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 14 of 27

651. ICML 2025Approximation to Smooth Functions by Low-Rank Swish Networks
652. ICML 2025Batch List-Decodable Linear Regression via Higher Moments
653. ICML 2025BCE vs. CE in Deep Feature Learning
654. ICML 2025Best of Both Worlds: Regret Minimization versus Minimax Play
655. ICML 2025Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
656. ICML 2025Compact Matrix Quantum Group Equivariant Neural Networks
657. ICML 2025Consensus Is All You Get: The Role of Attention in Transformers
658. ICML 2025Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
659. ICML 2025Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions
660. ICML 2025Design Considerations in Offline Preference-based RL
661. ICML 2025Dimension-Independent Rates for Structured Neural Density Estimation
662. ICML 2025Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
663. ICML 2025Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal
664. ICML 2025Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
665. ICML 2025Ehrenfeucht-Haussler Rank and Chain of Thought
666. ICML 2025Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
667. ICML 2025Equivariant Neural Tangent Kernels
668. ICML 2025Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
669. ICML 2025Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
670. ICML 2025Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices
671. ICML 2025Fully Dynamic Embedding into $\ell_p$ Spaces
672. ICML 2025Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
673. ICML 2025Generalization Analysis for Controllable Learning
674. ICML 2025Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings
675. ICML 2025Generalization and Robustness of the Tilted Empirical Risk
676. ICML 2025Generalization in Federated Learning: A Conditional Mutual Information Framework
677. ICML 2025Generation from Noisy Examples
678. ICML 2025GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
679. ICML 2025Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models
680. ICML 2025Grokking at the Edge of Linear Separability
681. ICML 2025Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
682. ICML 2025How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
683. ICML 2025Hypothesis Testing for Generalized Thurstone Models
684. ICML 2025Identifying Metric Structures of Deep Latent Variable Models
685. ICML 2025Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
686. ICML 2025Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
687. ICML 2025Incorporating Arbitrary Matrix Group Equivariance into KANs
688. ICML 2025Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
689. ICML 2025Learning Configurations for Data-Driven Multi-Objective Optimization
690. ICML 2025Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points
691. ICML 2025Learning Parametric Distributions from Samples and Preferences
692. ICML 2025Learning to Steer Learners in Games
693. ICML 2025Learning Utilities from Demonstrations in Markov Decision Processes
694. ICML 2025Learning with Exact Invariances in Polynomial Time
695. ICML 2025Learning-Augmented Hierarchical Clustering
696. ICML 2025Limitations of measure-first protocols in quantum machine learning
697. ICML 2025LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
698. ICML 2025Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
699. ICML 2025Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
700. ICML 2025Meta Optimality for Demographic Parity Constrained Regression via Post-Processing

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.