非凸优化论文趋势 2023–2026

收敛与 landscape

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,330 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

非凸优化论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023154799815346
202427510716018560
202527917719219667
202625017828643757

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

全部非凸优化论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 736 篇，第 10 / 15 页

  1. ICML 2025Secant Line Search for Frank-Wolfe Algorithms
  2. ICML 2025SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
  3. ICML 2025Simple Policy Optimization
  4. ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
  5. ICML 2025SkipGPT: Each Token is One of a Kind
  6. ICML 2025Solving Zero-Sum Convex Markov Games
  7. ICML 2025Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
  8. ICML 2025Sparse-pivot: Dynamic correlation clustering for node insertions
  9. ICML 2025Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
  10. ICML 2025Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints
  11. ICML 2025Structured Preconditioners in Adaptive Optimization: A Unified Analysis
  12. ICML 2025Subspace Optimization for Large Language Models with Convergence Guarantees
  13. ICML 2025The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations
  14. ICML 2025The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
  15. ICML 2025The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport
  16. ICML 2025The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
  17. ICML 2025Tilted Sharpness-Aware Minimization
  18. ICML 2025ToMA: Token Merge with Attention for Diffusion Models
  19. ICML 2025Toward a Unified Theory of Gradient Descent under Generalized Smoothness
  20. ICML 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
  21. ICML 2025TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization
  22. ICML 2025Unconstrained Robust Online Convex Optimization
  23. ICML 2025Understanding High-Dimensional Bayesian Optimization
  24. ICML 2025Unified Breakdown Analysis for Byzantine Robust Gossip
  25. ICML 2025Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations
  26. ICML 2025Wasserstein Policy Optimization
  27. ICML 2025When Maximum Entropy Misleads Policy Optimization
  28. ICML 2025When to Forget? Complexity Trade-offs in Machine Unlearning
  29. ICML 2024A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
  30. ICML 2024A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional Optimization
  31. ICML 2024A Geometric Decomposition of Finite Games: Convergence vs. Recurrence under Exponential Weights
  32. ICML 2024A Global Geometric Analysis of Maximal Coding Rate Reduction
  33. ICML 2024A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
  34. ICML 2024A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
  35. ICML 2024A New Theoretical Perspective on Data Heterogeneity in Federated Optimization
  36. ICML 2024A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle
  37. ICML 2024A Universal Transfer Theorem for Convex Optimization Algorithms Using Inexact First-order Oracles
  38. ICML 2024Absolute Policy Optimization: Enhancing Lower Probability Bound of Performance with High Confidence
  39. ICML 2024Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion
  40. ICML 2024Accelerating Convergence of Score-Based Diffusion Models, Provably
  41. ICML 2024Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you Need
  42. ICML 2024ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
  43. ICML 2024Activation-Descent Regularization for Input Optimization of ReLU Networks
  44. ICML 2024Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations
  45. ICML 2024Advancing Dynamic Sparse Training by Exploring Optimization Opportunities
  46. ICML 2024An Iterative Min-Min Optimization Method for Sparse Bayesian Learning
  47. ICML 2024An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization
  48. ICML 2024Autonomous Sparse Mean-CVaR Portfolio Optimization
  49. ICML 2024Barrier Algorithms for Constrained Non-Convex Optimization
  50. ICML 2024Bayesian Optimization of Function Networks with Partial Evaluations

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 查非凸优化在 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": "nonconvex-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非凸优化论文？
共 2,330 篇，按年份分别是 2023 年 346 篇、2024 年 560 篇、2025 年 667 篇、2026 年 757 篇。
NeurIPS 2026 有多少篇非凸优化论文？
NeurIPS 2026 有 250 篇非凸优化论文，上一届是 279 篇。
ICLR 2026 有多少篇非凸优化论文？
ICLR 2026 有 178 篇非凸优化论文，上一届是 177 篇。
ICML 2026 有多少篇非凸优化论文？
ICML 2026 有 286 篇非凸优化论文，上一届是 192 篇。
CVPR 2026 有多少篇非凸优化论文？
CVPR 2026 有 43 篇非凸优化论文，上一届是 19 篇。
哪个会议的非凸优化论文最多？
NeurIPS，2023–2026 年共 958 篇。

「优化与缩放」下的其他主题