理论 · statistics论文趋势 2023–2026

主要结论

• 理论 · statistics论文从 2023 年的 16 篇增长到 2026 年的 57 篇，三年间扩大到约 3.6 倍。
• NeurIPS 是发理论 · statistics论文最多的会议，2023–2026 年共 58 篇，占四个会议总量的 42%。
• 交叉方向里涨得最快的是理论 · learning theory：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 28 篇。
• 在「理论与统计」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的理论 · learning theory是 5.6 倍，理论 · statistics是 3.6 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 2026Asymptotic Anytime-Valid Inference for U-statistics
• ICML 2026A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
• ICLR 2026The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics
• NeurIPS 2025A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
• ICML 2025Contextual Bandits for Unbounded Context Distributions
• ICLR 2025Improving Pretraining Data Using Perplexity Correlations
• CVPR 2025Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics
• NeurIPS 2024FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
• ICML 2024Neural Networks Learn Statistics of Increasing Complexity
• ICLR 2024Kernelised Normalising Flows
• NeurIPS 2023Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics
• ICML 2023Fair Densities via Boosting the Sufficient Statistics of Exponential Families
• ICLR 2023Don’t fear the unlabelled: safe semi-supervised learning via debiasing
• NeurIPS 2026Computationally sufficient statistics for Ising models
• ICML 2026Adaptive Multiscale Binary Expansion Tests for Independence
• ICLR 2026Bayesian Influence Functions for Hessian-Free Data Attribution
• NeurIPS 2025Backward Conformal Prediction
• ICML 2025Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
• ICLR 2025From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation
• NeurIPS 2024Statistical Multicriteria Benchmarking via the GSD-Front

全部理论 · statistics论文

共 50 篇，第 1 / 1 页

1. ICML 2026A Random Matrix Perspective on the Consistency of Diffusion Models
2. ICML 2026A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning
3. ICML 2026A Studentized Spherical Harmonics–Based Nonparametric Two-Sample Test for Compositional and Directional Data
4. ICML 2026A Theory of Contrastive Learning with Natural Images
5. ICML 2026A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
6. ICML 2026A theory of learning data statistics in diffusion models, from easy to hard
7. ICML 2026Adaptive Multiscale Binary Expansion Tests for Independence
8. ICML 2026Approximating f -Divergences with Rank Statistics
9. ICML 2026Beyond First-order Asymptotics in Sequential Mean Testing
10. ICML 2026Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization
11. ICML 2026Combinatorial Sparse PCA Beyond the Spiked Identity Model
12. ICML 2026Deep networks learn to parse uniform-depth context-free languages from local statistics
13. ICML 2026Deep Neural Network Regression with Functional Covariates
14. ICML 2026Deriving Neural Scaling Laws from the Statistics of Natural Language
15. ICML 2026Finite-Width Neural Tangent Kernels from Feynman Diagrams
16. ICML 2026Learning $U$-Statistics with Active Inference
17. ICML 2026Learning Gaussian Graphical Models from a Glauber Trajectory Without Mixing
18. ICML 2026Linear Regression with Unknown Truncation Beyond Gaussian Features
19. ICML 2026Mean-Shift PCA by Knockoff Mean
20. ICML 2026On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification
21. ICML 2026On the Power of Statistics in Class-Incremental Learning with Pretrained Models
22. ICML 2026Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
23. ICML 2026Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
24. ICML 2026Provable Bounds for the Learnability of Sample-Compressible Families from Noisy Samples
25. ICML 2026Sample Complexity Bounds for Robust Mean Estimation with Mean-Shift Contamination
26. ICML 2026Sharp Concentration Bounds for Bundle-Valued Statistics on Manifolds
27. ICML 2026Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
28. ICML 2026Symmetries in language statistics shape the geometry of model representations
29. ICML 2026The Catastrophic Failure of *the* k-Means Algorithm in High Dimensions, and How Hartigan's Algorithm Avoids It
30. ICML 2026When Softmax Fails at the Top: Extreme‑Value Corrections for InfoNCE
31. ICML 2025Batch List-Decodable Linear Regression via Higher Moments
32. ICML 2025Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
33. ICML 2025Conformal Tail Risk Control for Large Language Model Alignment
34. ICML 2025Contextual Bandits for Unbounded Context Distributions
35. ICML 2025Dimension-Independent Rates for Structured Neural Density Estimation
36. ICML 2025Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
37. ICML 2025Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
38. ICML 2025From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
39. ICML 2025On Learning Parallel Pancakes with Mostly Uniform Weights
40. ICML 2025Position: Rethinking Explainable Machine Learning as Applied Statistics
41. ICML 2025QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions
42. ICML 2025Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
43. ICML 2025The Underlying Universal Statistical Structure of Natural Datasets
44. ICML 2024DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation
45. ICML 2024Neural Networks Learn Statistics of Increasing Complexity
46. ICML 2024Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
47. ICML 2024Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
48. ICML 2024What is the Long-Run Distribution of Stochastic Gradient Descent? A Large Deviations Analysis
49. ICML 2023Fair Densities via Boosting the Sufficient Statistics of Exponential Families
50. ICML 2023Is Learning Summary Statistics Necessary for Likelihood-free Inference?

常见问题

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

共 138 篇，按年份分别是 2023 年 16 篇、2024 年 21 篇、2025 年 44 篇、2026 年 57 篇。

NeurIPS 2026 有多少篇理论 · statistics论文？

NeurIPS 2026 有 12 篇理论 · statistics论文，上一届是 23 篇。

ICLR 2026 有多少篇理论 · statistics论文？

ICLR 2026 有 15 篇理论 · statistics论文，上一届是 7 篇。

ICML 2026 有多少篇理论 · statistics论文？

ICML 2026 有 30 篇理论 · statistics论文，上一届是 13 篇。

CVPR 2025 有多少篇理论 · statistics论文？

CVPR 2025 有 1 篇理论 · statistics论文。

哪个会议的理论 · statistics论文最多？

NeurIPS，2023–2026 年共 58 篇。