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 10 / 47 页

  1. ICML 2026RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
  2. ICML 2026Robust Bayesian Optimisation with Unbounded Corruptions
  3. ICML 2026Robust Contextual Optimization with Missing Covariates
  4. ICML 2026Robust Learning via Nested Distributionally Robust Optimization
  5. ICML 2026Romberg-Extrapolated Zeroth-Order Gradient Estimator: Higher-Order Bias Reduction with Preserved Leading Directional Variance
  6. ICML 2026Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
  7. ICML 2026SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
  8. ICML 2026Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
  9. ICML 2026SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference
  10. ICML 2026Scalable and Stable Estimation of Amari $\alpha$-Divergence using Random Fourier Features
  11. ICML 2026Second-Order Bilevel Optimization with Accelerated Convergence Rates
  12. ICML 2026Segment-Aligned Policy Optimization for Multi-Modal Reasoning
  13. ICML 2026Sharpness-Aware Minimization Can Hallucinate Minimizers
  14. ICML 2026SimpleGPT: Improving GPT via A Simple Normalization Strategy
  15. ICML 2026Simultaneous Confidence Bounds for Aggregated Effects via Exact Subset Optimization
  16. ICML 2026Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
  17. ICML 2026SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
  18. ICML 2026Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
  19. ICML 2026Solving Imperfect-Recall Games via Sum-of-Squares Optimization
  20. ICML 2026Solving Stochastic Variational Inequalities without the Bounded Variance Assumption
  21. ICML 2026Spatially-Adaptive Gradient Re-parameterization for 3D Large Kernel Optimization
  22. ICML 2026Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
  23. ICML 2026Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
  24. ICML 2026Step-Size Stability in Stochastic Optimization: A Theoretical Perspective
  25. ICML 2026STLA: Spatiotemporal Lookahead Alignment for Post-Training Quantization
  26. ICML 2026Stochastic Gradient Methods under Heavy-Tailed Noises in Weakly Convex Optimization
  27. ICML 2026Submodular Optimization for Minimal Augmentation in Robust Language Model Alignment
  28. ICML 2026Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
  29. ICML 2026Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
  30. ICML 2026Taking the GP Out of the Loop
  31. ICML 2026Taming Stochastic Gradient Descent: Almost Sure Convergence and Saddle-Point Avoidance under $(L_{0},L_{1})$-Smoothness
  32. ICML 2026Target-Aware Bandit Allocation for Scalable Surrogate Optimization in Chemical Space
  33. ICML 2026The Differences Between Direct Alignment Algorithms are a Blur
  34. ICML 2026The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order
  35. ICML 2026Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate
  36. ICML 2026Theoretical Challenges in Learning for Branch-and-Cut
  37. ICML 2026TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization
  38. ICML 2026Tournament Style RL: Stabilizing Policy Optimization on Non Verifiable Problems
  39. ICML 2026Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner
  40. ICML 2026Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding Analysis
  41. ICML 2026Towards Parameter-Free Temporal Difference Learning
  42. ICML 2026Trainable Nonexpansive Denoisers for Contractive Image Reconstruction
  43. ICML 2026Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
  44. ICML 2026Trajectory Stitching for Solving Inverse Problems with Flow-Based Models
  45. ICML 2026TSP with Predictions: Heatmap to Tour with Provable Guarantees
  46. ICML 2026TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization
  47. ICML 2026Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization
  48. ICML 2026UCPO: Uncertainty-Aware Policy Optimization
  49. ICML 2026Unbiased Principles, Robust Rewards
  50. ICML 2026UniDrag: Unified Multi-Field Prediction and Robust Shape Optimization for Vehicle Aerodynamics

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