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 958 篇，第 11 / 20 页

  1. NeurIPS 2025Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization
  2. NeurIPS 2025Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate
  3. NeurIPS 2025Structure-Aware Cooperative Ensemble Evolutionary Optimization on Combinatorial Problems with Multimodal Large Language Models
  4. NeurIPS 2025SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
  5. NeurIPS 2025System Prompt Optimization with Meta-Learning
  6. NeurIPS 2025TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
  7. NeurIPS 2025Targeted Maximum Likelihood Learning: An Optimization Perspective
  8. NeurIPS 2025The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective
  9. NeurIPS 2025The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
  10. NeurIPS 2025The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization
  11. NeurIPS 2025Theoretical Investigation of Adafactor for Non-Convex Smooth Optimization
  12. NeurIPS 2025Thompson Sampling in Function Spaces via Neural Operators
  13. NeurIPS 2025Tight analyses of first-order methods with error feedback
  14. NeurIPS 2025Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions
  15. NeurIPS 2025Tight Lower Bounds and Improved Convergence in Performative Prediction
  16. NeurIPS 2025TokMan:Tokenize Manhattan Mask Optimization for Inverse Lithography
  17. NeurIPS 2025Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach
  18. NeurIPS 2025Training the Untrainable: Introducing Inductive Bias via Representational Alignment
  19. NeurIPS 2025Transformers Learn Faster with Semantic Focus
  20. NeurIPS 2025Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm
  21. NeurIPS 2025Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization
  22. NeurIPS 2025UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection
  23. NeurIPS 2025Uniform Wrappers: Bridging Concave to Quadratizable Functions in Online Optimization
  24. NeurIPS 2025Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs
  25. NeurIPS 2025Variance-Reduced Long-Term Rehearsal Learning with Quadratic Programming Reformulation
  26. NeurIPS 2025Variational Inference with Mixtures of Isotropic Gaussians
  27. NeurIPS 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
  28. NeurIPS 2025What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization
  29. NeurIPS 2025Zeroth-Order Optimization Finds Flat Minima
  30. NeurIPS 2024$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
  31. NeurIPS 2024A Framework for Bilevel Optimization on Riemannian Manifolds
  32. NeurIPS 2024A Globally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization
  33. NeurIPS 2024A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
  34. NeurIPS 2024A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
  35. NeurIPS 2024A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training
  36. NeurIPS 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
  37. NeurIPS 2024Accelerating Matroid Optimization through Fast Imprecise Oracles
  38. NeurIPS 2024Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values
  39. NeurIPS 2024Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization
  40. NeurIPS 2024Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
  41. NeurIPS 2024Active Set Ordering
  42. NeurIPS 2024Adam with model exponential moving average is effective for nonconvex optimization
  43. NeurIPS 2024Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
  44. NeurIPS 2024Adaptive Proximal Gradient Method for Convex Optimization
  45. NeurIPS 2024Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions
  46. NeurIPS 2024Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
  47. NeurIPS 2024ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
  48. NeurIPS 2024Amortized Eigendecomposition for Neural Networks
  49. NeurIPS 2024An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
  50. NeurIPS 2024An Accelerated Gradient Method for Convex Smooth Simple Bilevel 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