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 16 / 47 页

  1. NeurIPS 2026Variational Active Flow Matching for Discrete Online Black-Box Optimization
  2. NeurIPS 2026Variational Trajectory Optimization of Anisotropic Diffusion Schedules
  3. NeurIPS 2026VESPO: Variational Sequence-level Soft Policy Optimization for Off-Policy LLM Training
  4. NeurIPS 2026Virtual Double Oracle: Faster Convergence by Leveraging Strategies That Were Watching All Along
  5. NeurIPS 2026VSPO: Vector-Steered Policy Optimization for Controllable Model Behavior
  6. NeurIPS 2026Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-Training
  7. NeurIPS 2026Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel Optimization
  8. CVPR 2025AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
  9. CVPR 2025Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
  10. CVPR 2025Balanced Rate-Distortion Optimization in Learned Image Compression
  11. CVPR 2025Calibrated Multi-Preference Optimization for Aligning Diffusion Models
  12. CVPR 2025CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation
  13. CVPR 2025CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion
  14. CVPR 2025Curriculum Direct Preference Optimization for Diffusion and Consistency Models
  15. CVPR 2025EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting
  16. CVPR 2025FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors
  17. CVPR 2025HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
  18. CVPR 2025InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment
  19. CVPR 2025Instance-wise Supervision-level Optimization in Active Learning
  20. CVPR 2025Investigating the Role of Weight Decay in Enhancing Nonconvex SGD
  21. CVPR 2025Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video
  22. CVPR 2025Locally Orderless Images for Optimization in Differentiable Rendering
  23. CVPR 2025PIDLoc: Cross-View Pose Optimization Network Inspired by PID Controllers
  24. CVPR 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
  25. CVPR 2025SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization
  26. CVPR 2025SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
  27. ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
  28. ICLR 2025$q$-exponential family for policy optimization
  29. ICLR 2025A Coefficient Makes SVRG Effective
  30. ICLR 2025A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
  31. ICLR 2025A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization
  32. ICLR 2025A New Perspective on Shampoo's Preconditioner
  33. ICLR 2025A Stochastic Approach to the Subset Selection Problem via Mirror Descent
  34. ICLR 2025A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
  35. ICLR 2025A Tight Convergence Analysis of Inexact Stochastic Proximal Point Algorithm for Stochastic Composite Optimization Problems
  36. ICLR 2025A Truncated Newton Method for Optimal Transport
  37. ICLR 2025A Unified Theory of Quantum Neural Network Loss Landscapes
  38. ICLR 2025Accelerated Over-Relaxation Heavy-Ball Method: Achieving Global Accelerated Convergence with Broad Generalization
  39. ICLR 2025Accelerated training through iterative gradient propagation along the residual path
  40. ICLR 2025Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization
  41. ICLR 2025AdaGrad under Anisotropic Smoothness
  42. ICLR 2025Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity
  43. ICLR 2025ADAM Optimization with Adaptive Batch Selection
  44. ICLR 2025Adaptive backtracking line search
  45. ICLR 2025Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
  46. ICLR 2025Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
  47. ICLR 2025Adaptive Pruning of Pretrained Transformer via Differential Inclusions
  48. ICLR 2025ADMM for Nonconvex Optimization under Minimal Continuity Assumption
  49. ICLR 2025ADMM for Structured Fractional Minimization
  50. ICLR 2025Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning

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