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 757 篇，第 5 / 16 页

  1. ICLR 2026Strongly Convex Sets in Riemannian Manifolds
  2. ICLR 2026Submodular Function Minimization with Dueling Oracle
  3. ICLR 2026SVD Provably Denoises Nearest Neighbor Data
  4. ICLR 2026Symmetry-Aware Bayesian Optimization via Max Kernels
  5. ICLR 2026Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
  6. ICLR 2026TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
  7. ICLR 2026Task-free Adaptive Meta Black-box Optimization
  8. ICLR 2026The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton
  9. ICLR 2026Token-Importance Guided Direct Preference Optimization
  10. ICLR 2026Towards Dynamic Interleaving Optimizers
  11. ICLR 2026Towards Learned Optimization Free Lunch
  12. ICLR 2026Towards Real-World Routing with Neural Combinatorial Optimization
  13. ICLR 2026Understanding and improving Shampoo and SOAP via Kullback-Leibler Minimization
  14. ICLR 2026Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
  15. ICLR 2026Unified Analyses for Hierarchical Federated Learning: Topology Selection under Data Heterogeneity
  16. ICLR 2026Unifying Formal Explanations: A Complexity-Theoretic Perspective
  17. ICLR 2026Unifying Stable Optimization and Reference Regularization in RLHF
  18. ICLR 2026Unlocking the Potential of Weighting Methods in Federated Learning Through Communication Compression
  19. ICLR 2026Why DPO is a Misspecified Estimator and How to Fix It
  20. ICLR 2026WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data
  21. ICLR 2026XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
  22. ICML 2026$\alpha$-PFN: Fast Entropy Search via In-Context Learning
  23. ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
  24. ICML 2026$\texttt{MetaDistill}$: Unlocking the Performance Ceiling for Pretrained Optimizers
  25. ICML 2026A Constrained Optimization Perspective of Unrolled Transformers
  26. ICML 2026A Fully First-Order Layer for Differentiable Optimization
  27. ICML 2026A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention
  28. ICML 2026A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search
  29. ICML 2026A Linearly Convergent Proximal Subgradient Algorithm for Sparse Portfolio Optimization with Transaction Cost
  30. ICML 2026A proximal ADMM for multiblock problems with block anti-upper triangular constraints
  31. ICML 2026A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
  32. ICML 2026A Solver-Free Training Method for Predict-then-Optimize
  33. ICML 2026A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization
  34. ICML 2026A Tight Theory of Error Feedback Algorithms in Distributed Optimization
  35. ICML 2026Accelerated and Stable Convergence with Anchored Generalized Optimistic Method
  36. ICML 2026Accelerated Dual Method for Distributed Optimization: An Inexact-Gradient View of Local Updates
  37. ICML 2026Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional Optimization
  38. ICML 2026Achieving Structurally Robust Gromov Wasserstein Distance via Adaptive Dual-Mask
  39. ICML 2026Adapting to Evolving Graphs: A Scalable Framework for Dynamic Coarsening
  40. ICML 2026Adaptive Momentum and Nonlinear Damping for Neural Network Training
  41. ICML 2026Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
  42. ICML 2026AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
  43. ICML 2026ALAS: Additive Learnable Alpha-Stable Kernels for Flexible Bayesian Optimization
  44. ICML 2026All ERMs Can Fail in Stochastic Convex Optimization Lower Bounds in Linear Dimension
  45. ICML 2026AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training
  46. ICML 2026An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale
  47. ICML 2026An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants
  48. ICML 2026An Exterior Method for Nonnegative Matrix Factorization
  49. ICML 2026ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization
  50. ICML 2026Asymmetric Perturbation in Solving Bilinear Saddle-Point 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