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 5 / 15 页

  1. ICML 2026Parallel Stochastic Gradient-Based Planning for World Models
  2. ICML 2026Parameter-Masked Decoupled Optimization for Cross-Domain Class-Incremental Learning
  3. ICML 2026PASO: Step Parallel Stochastic Optimization
  4. ICML 2026PepCompass: Navigating Peptide Embedding Spaces Using Riemannian Geometry
  5. ICML 2026PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization
  6. ICML 2026Policy Search via Bayesian Optimization with Temporal Difference Gaussian Processes
  7. ICML 2026Preconditioning Neural Tangent Kernel for Adaptive Optimization
  8. ICML 2026Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction
  9. ICML 2026Preference-Modulated Structural Attention for Multi-Objective Combinatorial Optimization
  10. ICML 2026Probability of Matching for Batch Multi-Objective Bayesian Optimization
  11. ICML 2026Projection-Free Algorithms for Minimax Problems
  12. ICML 2026QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
  13. ICML 2026Randomized Feasibility Methods for Constrained Optimization with Adaptive Step Sizes
  14. ICML 2026Ratio-Variance Regularized Policy Optimization
  15. ICML 2026Recursive Monte-Carlo Tree Search
  16. ICML 2026Reducing Per-Sample Harm in Stochastic Optimization
  17. ICML 2026Reflect-then-Correct: Rebalancing Task Optimization for Generalizable Meta-Reinforcement Learning via Distributional Value Error Reduction
  18. ICML 2026Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes
  19. ICML 2026Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
  20. ICML 2026Reparameterization Flow Policy Optimization
  21. ICML 2026Reparameterization Proximal Policy Optimization
  22. ICML 2026Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models
  23. ICML 2026Rethinking Convergence in MoE Training: The Role of Routing Sparsity
  24. ICML 2026Rethinking Neural Network Learning Rates: A Stackelberg Perspective
  25. ICML 2026Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games
  26. ICML 2026Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens
  27. ICML 2026Riemannian Dueling Optimization
  28. ICML 2026Riemannian Optimization for Fair Spectral Clustering
  29. ICML 2026Riemannian stochastic optimization for sufficient dimension reduction
  30. ICML 2026RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
  31. ICML 2026Robust Bayesian Optimisation with Unbounded Corruptions
  32. ICML 2026Robust Contextual Optimization with Missing Covariates
  33. ICML 2026Robust Learning via Nested Distributionally Robust Optimization
  34. ICML 2026Romberg-Extrapolated Zeroth-Order Gradient Estimator: Higher-Order Bias Reduction with Preserved Leading Directional Variance
  35. ICML 2026Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
  36. ICML 2026SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
  37. ICML 2026Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
  38. ICML 2026SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference
  39. ICML 2026Scalable and Stable Estimation of Amari $\alpha$-Divergence using Random Fourier Features
  40. ICML 2026Second-Order Bilevel Optimization with Accelerated Convergence Rates
  41. ICML 2026Segment-Aligned Policy Optimization for Multi-Modal Reasoning
  42. ICML 2026Sharpness-Aware Minimization Can Hallucinate Minimizers
  43. ICML 2026SimpleGPT: Improving GPT via A Simple Normalization Strategy
  44. ICML 2026Simultaneous Confidence Bounds for Aggregated Effects via Exact Subset Optimization
  45. ICML 2026Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
  46. ICML 2026SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
  47. ICML 2026Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
  48. ICML 2026Solving Imperfect-Recall Games via Sum-of-Squares Optimization
  49. ICML 2026Solving Stochastic Variational Inequalities without the Bounded Variance Assumption
  50. ICML 2026Spatially-Adaptive Gradient Re-parameterization for 3D Large Kernel 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