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 667 篇，第 8 / 14 页

  1. ICML 2025Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
  2. ICML 2025Riemannian Diffusion Adaptation for Distributed Optimization on Manifolds
  3. ICML 2025Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
  4. ICML 2025Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity
  5. ICML 2025Robust Sparsification via Sensitivity
  6. ICML 2025ROPO: Robust Preference Optimization for Large Language Models
  7. ICML 2025SAFE: Finding Sparse and Flat Minima to Improve Pruning
  8. ICML 2025Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation
  9. ICML 2025Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
  10. ICML 2025Scalable Meta-Learning via Mixed-Mode Differentiation
  11. ICML 2025Secant Line Search for Frank-Wolfe Algorithms
  12. ICML 2025SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
  13. ICML 2025Simple Policy Optimization
  14. ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
  15. ICML 2025SkipGPT: Each Token is One of a Kind
  16. ICML 2025Solving Zero-Sum Convex Markov Games
  17. ICML 2025Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
  18. ICML 2025Sparse-pivot: Dynamic correlation clustering for node insertions
  19. ICML 2025Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
  20. ICML 2025Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints
  21. ICML 2025Structured Preconditioners in Adaptive Optimization: A Unified Analysis
  22. ICML 2025Subspace Optimization for Large Language Models with Convergence Guarantees
  23. ICML 2025The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations
  24. ICML 2025The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
  25. ICML 2025The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport
  26. ICML 2025The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
  27. ICML 2025Tilted Sharpness-Aware Minimization
  28. ICML 2025ToMA: Token Merge with Attention for Diffusion Models
  29. ICML 2025Toward a Unified Theory of Gradient Descent under Generalized Smoothness
  30. ICML 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
  31. ICML 2025TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization
  32. ICML 2025Unconstrained Robust Online Convex Optimization
  33. ICML 2025Understanding High-Dimensional Bayesian Optimization
  34. ICML 2025Unified Breakdown Analysis for Byzantine Robust Gossip
  35. ICML 2025Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations
  36. ICML 2025Wasserstein Policy Optimization
  37. ICML 2025When Maximum Entropy Misleads Policy Optimization
  38. ICML 2025When to Forget? Complexity Trade-offs in Machine Unlearning
  39. NeurIPS 2025$\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
  40. NeurIPS 20253BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs
  41. NeurIPS 2025A Beyond-Worst-Case Analysis of Greedy k-means++
  42. NeurIPS 2025A Computationally Viable Numerical Gradient-based Technique for Optimal Covering Problems
  43. NeurIPS 2025A geometric framework for momentum-based optimizers for low-rank training
  44. NeurIPS 2025A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
  45. NeurIPS 2025A Gradient Guided Diffusion Framework for Chance Constrained Programming
  46. NeurIPS 2025A Minimalist Example of Edge-of-Stability and Progressive Sharpening
  47. NeurIPS 2025A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization
  48. NeurIPS 2025A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees
  49. NeurIPS 2025A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization
  50. NeurIPS 2025A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation

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