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 192 篇，第 4 / 4 页

  1. ICML 2025Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games
  2. ICML 2025Refining Adaptive Zeroth-Order Optimization at Ease
  3. ICML 2025Regularized Langevin Dynamics for Combinatorial Optimization
  4. ICML 2025Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
  5. ICML 2025Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
  6. ICML 2025Riemannian Diffusion Adaptation for Distributed Optimization on Manifolds
  7. ICML 2025Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
  8. ICML 2025Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity
  9. ICML 2025Robust Sparsification via Sensitivity
  10. ICML 2025ROPO: Robust Preference Optimization for Large Language Models
  11. ICML 2025SAFE: Finding Sparse and Flat Minima to Improve Pruning
  12. ICML 2025Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation
  13. ICML 2025Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
  14. ICML 2025Scalable Meta-Learning via Mixed-Mode Differentiation
  15. ICML 2025Secant Line Search for Frank-Wolfe Algorithms
  16. ICML 2025SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
  17. ICML 2025Simple Policy Optimization
  18. ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
  19. ICML 2025SkipGPT: Each Token is One of a Kind
  20. ICML 2025Solving Zero-Sum Convex Markov Games
  21. ICML 2025Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
  22. ICML 2025Sparse-pivot: Dynamic correlation clustering for node insertions
  23. ICML 2025Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
  24. ICML 2025Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints
  25. ICML 2025Structured Preconditioners in Adaptive Optimization: A Unified Analysis
  26. ICML 2025Subspace Optimization for Large Language Models with Convergence Guarantees
  27. ICML 2025The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations
  28. ICML 2025The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
  29. ICML 2025The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport
  30. ICML 2025The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
  31. ICML 2025Tilted Sharpness-Aware Minimization
  32. ICML 2025ToMA: Token Merge with Attention for Diffusion Models
  33. ICML 2025Toward a Unified Theory of Gradient Descent under Generalized Smoothness
  34. ICML 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
  35. ICML 2025TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization
  36. ICML 2025Unconstrained Robust Online Convex Optimization
  37. ICML 2025Understanding High-Dimensional Bayesian Optimization
  38. ICML 2025Unified Breakdown Analysis for Byzantine Robust Gossip
  39. ICML 2025Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations
  40. ICML 2025Wasserstein Policy Optimization
  41. ICML 2025When Maximum Entropy Misleads Policy Optimization
  42. ICML 2025When to Forget? Complexity Trade-offs in Machine Unlearning

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