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 15 of 27

701. ICML 2025Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
702. ICML 2025Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
703. ICML 2025Model Uncertainty Quantification by Conformal Prediction in Continual Learning
704. ICML 2025Models of Heavy-Tailed Mechanistic Universality
705. ICML 2025Modular Duality in Deep Learning
706. ICML 2025Nearly Optimal Sample Complexity for Learning with Label Proportions
707. ICML 2025No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
708. ICML 2025Non-Asymptotic Length Generalization
709. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
710. ICML 2025Nonlinear transformers can perform inference-time feature learning
711. ICML 2025On Learning Parallel Pancakes with Mostly Uniform Weights
712. ICML 2025On the Convergence of Continuous Single-timescale Actor-critic
713. ICML 2025On the Emergence of Position Bias in Transformers
714. ICML 2025On the Generalization Ability of Next-Token-Prediction Pretraining
715. ICML 2025On the Learnability of Distribution Classes with Adaptive Adversaries
716. ICML 2025On the Role of Label Noise in the Feature Learning Process
717. ICML 2025On the Similarities of Embeddings in Contrastive Learning
718. ICML 2025On the Statistical Mechanisms of Distributional Compositional Generalization
719. ICML 2025On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures
720. ICML 2025PAC Learning with Improvements
721. ICML 2025PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
722. ICML 2025Policy-Regret Minimization in Markov Games with Function Approximation
723. ICML 2025Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
724. ICML 2025Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
725. ICML 2025Probably Approximately Global Robustness Certification
726. ICML 2025Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
727. ICML 2025Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
728. ICML 2025Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
729. ICML 2025Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
730. ICML 2025Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
731. ICML 2025Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
732. ICML 2025Representation Preserving Multiclass Agnostic to Realizable Reduction
733. ICML 2025Representative Language Generation
734. ICML 2025Rethinking Benign Overfitting in Two-Layer Neural Networks
735. ICML 2025Retraining with Predicted Hard Labels Provably Increases Model Accuracy
736. ICML 2025Revisiting the Predictability of Performative, Social Events
737. ICML 2025Sample-Optimal Agnostic Boosting with Unlabeled Data
738. ICML 2025Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
739. ICML 2025Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs
740. ICML 2025Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness
741. ICML 2025Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise
742. ICML 2025System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
743. ICML 2025The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
744. ICML 2025The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli
745. ICML 2025The impact of uncertainty on regularized learning in games
746. ICML 2025The Power of Random Features and the Limits of Distribution-Free Gradient Descent
747. ICML 2025The Role of Randomness in Stability
748. ICML 2025Theoretical Limitations of Ensembles in the Age of Overparameterization
749. ICML 2025Tight and Fast Bounds for Multi-Label Learning
750. ICML 2025Toward a Unified Theory of Gradient Descent under Generalized Smoothness

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.