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 541 篇，第 4 / 11 页

  1. ICLR 2026Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence Analysis
  2. ICLR 2026Soft Quality-Diversity Optimization
  3. ICLR 2026SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization
  4. ICLR 2026Special Unitary Parameterized Estimators of Rotation
  5. ICLR 2026SPRIG: Improving Large Language Model Performance by System Prompt Optimization
  6. ICLR 2026Stop Guessing: Choosing the Optimization-Consistent Uncertainty Measurement for Evidential Deep Learning
  7. ICLR 2026Strong Correlations Induce Cause Only Predictions in Transformer Training
  8. ICLR 2026Strongly Convex Sets in Riemannian Manifolds
  9. ICLR 2026Submodular Function Minimization with Dueling Oracle
  10. ICLR 2026SVD Provably Denoises Nearest Neighbor Data
  11. ICLR 2026Symmetry-Aware Bayesian Optimization via Max Kernels
  12. ICLR 2026Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
  13. ICLR 2026TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
  14. ICLR 2026Task-free Adaptive Meta Black-box Optimization
  15. ICLR 2026The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton
  16. ICLR 2026Token-Importance Guided Direct Preference Optimization
  17. ICLR 2026Towards Dynamic Interleaving Optimizers
  18. ICLR 2026Towards Learned Optimization Free Lunch
  19. ICLR 2026Towards Real-World Routing with Neural Combinatorial Optimization
  20. ICLR 2026Understanding and improving Shampoo and SOAP via Kullback-Leibler Minimization
  21. ICLR 2026Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
  22. ICLR 2026Unified Analyses for Hierarchical Federated Learning: Topology Selection under Data Heterogeneity
  23. ICLR 2026Unifying Formal Explanations: A Complexity-Theoretic Perspective
  24. ICLR 2026Unifying Stable Optimization and Reference Regularization in RLHF
  25. ICLR 2026Unlocking the Potential of Weighting Methods in Federated Learning Through Communication Compression
  26. ICLR 2026Why DPO is a Misspecified Estimator and How to Fix It
  27. ICLR 2026WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data
  28. ICLR 2026XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
  29. ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
  30. ICLR 2025$q$-exponential family for policy optimization
  31. ICLR 2025A Coefficient Makes SVRG Effective
  32. ICLR 2025A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
  33. ICLR 2025A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization
  34. ICLR 2025A New Perspective on Shampoo's Preconditioner
  35. ICLR 2025A Stochastic Approach to the Subset Selection Problem via Mirror Descent
  36. ICLR 2025A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
  37. ICLR 2025A Tight Convergence Analysis of Inexact Stochastic Proximal Point Algorithm for Stochastic Composite Optimization Problems
  38. ICLR 2025A Truncated Newton Method for Optimal Transport
  39. ICLR 2025A Unified Theory of Quantum Neural Network Loss Landscapes
  40. ICLR 2025Accelerated Over-Relaxation Heavy-Ball Method: Achieving Global Accelerated Convergence with Broad Generalization
  41. ICLR 2025Accelerated training through iterative gradient propagation along the residual path
  42. ICLR 2025Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization
  43. ICLR 2025AdaGrad under Anisotropic Smoothness
  44. ICLR 2025Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity
  45. ICLR 2025ADAM Optimization with Adaptive Batch Selection
  46. ICLR 2025Adaptive backtracking line search
  47. ICLR 2025Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
  48. ICLR 2025Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
  49. ICLR 2025Adaptive Pruning of Pretrained Transformer via Differential Inclusions
  50. ICLR 2025ADMM for Nonconvex Optimization under Minimal Continuity Assumption

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