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 4 / 14 页

  1. ICLR 2025Provable Convergence Bounds for Hybrid Dynamical Sampling and Optimization
  2. ICLR 2025Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
  3. ICLR 2025qNBO: quasi-Newton Meets Bilevel Optimization
  4. ICLR 2025RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
  5. ICLR 2025Rethinking Neural Multi-Objective Combinatorial Optimization via Neat Weight Embedding
  6. ICLR 2025Revisiting Large-Scale Non-convex Distributionally Robust Optimization
  7. ICLR 2025Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations
  8. ICLR 2025Robustness of Quantum Algorithms for Nonconvex Optimization
  9. ICLR 2025Scalable Decentralized Learning with Teleportation
  10. ICLR 2025Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics
  11. ICLR 2025Searching for Optimal Solutions with LLMs via Bayesian Optimization
  12. ICLR 2025Second-Order Min-Max Optimization with Lazy Hessians
  13. ICLR 2025Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning
  14. ICLR 2025Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
  15. ICLR 2025Sharpness-Aware Black-Box Optimization
  16. ICLR 2025Sketching for Convex and Nonconvex Regularized Least Squares with Sharp Guarantees
  17. ICLR 2025SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box Optimization
  18. ICLR 2025SOREL: A Stochastic Algorithm for Spectral Risks Minimization
  19. ICLR 2025Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization
  20. ICLR 2025Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
  21. ICLR 2025Taming Transformer Without Using Learning Rate Warmup
  22. ICLR 2025Temporal Difference Learning: Why It Can Be Fast and How It Will Be Faster
  23. ICLR 2025The AdEMAMix Optimizer: Better, Faster, Older
  24. ICLR 2025The Crucial Role of Samplers in Online Direct Preference Optimization
  25. ICLR 2025The Directionality of Optimization Trajectories in Neural Networks
  26. ICLR 2025The Optimization Landscape of SGD Across the Feature Learning Strength
  27. ICLR 2025Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform Convexity
  28. ICLR 2025Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics
  29. ICLR 2025TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
  30. ICLR 2025To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
  31. ICLR 2025TopoGaussian: Inferring Internal Topology Structures from Visual Clues
  32. ICLR 2025Towards Faster Decentralized Stochastic Optimization with Communication Compression
  33. ICLR 2025Towards hyperparameter-free optimization with differential privacy
  34. ICLR 2025Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
  35. ICLR 2025Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
  36. ICLR 2025Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis
  37. ICLR 2025Understanding Optimization in Deep Learning with Central Flows
  38. ICLR 2025UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
  39. ICLR 2025Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
  40. ICLR 2025Unlocking Global Optimality in Bilevel Optimization: A Pilot Study
  41. ICLR 2025UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement Learning
  42. ICLR 2025Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
  43. ICLR 2025Vertical Federated Learning with Missing Features During Training and Inference
  44. ICLR 2025Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
  45. ICLR 2025Weighted-Reward Preference Optimization for Implicit Model Fusion
  46. ICLR 2025Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
  47. ICML 2025A Bregman Proximal Viewpoint on Neural Operators
  48. ICML 2025A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD
  49. ICML 2025A First-order Generative Bilevel Optimization Framework for Diffusion Models
  50. ICML 2025A Generalization Result for Convergence in Learning-to-Optimize

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