural Training via a Correlated Dynamics Model
897. ICLR 2024Fantastic Generalization Measures are Nowhere to be Found
898. ICLR 2024Feature Collapse
899. ICLR 2024Feature emergence via margin maximization: case studies in algebraic tasks
900. ICLR 2024Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem

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.