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 20 / 47 页

  1. ICLR 2025Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
  2. ICLR 2025Weighted-Reward Preference Optimization for Implicit Model Fusion
  3. ICLR 2025Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
  4. ICML 2025A Bregman Proximal Viewpoint on Neural Operators
  5. ICML 2025A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD
  6. ICML 2025A First-order Generative Bilevel Optimization Framework for Diffusion Models
  7. ICML 2025A Generalization Result for Convergence in Learning-to-Optimize
  8. ICML 2025A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models
  9. ICML 2025A Near Linear Query Lower Bound for Submodular Maximization
  10. ICML 2025A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization
  11. ICML 2025A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization
  12. ICML 2025A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization
  13. ICML 2025Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators
  14. ICML 2025Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks
  15. ICML 2025Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
  16. ICML 2025Adaptive Partitioning Schemes for Optimistic Optimization
  17. ICML 2025Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
  18. ICML 2025Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks
  19. ICML 2025AMPO: Active Multi Preference Optimization for Self-play Preference Selection
  20. ICML 2025An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions
  21. ICML 2025Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
  22. ICML 2025Attention-Only Transformers via Unrolled Subspace Denoising
  23. ICML 2025Autoformulation of Mathematical Optimization Models Using LLMs
  24. ICML 2025Automatic Differentiation of Optimization Algorithms with Time-Varying Updates
  25. ICML 2025BackSlash: Rate Constrained Optimized Training of Large Language Models
  26. ICML 2025BARK: A Fully Bayesian Tree Kernel for Black-box Optimization
  27. ICML 2025Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
  28. ICML 2025BILBO: BILevel Bayesian Optimization
  29. ICML 2025BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
  30. ICML 2025BSO: Binary Spiking Online Optimization Algorithm
  31. ICML 2025Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies
  32. ICML 2025Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
  33. ICML 2025COExpander: Adaptive Solution Expansion for Combinatorial Optimization
  34. ICML 2025Compute or Load KV Cache? Why Not Both?
  35. ICML 2025ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
  36. ICML 2025Consensus Based Stochastic Optimal Control
  37. ICML 2025Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
  38. ICML 2025Constrained Online Convex Optimization with Polyak Feasibility Steps
  39. ICML 2025Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach
  40. ICML 2025Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization
  41. ICML 2025Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
  42. ICML 2025Cover learning for large-scale topology representation
  43. ICML 2025Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised Learning
  44. ICML 2025Differentiable Quadratic Optimization For the Maximum Independent Set Problem
  45. ICML 2025Differentiable Structure Learning with Ancestral Constraints
  46. ICML 2025Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
  47. ICML 2025Discrepancy Minimization in Input-Sparsity Time
  48. ICML 2025Distributed Event-Based Learning via ADMM
  49. ICML 2025Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel Manifold
  50. ICML 2025DTZO: Distributed Trilevel Zeroth Order Learning with Provable Non-Asymptotic Convergence

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