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 346 篇，第 6 / 7 页

  1. NeurIPS 2023Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond
  2. NeurIPS 2023Federated Conditional Stochastic Optimization
  3. NeurIPS 2023Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds
  4. NeurIPS 2023FedNAR: Federated Optimization with Normalized Annealing Regularization
  5. NeurIPS 2023Finding Local Minima Efficiently in Decentralized Optimization
  6. NeurIPS 2023Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization
  7. NeurIPS 2023First Order Stochastic Optimization with Oblivious Noise
  8. NeurIPS 2023Fractal Landscapes in Policy Optimization
  9. NeurIPS 2023Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
  10. NeurIPS 2023Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization
  11. NeurIPS 2023Global Identifiability of $\ell_1$-based Dictionary Learning via Matrix Volume Optimization
  12. NeurIPS 2023GloptiNets: Scalable Non-Convex Optimization with Certificates
  13. NeurIPS 2023Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
  14. NeurIPS 2023Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
  15. NeurIPS 2023Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise
  16. NeurIPS 2023Improving the Knowledge Gradient Algorithm
  17. NeurIPS 2023Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization
  18. NeurIPS 2023Knowledge Distillation Performs Partial Variance Reduction
  19. NeurIPS 2023L2T-DLN: Learning to Teach with Dynamic Loss Network
  20. NeurIPS 2023Learning Cuts via Enumeration Oracles
  21. NeurIPS 2023Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt
  22. NeurIPS 2023Leveraging the two-timescale regime to demonstrate convergence of neural networks
  23. NeurIPS 2023Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices
  24. NeurIPS 2023Max-Margin Token Selection in Attention Mechanism
  25. NeurIPS 2023Mechanic: A Learning Rate Tuner
  26. NeurIPS 2023Memory-Constrained Algorithms for Convex Optimization
  27. NeurIPS 2023MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning
  28. NeurIPS 2023MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates
  29. NeurIPS 2023Model-Based Control with Sparse Neural Dynamics
  30. NeurIPS 2023Momentum Provably Improves Error Feedback!
  31. NeurIPS 2023Neural Fields with Hard Constraints of Arbitrary Differential Order
  32. NeurIPS 2023Non-Convex Bilevel Optimization with Time-Varying Objective Functions
  33. NeurIPS 2023Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization
  34. NeurIPS 2023On skip connections and normalisation layers in deep optimisation
  35. NeurIPS 2023On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis
  36. NeurIPS 2023On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
  37. NeurIPS 2023On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
  38. NeurIPS 2023One-step differentiation of iterative algorithms
  39. NeurIPS 2023Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure
  40. NeurIPS 2023Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
  41. NeurIPS 2023Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model
  42. NeurIPS 2023Optimization of Inter-group criteria for clustering with minimum size constraints
  43. NeurIPS 2023Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization
  44. NeurIPS 2023Ordering-based Conditions for Global Convergence of Policy Gradient Methods
  45. NeurIPS 2023Outlier-Robust Gromov-Wasserstein for Graph Data
  46. NeurIPS 2023Outlier-Robust Wasserstein DRO
  47. NeurIPS 2023Parallel Submodular Function Minimization
  48. NeurIPS 2023Parallel-mentoring for Offline Model-based Optimization
  49. NeurIPS 2023Physics-Informed Bayesian Optimization of Variational Quantum Circuits
  50. NeurIPS 2023Policy Optimization for Continuous Reinforcement Learning

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