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 19 of 27

901. ICLR 2024General Stability Analysis for Zeroth-Order Optimization Algorithms
902. ICLR 2024Generalization error of spectral algorithms
903. ICLR 2024Generalization of Scaled Deep ResNets in the Mean-Field Regime
904. ICLR 2024Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
905. ICLR 2024Harnessing Density Ratios for Online Reinforcement Learning
906. ICLR 2024High-dimensional SGD aligns with emerging outlier eigenspaces
907. ICLR 2024Horizon-Free Regret for Linear Markov Decision Processes
908. ICLR 2024How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
909. ICLR 2024How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
910. ICLR 2024How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
911. ICLR 2024Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
912. ICLR 2024Implicit regularization of deep residual networks towards neural ODEs
913. ICLR 2024Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
914. ICLR 2024Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
915. ICLR 2024Incentivized Truthful Communication for Federated Bandits
916. ICLR 2024Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
917. ICLR 2024Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
918. ICLR 2024Koopman-based generalization bound: New aspect for full-rank weights
919. ICLR 2024Learning Conditional Invariances through Non-Commutativity
920. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
921. ICLR 2024Learning Hierarchical Polynomials with Three-Layer Neural Networks
922. ICLR 2024Learning Nash Equilibria in Rank-1 Games
923. ICLR 2024Learning Thresholds with Latent Values and Censored Feedback
924. ICLR 2024Learning to Reject Meets Long-tail Learning
925. ICLR 2024Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
926. ICLR 2024lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning
927. ICLR 2024Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
928. ICLR 2024Memorization Capacity of Multi-Head Attention in Transformers
929. ICLR 2024Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods
930. ICLR 2024Minimum width for universal approximation using ReLU networks on compact domain
931. ICLR 2024More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
932. ICLR 2024Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications
933. ICLR 2024Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
934. ICLR 2024Noisy Interpolation Learning with Shallow Univariate ReLU Networks
935. ICLR 2024On Representation Complexity of Model-based and Model-free Reinforcement Learning
936. ICLR 2024On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection
937. ICLR 2024On the hardness of learning under symmetries
938. ICLR 2024On the Limitations of Temperature Scaling for Distributions with Overlaps
939. ICLR 2024On the Provable Advantage of Unsupervised Pretraining
940. ICLR 2024One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention
941. ICLR 2024Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
942. ICLR 2024OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS
943. ICLR 2024Optimal Sample Complexity of Contrastive Learning
944. ICLR 2024Oracle Efficient Algorithms for Groupwise Regret
945. ICLR 2024Out-Of-Domain Unlabeled Data Improves Generalization
946. ICLR 2024Plugin estimators for selective classification with out-of-distribution detection
947. ICLR 2024Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
948. ICLR 2024Provable Offline Preference-Based Reinforcement Learning
949. ICLR 2024Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
950. ICLR 2024Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks

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.