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 2,330 篇，第 43 / 47 页

  1. ICML 2023Constrained Efficient Global Optimization of Expensive Black-box Functions
  2. ICML 2023Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
  3. ICML 2023Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data
  4. ICML 2023Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss
  5. ICML 2023Cut your Losses with Squentropy
  6. ICML 2023Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization
  7. ICML 2023DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization
  8. ICML 2023Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity
  9. ICML 2023Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback
  10. ICML 2023DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning
  11. ICML 2023Differentially Private Stochastic Convex Optimization under a Quantile Loss Function
  12. ICML 2023Diffusion Models for Black-Box Optimization
  13. ICML 2023Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost
  14. ICML 2023DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
  15. ICML 2023Dynamic Constrained Submodular Optimization with Polylogarithmic Update Time
  16. ICML 2023EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression
  17. ICML 2023Efficient displacement convex optimization with particle gradient descent
  18. ICML 2023Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization
  19. ICML 2023End-to-End Learning for Stochastic Optimization: A Bayesian Perspective
  20. ICML 2023Escaping saddle points in zeroth-order optimization: the power of two-point estimators
  21. ICML 2023Fast as CHITA: Neural Network Pruning with Combinatorial Optimization
  22. ICML 2023Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization
  23. ICML 2023Faster Rates of Convergence to Stationary Points in Differentially Private Optimization
  24. ICML 2023Federated Online and Bandit Convex Optimization
  25. ICML 2023FedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization
  26. ICML 2023Generalized Polyak Step Size for First Order Optimization with Momentum
  27. ICML 2023Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization
  28. ICML 2023Generative Pretraining for Black-Box Optimization
  29. ICML 2023Global Optimization with Parametric Function Approximation
  30. ICML 2023Graph Reinforcement Learning for Network Control via Bi-Level Optimization
  31. ICML 2023High Probability Convergence of Stochastic Gradient Methods
  32. ICML 2023High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
  33. ICML 2023Implicit Jacobian regularization weighted with impurity of probability output
  34. ICML 2023Improving Bi-level Optimization Based Methods with Inspiration from Humans' Classroom Study Techniques
  35. ICML 2023Is Consensus Acceleration Possible in Decentralized Optimization over Slowly Time-Varying Networks?
  36. ICML 2023Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement
  37. ICML 2023Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach
  38. ICML 2023Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability
  39. ICML 2023Low Complexity Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Optimization over (Non-)Convex Set
  40. ICML 2023Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions
  41. ICML 2023Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime
  42. ICML 2023Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization
  43. ICML 2023Neural Network Accelerated Implicit Filtering: Integrating Neural Network Surrogates With Provably Convergent Derivative Free Optimization Methods
  44. ICML 2023Nonparametric Iterative Machine Teaching
  45. ICML 2023Omnipredictors for Constrained Optimization
  46. ICML 2023On the Convergence of Federated Averaging with Cyclic Client Participation
  47. ICML 2023On the Convergence of SARSA with Linear Function Approximation
  48. ICML 2023On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm
  49. ICML 2023On the Convergence Rate of Gaussianization with Random Rotations
  50. ICML 2023On User-Level Private Convex Optimization

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