理论 · learning theory论文趋势 2023–2026
学习理论及相关：learning_theory
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,350 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 57 | 24 | 5 | 0 | 86 |
| 2024 | 265 | 106 | 21 | 1 | 393 |
| 2025 | 106 | 147 | 132 | 4 | 389 |
| 2026 | 112 | 200 | 170 | 0 | 482 |
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 1,350 篇，第 14 / 27 页
- ICML 2025Approximation to Smooth Functions by Low-Rank Swish Networks
- ICML 2025Batch List-Decodable Linear Regression via Higher Moments
- ICML 2025BCE vs. CE in Deep Feature Learning
- ICML 2025Best of Both Worlds: Regret Minimization versus Minimax Play
- ICML 2025Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
- ICML 2025Compact Matrix Quantum Group Equivariant Neural Networks
- ICML 2025Consensus Is All You Get: The Role of Attention in Transformers
- ICML 2025Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
- ICML 2025Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions
- ICML 2025Design Considerations in Offline Preference-based RL
- ICML 2025Dimension-Independent Rates for Structured Neural Density Estimation
- ICML 2025Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
- ICML 2025Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal
- ICML 2025Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
- ICML 2025Ehrenfeucht-Haussler Rank and Chain of Thought
- ICML 2025Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
- ICML 2025Equivariant Neural Tangent Kernels
- ICML 2025Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
- ICML 2025Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
- ICML 2025Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices
- ICML 2025Fully Dynamic Embedding into $\ell_p$ Spaces
- ICML 2025Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
- ICML 2025Generalization Analysis for Controllable Learning
- ICML 2025Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings
- ICML 2025Generalization and Robustness of the Tilted Empirical Risk
- ICML 2025Generalization in Federated Learning: A Conditional Mutual Information Framework
- ICML 2025Generation from Noisy Examples
- ICML 2025GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
- ICML 2025Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models
- ICML 2025Grokking at the Edge of Linear Separability
- ICML 2025Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
- ICML 2025How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
- ICML 2025Hypothesis Testing for Generalized Thurstone Models
- ICML 2025Identifying Metric Structures of Deep Latent Variable Models
- ICML 2025Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
- ICML 2025Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
- ICML 2025Incorporating Arbitrary Matrix Group Equivariance into KANs
- ICML 2025Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
- ICML 2025Learning Configurations for Data-Driven Multi-Objective Optimization
- ICML 2025Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points
- ICML 2025Learning Parametric Distributions from Samples and Preferences
- ICML 2025Learning to Steer Learners in Games
- ICML 2025Learning Utilities from Demonstrations in Markov Decision Processes
- ICML 2025Learning with Exact Invariances in Polynomial Time
- ICML 2025Learning-Augmented Hierarchical Clustering
- ICML 2025Limitations of measure-first protocols in quantum machine learning
- ICML 2025LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
- ICML 2025Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
- ICML 2025Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
- ICML 2025Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查理论 · learning theory在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "theory-learning-theory"}
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。