理论 · learning theory论文趋势 2023–2026

主要结论

• 理论 · learning theory论文从 2023 年的 86 篇增长到 2026 年的 482 篇，三年间扩大到约 5.6 倍。
• NeurIPS 是发理论 · learning theory论文最多的会议，2023–2026 年共 540 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是社会层面 · accountability transparency and interpretability：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 33 篇。
• 在「理论与统计」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的理论 · optimization是 4.7 倍，理论 · learning theory是 5.6 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部理论 · learning theory论文

共 106 篇，第 1 / 3 页

1. ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
2. ICLR 2024A path-norm toolkit for modern networks: consequences, promises and challenges
3. ICLR 2024A Policy Gradient Method for Confounded POMDPs
4. ICLR 2024A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data
5. ICLR 2024A Sublinear Adversarial Training Algorithm
6. ICLR 2024Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
7. ICLR 2024Adaptive Regret for Bandits Made Possible: Two Queries Suffice
8. ICLR 2024Algorithms for Caching and MTS with reduced number of predictions
9. ICLR 2024An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
10. ICLR 2024An Efficient Tester-Learner for Halfspaces
11. ICLR 2024Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
12. ICLR 2024Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning
13. ICLR 2024Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
14. ICLR 2024BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
15. ICLR 2024Beating Price of Anarchy and Gradient Descent without Regret in Potential Games
16. ICLR 2024Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
17. ICLR 2024Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
18. ICLR 2024Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
19. ICLR 2024Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback
20. ICLR 2024Convergence of Bayesian Bilevel Optimization
21. ICLR 2024Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
22. ICLR 2024Distinguished In Uniform: Self-Attention Vs. Virtual Nodes
23. ICLR 2024Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
24. ICLR 2024Enhancing Neural Training via a Correlated Dynamics Model
25. ICLR 2024Fantastic Generalization Measures are Nowhere to be Found
26. ICLR 2024Feature Collapse
27. ICLR 2024Feature emergence via margin maximization: case studies in algebraic tasks
28. ICLR 2024Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem
29. ICLR 2024General Stability Analysis for Zeroth-Order Optimization Algorithms
30. ICLR 2024Generalization error of spectral algorithms
31. ICLR 2024Generalization of Scaled Deep ResNets in the Mean-Field Regime
32. ICLR 2024Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
33. ICLR 2024Harnessing Density Ratios for Online Reinforcement Learning
34. ICLR 2024High-dimensional SGD aligns with emerging outlier eigenspaces
35. ICLR 2024Horizon-Free Regret for Linear Markov Decision Processes
36. ICLR 2024How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
37. ICLR 2024How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
38. ICLR 2024How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
39. ICLR 2024Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
40. ICLR 2024Implicit regularization of deep residual networks towards neural ODEs
41. ICLR 2024Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
42. ICLR 2024Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
43. ICLR 2024Incentivized Truthful Communication for Federated Bandits
44. ICLR 2024Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
45. ICLR 2024Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
46. ICLR 2024Koopman-based generalization bound: New aspect for full-rank weights
47. ICLR 2024Learning Conditional Invariances through Non-Commutativity
48. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
49. ICLR 2024Learning Hierarchical Polynomials with Three-Layer Neural Networks
50. ICLR 2024Learning Nash Equilibria in Rank-1 Games

常见问题

2023–2026 年四大会议一共有多少篇理论 · learning theory论文？

共 1,350 篇，按年份分别是 2023 年 86 篇、2024 年 393 篇、2025 年 389 篇、2026 年 482 篇。

NeurIPS 2026 有多少篇理论 · learning theory论文？

NeurIPS 2026 有 112 篇理论 · learning theory论文，上一届是 106 篇。

ICLR 2026 有多少篇理论 · learning theory论文？

ICLR 2026 有 200 篇理论 · learning theory论文，上一届是 147 篇。

ICML 2026 有多少篇理论 · learning theory论文？

ICML 2026 有 170 篇理论 · learning theory论文，上一届是 132 篇。

CVPR 2025 有多少篇理论 · learning theory论文？

CVPR 2025 有 4 篇理论 · learning theory论文，上一届是 1 篇。

哪个会议的理论 · learning theory论文最多？

NeurIPS，2023–2026 年共 540 篇。