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 667 篇，第 13 / 14 页

  1. NeurIPS 2025ReDit: Reward Dithering for Improved LLM Policy Optimization
  2. NeurIPS 2025RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models
  3. NeurIPS 2025RePO: Understanding Preference Learning Through ReLU-Based Optimization
  4. NeurIPS 2025Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
  5. NeurIPS 2025Rethinking PCA Through Duality
  6. NeurIPS 2025Revisiting Consensus Error: A Fine-grained Analysis of Local SGD under Second-order Data Heterogeneity
  7. NeurIPS 2025Revisiting Frank-Wolfe for Structured Nonconvex Optimization
  8. NeurIPS 2025Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
  9. NeurIPS 2025RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
  10. NeurIPS 2025Risk-aware Direct Preference Optimization under Nested Risk Measure
  11. NeurIPS 2025Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA
  12. NeurIPS 2025Robust Hyperbolic Learning with Curvature-Aware Optimization
  13. NeurIPS 2025Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
  14. NeurIPS 2025RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
  15. NeurIPS 2025RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
  16. NeurIPS 2025SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
  17. NeurIPS 2025Scalable inference of functional neural connectivity at submillisecond timescales
  18. NeurIPS 2025Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf’s Law
  19. NeurIPS 2025SDPGO: Efficient Self-Distillation Training Meets Proximal Gradient Optimization
  20. NeurIPS 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization
  21. NeurIPS 2025Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
  22. NeurIPS 2025Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
  23. NeurIPS 2025Semi-infinite Nonconvex Constrained Min-Max Optimization
  24. NeurIPS 2025Set Smoothness Unlocks Clarke Hyper-stationarity in Bilevel Optimization
  25. NeurIPS 2025Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings
  26. NeurIPS 2025Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
  27. NeurIPS 2025Sketched Adaptive Distributed Deep Learning: A Sharp Convergence Analysis
  28. NeurIPS 2025Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints
  29. NeurIPS 2025Solver-Free Decision-Focused Learning for Linear Optimization Problems
  30. NeurIPS 2025Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics
  31. NeurIPS 2025Solving the Asymmetric Traveling Salesman Problem via Trace-Guided Cost Augmentation
  32. NeurIPS 2025Spike-timing-dependent Hebbian learning as noisy gradient descent
  33. NeurIPS 2025SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes
  34. NeurIPS 2025Stab-SGD: Noise-Adaptivity in Smooth Optimization with Stability Ratios
  35. NeurIPS 2025Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$
  36. NeurIPS 2025Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
  37. NeurIPS 2025Stepsize anything: A unified learning rate schedule for budgeted-iteration training
  38. NeurIPS 2025Stochastic Gradients under Nuisances
  39. NeurIPS 2025Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization
  40. NeurIPS 2025Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate
  41. NeurIPS 2025Structure-Aware Cooperative Ensemble Evolutionary Optimization on Combinatorial Problems with Multimodal Large Language Models
  42. NeurIPS 2025SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
  43. NeurIPS 2025System Prompt Optimization with Meta-Learning
  44. NeurIPS 2025TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
  45. NeurIPS 2025Targeted Maximum Likelihood Learning: An Optimization Perspective
  46. NeurIPS 2025The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective
  47. NeurIPS 2025The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
  48. NeurIPS 2025The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization
  49. NeurIPS 2025Theoretical Investigation of Adafactor for Non-Convex Smooth Optimization
  50. NeurIPS 2025Thompson Sampling in Function Spaces via Neural Operators

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