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 757 篇，第 7 / 16 页

  1. ICML 2026DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise
  2. ICML 2026Dual Quaternion SE(3) Synchronization with Recovery Guarantees
  3. ICML 2026Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training
  4. ICML 2026ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization
  5. ICML 2026Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing
  6. ICML 2026Efficient Diffusion Models via Time Step Optimization with Consistent Training and Inference Constraints
  7. ICML 2026Efficient Distributionally Robust Assortment Optimization in MNL Bandits
  8. ICML 2026Eliminating Solution Bias in Differentially Private Optimization
  9. ICML 2026Evolution of Benchmark: Black-Box Optimization Benchmark Design through Large Language Model
  10. ICML 2026Exploiting weight-space symmetries for approximating curvature
  11. ICML 2026FAB: A First-Order AB-based Gradient Algorithm for Distributed Bilevel Optimization over Time-Varying Directed Graphs
  12. ICML 2026Failure-Driven Workflow Refinement
  13. ICML 2026Fast Spectrally Sparse Signal Reconstruction via Jacobi-Preconditioned Gradient Descent
  14. ICML 2026FedCDWA: Decoupled Federated Prototype Distillation with Hierarchical Wasserstein Aggregation
  15. ICML 2026Federated Bilevel Performative Prediction
  16. ICML 2026FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction
  17. ICML 2026Finding Stationary Points by Comparisons
  18. ICML 2026Finite-time Convergence Analysis of Actor-Critic with Evolving Reward
  19. ICML 2026Flat Minima and Generalization: Insights from Stochastic Convex Optimization
  20. ICML 2026Flatland: The Adventures of Gradient Descent with Large Step Sizes
  21. ICML 2026Flatness-Aware Stochastic Gradient Langevin Dynamics
  22. ICML 2026FOAM: Frequency and Operator-Error Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
  23. ICML 2026From Lyapunov Analysis to Algorithm Design in two-sided PL Minimax Optimization
  24. ICML 2026From Muon to Gluon: Bridging Theory and Practice of LMO-based Optimizers for LLMs
  25. ICML 2026From Optimization to Generalization under Heavy-Tailed Data: The Role of Gradient Clipping
  26. ICML 2026Generative Large Neighborhood Search: Scalable Set Cover Optimization via Discrete Diffusion
  27. ICML 2026Geometric Convergence of Gauss–Newton for Neural Networks: Riemannian Geometry and Adaptive Damping
  28. ICML 2026Geometry-Misalignment in Distributional Learning
  29. ICML 2026GIPO: Gaussian Importance Sampling Policy Optimization
  30. ICML 2026GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry
  31. ICML 2026Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
  32. ICML 2026Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimization
  33. ICML 2026Gradient Flow Sampler-based Distributionally Robust Optimization
  34. ICML 2026Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization
  35. ICML 2026Gradient Testing and Estimation by Comparisons
  36. ICML 2026Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity
  37. ICML 2026GradPower: Powering Gradients for Faster Language Model Pre-Training
  38. ICML 2026GRPO is Secretly a Process Reward Model
  39. ICML 2026Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization
  40. ICML 2026High-Probability Convergence Guarantees of Decentralized SGD
  41. ICML 2026HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
  42. ICML 2026Hom-PGD$^+$: Fast Reparameterized Optimization over Non-convex Ball-Homeomorphic Set
  43. ICML 2026HONet: Data-Efficient Learning for Exact Cover Tasks via Hypergraph Optimization
  44. ICML 2026How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
  45. ICML 2026Improved Convergence Analysis of Topology Dependence in Decentralized SGD
  46. ICML 2026Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variation
  47. ICML 2026Improved Stochastic Optimization of LogSumExp
  48. ICML 2026Improving Explicit Dynamic Gaussian Splatting Optimization via Update Mixture
  49. ICML 2026In-Context Learning as Rate–Distortion Optimization
  50. ICML 2026Incremental Learning of Sparse Attention Patterns in Transformers

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