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 667 篇，第 7 / 14 页

  1. ICML 2025Learning Robust Neural Processes with Risk-Averse Stochastic Optimization
  2. ICML 2025Linear convergence of Sinkhorn's algorithm for generalized static Schrödinger bridge
  3. ICML 2025LLM Data Selection and Utilization via Dynamic Bi-level Optimization
  4. ICML 2025Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization
  5. ICML 2025MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
  6. ICML 2025Meta-Black-Box-Optimization through Offline Q-function Learning
  7. ICML 2025MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
  8. ICML 2025MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES
  9. ICML 2025MixMin: Finding Data Mixtures via Convex Minimization
  10. ICML 2025Model Immunization from a Condition Number Perspective
  11. ICML 2025Multi-Objective Causal Bayesian Optimization
  12. ICML 2025Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks
  13. ICML 2025Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion
  14. ICML 2025Multiobjective distribution matching
  15. ICML 2025Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization
  16. ICML 2025Nesterov Method for Asynchronous Pipeline Parallel Optimization
  17. ICML 2025Neural Event-Triggered Control with Optimal Scheduling
  18. ICML 2025Neural Solver Selection for Combinatorial Optimization
  19. ICML 2025Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails
  20. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
  21. ICML 2025Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
  22. ICML 2025On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms
  23. ICML 2025On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
  24. ICML 2025On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning
  25. ICML 2025One-Step Generalization Ratio Guided Optimization for Domain Generalization
  26. ICML 2025Online Conformal Prediction via Online Optimization
  27. ICML 2025Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization
  28. ICML 2025Optimization for Neural Operators can Benefit from Width
  29. ICML 2025Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
  30. ICML 2025Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach
  31. ICML 2025PARQ: Piecewise-Affine Regularized Quantization
  32. ICML 2025PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
  33. ICML 2025Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks
  34. ICML 2025Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization
  35. ICML 2025Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion
  36. ICML 2025Preference Optimization for Combinatorial Optimization Problems
  37. ICML 2025Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation
  38. ICML 2025Probabilistic Group Mask Guided Discrete Optimization for Incremental Learning
  39. ICML 2025Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent
  40. ICML 2025Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity
  41. ICML 2025Quantum Optimization via Gradient-Based Hamiltonian Descent
  42. ICML 2025R.I.P.: Better Models by Survival of the Fittest Prompts
  43. ICML 2025Radio: Rate–Distortion Optimization for Large Language Model Compression
  44. ICML 2025Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures
  45. ICML 2025Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
  46. ICML 2025Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization
  47. ICML 2025Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games
  48. ICML 2025Refining Adaptive Zeroth-Order Optimization at Ease
  49. ICML 2025Regularized Langevin Dynamics for Combinatorial Optimization
  50. ICML 2025Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness

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