理论 · optimization论文趋势 2023–2026

学习理论及相关：optimization

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,871 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

理论 · optimization论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20233746355123
2024304123670494
20253181961479670
20261192442147584

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

全部理论 · optimization论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 494 篇，第 7 / 10 页

  1. NeurIPS 2024How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?
  2. NeurIPS 2024How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks
  3. NeurIPS 2024How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
  4. NeurIPS 2024How to Boost Any Loss Function
  5. NeurIPS 2024How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
  6. NeurIPS 2024HyperPrism: An Adaptive Non-linear Aggregation Framework for Distributed Machine Learning over Non-IID Data and Time-varying Communication Links
  7. NeurIPS 2024Implicit Bias of Mirror Flow on Separable Data
  8. NeurIPS 2024Implicit Regularization of Decentralized Gradient Descent for Sparse Regression
  9. NeurIPS 2024Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
  10. NeurIPS 2024Improved Guarantees for Fully Dynamic $k$-Center Clustering with Outliers in General Metric Spaces
  11. NeurIPS 2024Improved Particle Approximation Error for Mean Field Neural Networks
  12. NeurIPS 2024Improved Sample Complexity for Multiclass PAC Learning
  13. NeurIPS 2024Improving Equivariant Model Training via Constraint Relaxation
  14. NeurIPS 2024Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
  15. NeurIPS 2024In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
  16. NeurIPS 2024Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
  17. NeurIPS 2024Inexact Augmented Lagrangian Methods for Conic Optimization: Quadratic Growth and Linear Convergence
  18. NeurIPS 2024Infinite Limits of Multi-head Transformer Dynamics
  19. NeurIPS 2024Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors
  20. NeurIPS 2024IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
  21. NeurIPS 2024Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance?
  22. NeurIPS 2024Iterative Methods via Locally Evolving Set Process
  23. NeurIPS 2024John Ellipsoids via Lazy Updates
  24. NeurIPS 2024Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
  25. NeurIPS 2024Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities
  26. NeurIPS 2024Learnability of high-dimensional targets by two-parameter models and gradient flow
  27. NeurIPS 2024Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
  28. NeurIPS 2024Learning Cut Generating Functions for Integer Programming
  29. NeurIPS 2024Learning diffusion at lightspeed
  30. NeurIPS 2024Learning Elastic Costs to Shape Monge Displacements
  31. NeurIPS 2024Learning from Noisy Labels via Conditional Distributionally Robust Optimization
  32. NeurIPS 2024Learning Generalized Linear Programming Value Functions
  33. NeurIPS 2024Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
  34. NeurIPS 2024Learning to Handle Complex Constraints for Vehicle Routing Problems
  35. NeurIPS 2024Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way
  36. NeurIPS 2024Learning via Surrogate PAC-Bayes
  37. NeurIPS 2024Learning with Fitzpatrick Losses
  38. NeurIPS 2024Learning-Augmented Algorithms for the Bahncard Problem
  39. NeurIPS 2024Learning-Augmented Approximation Algorithms for Maximum Cut and Related Problems
  40. NeurIPS 2024Learning-Augmented Dynamic Submodular Maximization
  41. NeurIPS 2024Length Optimization in Conformal Prediction
  42. NeurIPS 2024LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
  43. NeurIPS 2024Linear Time Approximation Algorithm for Column Subset Selection with Local Search
  44. NeurIPS 2024Loss Landscape Characterization of Neural Networks without Over-Parametrization
  45. NeurIPS 2024Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks
  46. NeurIPS 2024Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
  47. NeurIPS 2024MAC Advice for facility location mechanism design
  48. NeurIPS 2024Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent
  49. NeurIPS 2024Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
  50. NeurIPS 2024Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization

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 · optimization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-optimization"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇理论 · optimization论文？
共 1,871 篇，按年份分别是 2023 年 123 篇、2024 年 494 篇、2025 年 670 篇、2026 年 584 篇。
NeurIPS 2026 有多少篇理论 · optimization论文？
NeurIPS 2026 有 119 篇理论 · optimization论文，上一届是 318 篇。
ICLR 2026 有多少篇理论 · optimization论文？
ICLR 2026 有 244 篇理论 · optimization论文，上一届是 196 篇。
ICML 2026 有多少篇理论 · optimization论文？
ICML 2026 有 214 篇理论 · optimization论文，上一届是 147 篇。
CVPR 2026 有多少篇理论 · optimization论文？
CVPR 2026 有 7 篇理论 · optimization论文，上一届是 9 篇。
哪个会议的理论 · optimization论文最多？
NeurIPS，2023–2026 年共 778 篇。

「理论与统计」下的其他主题