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 8 / 15 页

  1. ICML 2025Fast Tensor Completion via Approximate Richardson Iteration
  2. ICML 2025Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization
  3. ICML 2025Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching
  4. ICML 2025Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions
  5. ICML 2025Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games
  6. ICML 2025Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agents
  7. ICML 2025FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
  8. ICML 2025General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization
  9. ICML 2025Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks
  10. ICML 2025Generalized Smooth Bilevel Optimization with Nonconvex Lower-Level
  11. ICML 2025Geometric Algebra Planes: Convex Implicit Neural Volumes
  12. ICML 2025Global curvature for second-order optimization of neural networks
  13. ICML 2025Global Optimization with a Power-Transformed Objective and Gaussian Smoothing
  14. ICML 2025GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration
  15. ICML 2025Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes
  16. ICML 2025Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
  17. ICML 2025HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training
  18. ICML 2025High-Dimensional Tensor Regression With Oracle Properties
  19. ICML 2025How Much Can We Forget about Data Contamination?
  20. ICML 2025How to set AdamW's weight decay as you scale model and dataset size
  21. ICML 2025Hyperband-based Bayesian Optimization for Black-box Prompt Selection
  22. ICML 2025Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
  23. ICML 2025Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling
  24. ICML 2025Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
  25. ICML 2025Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint
  26. ICML 2025Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems
  27. ICML 2025Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models
  28. ICML 2025Inverse Optimization via Learning Feasible Regions
  29. ICML 2025Joint Learning of Energy-based Models and their Partition Function
  30. ICML 2025Joker: Joint Optimization Framework for Lightweight Kernel Machines
  31. ICML 2025Knowledge-Guided Wasserstein Distributionally Robust Optimization
  32. ICML 2025Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication Optimization
  33. ICML 2025LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
  34. ICML 2025Latent Variable Estimation in Bayesian Black-Litterman Models
  35. ICML 2025Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
  36. ICML 2025Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best Response
  37. ICML 2025Learning Curves of Stochastic Gradient Descent in Kernel Regression
  38. ICML 2025Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback
  39. ICML 2025Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms
  40. ICML 2025Learning Mixtures of Experts with EM: A Mirror Descent Perspective
  41. ICML 2025Learning Robust Neural Processes with Risk-Averse Stochastic Optimization
  42. ICML 2025Linear convergence of Sinkhorn's algorithm for generalized static Schrödinger bridge
  43. ICML 2025LLM Data Selection and Utilization via Dynamic Bi-level Optimization
  44. ICML 2025Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization
  45. ICML 2025MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
  46. ICML 2025Meta-Black-Box-Optimization through Offline Q-function Learning
  47. ICML 2025MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
  48. ICML 2025MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES
  49. ICML 2025MixMin: Finding Data Mixtures via Convex Minimization
  50. ICML 2025Model Immunization from a Condition Number Perspective

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