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 9 / 11 页

  1. ICLR 2024How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
  2. ICLR 2024Implicit Maximum a Posteriori Filtering via Adaptive Optimization
  3. ICLR 2024Implicit regularization of deep residual networks towards neural ODEs
  4. ICLR 2024Improving Convergence and Generalization Using Parameter Symmetries
  5. ICLR 2024Improving protein optimization with smoothed fitness landscapes
  6. ICLR 2024Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach
  7. ICLR 2024L2P-MIP: Learning to Presolve for Mixed Integer Programming
  8. ICLR 2024Language Model Decoding as Direct Metrics Optimization
  9. ICLR 2024Large Language Models to Enhance Bayesian Optimization
  10. ICLR 2024Learning model uncertainty as variance-minimizing instance weights
  11. ICLR 2024Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder Model
  12. ICLR 2024Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning
  13. ICLR 2024Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Lightweight Optimizer and Small-scale Training Dataset
  14. ICLR 2024Linear attention is (maybe) all you need (to understand Transformer optimization)
  15. ICLR 2024Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts
  16. ICLR 2024Local Composite Saddle Point Optimization
  17. ICLR 2024Magnitude Invariant Parametrizations Improve Hypernetwork Learning
  18. ICLR 2024Massively Scalable Inverse Reinforcement Learning in Google Maps
  19. ICLR 2024Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis
  20. ICLR 2024Meta-VBO: Utilizing Prior Tasks in Optimizing Risk Measures with Gaussian Processes
  21. ICLR 2024Momentum Benefits Non-iid Federated Learning Simply and Provably
  22. ICLR 2024Near-Optimal Solutions of Constrained Learning Problems
  23. ICLR 2024Neur2RO: Neural Two-Stage Robust Optimization
  24. ICLR 2024Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization
  25. ICLR 2024New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
  26. ICLR 2024On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
  27. ICLR 2024On Stationary Point Convergence of PPO-Clip
  28. ICLR 2024On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
  29. ICLR 2024On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback
  30. ICLR 2024On the Parameterization of Second-Order Optimization Effective towards the Infinite Width
  31. ICLR 2024One Forward is Enough for Neural Network Training via Likelihood Ratio Method
  32. ICLR 2024Optimistic Bayesian Optimization with Unknown Constraints
  33. ICLR 2024Order-Preserving GFlowNets
  34. ICLR 2024Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
  35. ICLR 2024Private Zeroth-Order Nonsmooth Nonconvex Optimization
  36. ICLR 2024PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
  37. ICLR 2024Quality-Diversity through AI Feedback
  38. ICLR 2024Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How
  39. ICLR 2024Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks
  40. ICLR 2024Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization
  41. ICLR 2024Rethinking Branching on Exact Combinatorial Optimization Solver: The First Deep Symbolic Discovery Framework
  42. ICLR 2024Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
  43. ICLR 2024Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods
  44. ICLR 2024Robust Model-Based Optimization for Challenging Fitness Landscapes
  45. ICLR 2024Scaling Convex Neural Networks with Burer-Monteiro Factorization
  46. ICLR 2024SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
  47. ICLR 2024Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity
  48. ICLR 2024Small-scale proxies for large-scale Transformer training instabilities
  49. ICLR 2024Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
  50. ICLR 2024Statistical Rejection Sampling Improves Preference Optimization

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