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 9 / 16 页

  1. ICML 2026Normalized Rewards for Preference Optimization
  2. ICML 2026Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence
  3. ICML 2026Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation
  4. ICML 2026OLion: Approaching the Hadamard Ideal by Intersecting Spectral and L inf Implicit Biases
  5. ICML 2026On Densest $k$-Subgraph Mining and Diagonal Loading: Optimization Landscape and Finite-Step Exact Convergence Analysis
  6. ICML 2026On Regret Bounds of Thompson Sampling for Bayesian Optimization
  7. ICML 2026On the Anisotropy of Score-Based Generative Models
  8. ICML 2026On the Convergence of Decentralized Stochastic Minimax Optimization Algorithm with Compressed Communication
  9. ICML 2026On the Convergence Rate of LoRA Gradient Descent
  10. ICML 2026On the Optimization Trajectory of DeepWalk Embeddings
  11. ICML 2026On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
  12. ICML 2026On the Role of Batch Size in Stochastic Conditional Gradient Methods
  13. ICML 2026One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
  14. ICML 2026Operator Splitting with Hamilton-Jacobi-based Proximals
  15. ICML 2026OPIC: Enhancing Language Model Merging via Optimizing In-Context Capability
  16. ICML 2026Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification
  17. ICML 2026Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints
  18. ICML 2026Optimal Regret for Policy Optimization in Contextual Bandits
  19. ICML 2026Optimal Transport with Symmetry Groups
  20. ICML 2026Optimal Transport–Guided Stochastic Control for Graph Combinatorial Optimization
  21. ICML 2026OptMaster: A DAG-Based Framework for Formulation and Heuristic Discovery in Optimization
  22. ICML 2026Parallel Stochastic Gradient-Based Planning for World Models
  23. ICML 2026Parameter-Masked Decoupled Optimization for Cross-Domain Class-Incremental Learning
  24. ICML 2026PASO: Step Parallel Stochastic Optimization
  25. ICML 2026PepCompass: Navigating Peptide Embedding Spaces Using Riemannian Geometry
  26. ICML 2026PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization
  27. ICML 2026Policy Search via Bayesian Optimization with Temporal Difference Gaussian Processes
  28. ICML 2026Preconditioning Neural Tangent Kernel for Adaptive Optimization
  29. ICML 2026Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction
  30. ICML 2026Preference-Modulated Structural Attention for Multi-Objective Combinatorial Optimization
  31. ICML 2026Probability of Matching for Batch Multi-Objective Bayesian Optimization
  32. ICML 2026Projection-Free Algorithms for Minimax Problems
  33. ICML 2026QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
  34. ICML 2026Randomized Feasibility Methods for Constrained Optimization with Adaptive Step Sizes
  35. ICML 2026Ratio-Variance Regularized Policy Optimization
  36. ICML 2026Recursive Monte-Carlo Tree Search
  37. ICML 2026Reducing Per-Sample Harm in Stochastic Optimization
  38. ICML 2026Reflect-then-Correct: Rebalancing Task Optimization for Generalizable Meta-Reinforcement Learning via Distributional Value Error Reduction
  39. ICML 2026Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes
  40. ICML 2026Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
  41. ICML 2026Reparameterization Flow Policy Optimization
  42. ICML 2026Reparameterization Proximal Policy Optimization
  43. ICML 2026Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models
  44. ICML 2026Rethinking Convergence in MoE Training: The Role of Routing Sparsity
  45. ICML 2026Rethinking Neural Network Learning Rates: A Stackelberg Perspective
  46. ICML 2026Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games
  47. ICML 2026Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens
  48. ICML 2026Riemannian Dueling Optimization
  49. ICML 2026Riemannian Optimization for Fair Spectral Clustering
  50. ICML 2026Riemannian stochastic optimization for sufficient dimension reduction

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