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 736 篇，第 11 / 15 页

  1. ICML 2024Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
  2. ICML 2024Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
  3. ICML 2024BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation
  4. ICML 2024Boosting Offline Optimizers with Surrogate Sensitivity
  5. ICML 2024BOtied: Multi-objective Bayesian optimization with tied multivariate ranks
  6. ICML 2024Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints
  7. ICML 2024Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?
  8. ICML 2024Challenges in Training PINNs: A Loss Landscape Perspective
  9. ICML 2024Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
  10. ICML 2024Compact Optimality Verification for Optimization Proxies
  11. ICML 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
  12. ICML 2024Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms
  13. ICML 2024Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
  14. ICML 2024Convergence Guarantees for the DeepWalk Embedding on Block Models
  15. ICML 2024Convergence of Some Convex Message Passing Algorithms to a Fixed Point
  16. ICML 2024Convex and Bilevel Optimization for Neural-Symbolic Inference and Learning
  17. ICML 2024Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization
  18. ICML 2024Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers
  19. ICML 2024Deconstructing the Goldilocks Zone of Neural Network Initialization
  20. ICML 2024Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration
  21. ICML 2024Delving into the Convergence of Generalized Smooth Minimax Optimization
  22. ICML 2024Differentiability and Optimization of Multiparameter Persistent Homology
  23. ICML 2024Differentiable Distributionally Robust Optimization Layers
  24. ICML 2024Differentiable Mapper for Topological Optimization of Data Representation
  25. ICML 2024Distributed Bilevel Optimization with Communication Compression
  26. ICML 2024Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification
  27. ICML 2024Double Momentum Method for Lower-Level Constrained Bilevel Optimization
  28. ICML 2024Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient
  29. ICML 2024Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization
  30. ICML 2024Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond
  31. ICML 2024Efficient Algorithms for Sum-Of-Minimum Optimization
  32. ICML 2024Efficient Stochastic Approximation of Minimax Excess Risk Optimization
  33. ICML 2024Equivariant Deep Weight Space Alignment
  34. ICML 2024Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
  35. ICML 2024Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
  36. ICML 2024Exploring the Complexity of Deep Neural Networks through Functional Equivalence
  37. ICML 2024FADAS: Towards Federated Adaptive Asynchronous Optimization
  38. ICML 2024Faster Adaptive Decentralized Learning Algorithms
  39. ICML 2024Federated Optimization with Doubly Regularized Drift Correction
  40. ICML 2024Flora: Low-Rank Adapters Are Secretly Gradient Compressors
  41. ICML 2024From Generalization Analysis to Optimization Designs for State Space Models
  42. ICML 2024From Inverse Optimization to Feasibility to ERM
  43. ICML 2024Fundamental Benefit of Alternating Updates in Minimax Optimization
  44. ICML 2024Generalized Preference Optimization: A Unified Approach to Offline Alignment
  45. ICML 2024Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
  46. ICML 2024High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling
  47. ICML 2024High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails
  48. ICML 2024High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise
  49. ICML 2024How Free is Parameter-Free Stochastic Optimization?
  50. ICML 2024How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-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