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 560 篇，第 10 / 12 页

  1. NeurIPS 2024Non-geodesically-convex optimization in the Wasserstein space
  2. NeurIPS 2024Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data
  3. NeurIPS 2024Normalization and effective learning rates in reinforcement learning
  4. NeurIPS 2024Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
  5. NeurIPS 2024On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
  6. NeurIPS 2024On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
  7. NeurIPS 2024On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
  8. NeurIPS 2024Online Composite Optimization Between Stochastic and Adversarial Environments
  9. NeurIPS 2024OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations
  10. NeurIPS 2024Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
  11. NeurIPS 2024Optimal Scalarizations for Sublinear Hypervolume Regret
  12. NeurIPS 2024Optimization Algorithm Design via Electric Circuits
  13. NeurIPS 2024Optimization Can Learn Johnson Lindenstrauss Embeddings
  14. NeurIPS 2024Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition
  15. NeurIPS 2024Ordered Momentum for Asynchronous SGD
  16. NeurIPS 2024OT4P: Unlocking Effective Orthogonal Group Path for Permutation Relaxation
  17. NeurIPS 2024Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport
  18. NeurIPS 2024Parameter-free Clipped Gradient Descent Meets Polyak
  19. NeurIPS 2024Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds
  20. NeurIPS 2024Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
  21. NeurIPS 2024Policy Mirror Descent with Lookahead
  22. NeurIPS 2024Policy Optimization for Robust Average Reward MDPs
  23. NeurIPS 2024Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint
  24. NeurIPS 2024Private Geometric Median
  25. NeurIPS 2024Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
  26. NeurIPS 2024Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
  27. NeurIPS 2024Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks
  28. NeurIPS 2024Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
  29. NeurIPS 2024Public-data Assisted Private Stochastic Optimization: Power and Limitations
  30. NeurIPS 2024Quantitative Convergences of Lie Group Momentum Optimizers
  31. NeurIPS 2024Random Function Descent
  32. NeurIPS 2024Randomized Sparse Matrix Compression for Large-Scale Constrained Optimization in Cancer Radiotherapy
  33. NeurIPS 2024Recurrent neural networks: vanishing and exploding gradients are not the end of the story
  34. NeurIPS 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
  35. NeurIPS 2024Regularized Q-Learning
  36. NeurIPS 2024Rejection via Learning Density Ratios
  37. NeurIPS 2024ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization
  38. NeurIPS 2024Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
  39. NeurIPS 2024Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization
  40. NeurIPS 2024Resolving Discrepancies in Compute-Optimal Scaling of Language Models
  41. NeurIPS 2024Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks
  42. NeurIPS 2024Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation
  43. NeurIPS 2024Robust Gaussian Processes via Relevance Pursuit
  44. NeurIPS 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
  45. NeurIPS 2024S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial Optimization
  46. NeurIPS 2024Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport
  47. NeurIPS 2024Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization
  48. NeurIPS 2024Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes
  49. NeurIPS 2024Scalable Kernel Inverse Optimization
  50. NeurIPS 2024Scalable Optimization in the Modular Norm

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