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 8 / 47 页

  1. ICML 2026Iterated Population Based Training with Task-Agnostic Restarts
  2. ICML 2026Iterative Robust Satisficing: Minimizing Performance Degradation Under Distribution Shift
  3. ICML 2026Joint Learning in the Gaussian Single Index Model
  4. ICML 2026KernelFoundry: Hardware-Aware Evolutionary GPU Kernel Optimization
  5. ICML 2026L-SR1: Learned Symmetric-Rank-One Preconditioning
  6. ICML 2026Langevin Rollout Optimization for Modelic Reinforcement Learning
  7. ICML 2026Last-iterate Convergence of ADMM on Multi-affine Quadratic Equality Constrained Problem
  8. ICML 2026Latent Space Robust Optimization of Neural Processes with Aligned Stratified Order-Statistic Loss Reduction
  9. ICML 2026Layer-wise Gradient Disentanglement: Decoupling Semantics and Preferences in Direct Preference Optimization
  10. ICML 2026Learning Credal Ensembles via Distributionally Robust Optimization
  11. ICML 2026Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective
  12. ICML 2026Learning from Comparison: Constrained Projection Policy Optimization for Pareto-Front Improvement
  13. ICML 2026Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent
  14. ICML 2026Learning Permutation from Structure Without Supervision
  15. ICML 2026Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization
  16. ICML 2026Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts
  17. ICML 2026Learning-to-Optimize via Deep Unfolded Flows
  18. ICML 2026LILO: Bayesian Optimization with Natural Language Feedback
  19. ICML 2026LiMuon: Light and Fast Muon Optimizer for Large Models
  20. ICML 2026Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
  21. ICML 2026Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noises
  22. ICML 2026LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding
  23. ICML 2026Local Constrained Bayesian Optimization
  24. ICML 2026Local Minima in Quadratic-Penalty Relaxations of Binary Linear Programs
  25. ICML 2026Local-Minima-Preserving Polynomial Relaxation of Ising Problems
  26. ICML 2026Lookahead Path Likelihood Optimization for Diffusion LLMs
  27. ICML 2026Loss-Aware Distributionally Robust Optimization via Trainable Optimal Transport Ambiguity Sets
  28. ICML 2026Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles
  29. ICML 2026LS$^{2}$MC-GDA: A Smoothed Algorithm for Federated Stochastic Multi-Level Compositional Minimax Optimization
  30. ICML 2026M+Adam: Low-Precision Training via Additive–Multiplicative Optimization
  31. ICML 2026MaxSAT-Based Compression for Tsetlin Machines
  32. ICML 2026Mean Flow Policy Optimization
  33. ICML 2026Memory Savings at What Cost? A Study of Alternatives to Backpropagation
  34. ICML 2026Meta-Black-Box Optimization Can Do Search Guidance for Expensive Constrained Multi-Objective Optimization
  35. ICML 2026MineDraft: A Framework for Batch Parallel Speculative Decoding
  36. ICML 2026MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification
  37. ICML 2026Minimizing Upper Confidence Bounds: A Data-Driven Framework for Stochastic Programming
  38. ICML 2026Mirror Descent Under Generalized Smoothness
  39. ICML 2026Mirror Mean-Field Langevin Dynamics
  40. ICML 2026Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation
  41. ICML 2026MoSSP: A Momentum-Based Single-Loop Stochastic Penalty Method for Nonconvex Constrained DC-regularized Optimization
  42. ICML 2026MuCO: Generative Peptide Cyclization Empowered by Multi-stage Conformation Optimization
  43. ICML 2026Multi-Objective Bayesian Optimization via Adaptive $\varepsilon$-Constraint Decomposition
  44. ICML 2026Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation
  45. ICML 2026Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
  46. ICML 2026Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0,L_1)$-Smoothness
  47. ICML 2026Neural QAOA$^2$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
  48. ICML 2026Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization
  49. ICML 2026Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems
  50. ICML 2026Nonconvex Low-Rank Tensor Representation with Deep Priors for Multiview Subspace Clustering

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