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 20 of 27

951. ICLR 2024Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds
952. ICLR 2024Risk Bounds of Accelerated SGD for Overparameterized Linear Regression
953. ICLR 2024Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
954. ICLR 2024Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
955. ICLR 2024Sample-Efficient Multi-Agent RL: An Optimization Perspective
956. ICLR 2024Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization
957. ICLR 2024Scaling Laws for Associative Memories
958. ICLR 2024SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
959. ICLR 2024Simplifying Transformer Blocks
960. ICLR 2024Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing
961. ICLR 2024Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
962. ICLR 2024Spectrally Transformed Kernel Regression
963. ICLR 2024Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
964. ICLR 2024Stochastic Modified Equations and Dynamics of Dropout Algorithm
965. ICLR 2024Symmetric Single Index Learning
966. ICLR 2024The Effective Horizon Explains Deep RL Performance in Stochastic Environments
967. ICLR 2024The Expressive Power of Low-Rank Adaptation
968. ICLR 2024The Human-AI Substitution game: active learning from a strategic labeler
969. ICLR 2024The optimality of kernel classifiers in Sobolev space
970. ICLR 2024Theoretical Understanding of Learning from Adversarial Perturbations
971. ICLR 2024Tight Rates in Supervised Outlier Transfer Learning
972. ICLR 2024Toward Student-oriented Teacher Network Training for Knowledge Distillation
973. ICLR 2024Towards Establishing Guaranteed Error for Learned Database Operations
974. ICLR 2024Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models
975. ICLR 2024Towards the Fundamental Limits of Knowledge Transfer over Finite Domains
976. ICLR 2024Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
977. ICLR 2024Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
978. ICLR 2024When can transformers reason with abstract symbols?
979. ICML 2024A sampling theory perspective on activations for implicit neural representations
980. ICML 2024A Statistical Theory of Regularization-Based Continual Learning
981. ICML 2024A Theory of Fault-Tolerant Learning
982. ICML 2024A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
983. ICML 2024Critical windows: non-asymptotic theory for feature emergence in diffusion models
984. ICML 2024Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
985. ICML 2024Matrix Information Theory for Self-Supervised Learning
986. ICML 2024Minimum Norm Interpolation Meets The Local Theory of Banach Spaces
987. ICML 2024On Statistical Learning Theory for Distributional Inputs
988. ICML 2024Open Ad Hoc Teamwork with Cooperative Game Theory
989. ICML 2024PIDformer: Transformer Meets Control Theory
990. ICML 2024Position: Categorical Deep Learning is an Algebraic Theory of All Architectures
991. ICML 2024Position: Future Directions in the Theory of Graph Machine Learning
992. ICML 2024Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity Theory
993. ICML 2024Random matrix theory improved Fréchet mean of symmetric positive definite matrices
994. ICML 2024Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
995. ICML 2024Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction
996. ICML 2024Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
997. ICML 2024Theory of Consistency Diffusion Models: Distribution Estimation Meets Fast Sampling
998. ICML 2024Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms
999. ICML 2024Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models
1000. NeurIPS 20244+3 Phases of Compute-Optimal Neural Scaling Laws

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.