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 958 篇，第 9 / 20 页

  1. NeurIPS 2025MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees
  2. NeurIPS 2025Meta-Learning Objectives for Preference Optimization
  3. NeurIPS 2025MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization
  4. NeurIPS 2025MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
  5. NeurIPS 2025MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
  6. NeurIPS 2025Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling
  7. NeurIPS 2025MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions
  8. NeurIPS 2025Momentum-SAM: Sharpness Aware Minimization without Computational Overhead
  9. NeurIPS 2025Multi-Expert Distributionally Robust Optimization for Out-of-Distribution Generalization
  10. NeurIPS 2025Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms
  11. NeurIPS 2025Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
  12. NeurIPS 2025Natural Gradient VI: Guarantees for Non-Conjugate Models
  13. NeurIPS 2025Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference
  14. NeurIPS 2025Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data
  15. NeurIPS 2025New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results
  16. NeurIPS 2025No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization
  17. NeurIPS 2025Non-convex entropic mean-field optimization via Best Response flow
  18. NeurIPS 2025Non-Convex Tensor Recovery from Tube-Wise Sensing
  19. NeurIPS 2025Non-monotone Submodular Optimization: $p$-Matchoid Constraints and Fully Dynamic Setting
  20. NeurIPS 2025Non-Singularity of the Gradient Descent Map for Neural Networks with Piecewise Analytic Activations
  21. NeurIPS 2025Non-stationary Bandit Convex Optimization: A Comprehensive Study
  22. NeurIPS 2025Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
  23. NeurIPS 2025NopeRoomGS: Indoor 3D Gaussian Splatting Optimization without Camera Pose Input
  24. NeurIPS 2025Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies
  25. NeurIPS 2025Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
  26. NeurIPS 2025OMiSO: Adaptive optimization of state-dependent brain stimulation to shape neural population states
  27. NeurIPS 2025Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization
  28. NeurIPS 2025On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders
  29. NeurIPS 2025On Extending Direct Preference Optimization to Accommodate Ties
  30. NeurIPS 2025On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
  31. NeurIPS 2025On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
  32. NeurIPS 2025On the Convergence of Single-Timescale Actor-Critic
  33. NeurIPS 2025On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent Ascent
  34. NeurIPS 2025On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
  35. NeurIPS 2025On the Sample Complexity Bounds of Bilevel Reinforcement Learning
  36. NeurIPS 2025On Traceability in $\ell_p$ Stochastic Convex Optimization
  37. NeurIPS 2025Online Optimization for Offline Safe Reinforcement Learning
  38. NeurIPS 2025Online Strategic Classification With Noise and Partial Feedback
  39. NeurIPS 2025Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality
  40. NeurIPS 2025PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization
  41. NeurIPS 2025Partial Correlation Network Estimation by Semismooth Newton Methods
  42. NeurIPS 2025Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
  43. NeurIPS 2025PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs
  44. NeurIPS 2025PDPO: Parametric Density Path Optimization
  45. NeurIPS 2025Per-Architecture Training-Free Metric Optimization for Neural Architecture Search
  46. NeurIPS 2025PhySense: Sensor Placement Optimization for Accurate Physics Sensing
  47. NeurIPS 2025Preference Optimization by Estimating the Ratio of the Data Distribution
  48. NeurIPS 2025Preference-Guided Diffusion for Multi-Objective Offline Optimization
  49. NeurIPS 2025Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
  50. NeurIPS 2025PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs

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