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 13 / 47 页

  1. NeurIPS 2026Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal Supervision
  2. NeurIPS 2026How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
  3. NeurIPS 2026Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization
  4. NeurIPS 2026Improving Quantized Zeroth-Order Optimization through Reconstructed Low-Rank Structures
  5. NeurIPS 2026Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates
  6. NeurIPS 2026In-Context Black-Box Optimization with Unreliable Feedback
  7. NeurIPS 2026In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
  8. NeurIPS 2026InQuant: In-Place Mixed-Precision KV Cache Quantization via Saliency-Aware Neighbor-Slot Reuse
  9. NeurIPS 2026Instance-Dependent Bandit Convex Optimization in One Dimension
  10. NeurIPS 2026Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
  11. NeurIPS 2026Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds
  12. NeurIPS 2026Jacobian Descent for Multi-Objective Optimization
  13. NeurIPS 2026Joint Optimization of Tool Creation and Use for Large Language Model Agents
  14. NeurIPS 2026Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
  15. NeurIPS 2026KnowEvo: Knowledge Evolution for Protein Optimization
  16. NeurIPS 2026Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems
  17. NeurIPS 2026Layer Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
  18. NeurIPS 2026LDPCache: Locally Differentially Private Multi-Query Processing with Cache Optimization for Large Language Models
  19. NeurIPS 2026Learning Minimal Sufficient Evidence Graphs for GraphRAG via Nash-Guided Optimization
  20. NeurIPS 2026Learning Polyhedral Conformal Sets for Robust Optimization
  21. NeurIPS 2026Learning Rate Decay Can Exponentially Accelerate SGD for Global Optimization of Nonconvex Functions
  22. NeurIPS 2026Learning to Search, Searching to Learn: A Closed-Loop Framework for Large-Scale Vehicle Routing
  23. NeurIPS 2026Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning
  24. NeurIPS 2026Likelihood-Free Generative Policy Optimization
  25. NeurIPS 2026Literati: Towards Anytime Optimal Shape Generalized Trees via AO*
  26. NeurIPS 2026Locally-Additive Regret for Delayed Non-stationary Bandit Convex Optimization
  27. NeurIPS 2026LOCU: Löwdin-Orthogonalized Constraint Updates for Multi-Constraint Policy Optimization
  28. NeurIPS 2026LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
  29. NeurIPS 2026LOTION: Smoothing the Optimization Landscape for Quantized Training
  30. NeurIPS 2026MACRO: Training-free Multi-plane Attention for Closeup Render Optimization
  31. NeurIPS 2026Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
  32. NeurIPS 2026MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
  33. NeurIPS 2026Masked Sobolev Training for Feasibility-Reliable Optimization Proxies
  34. NeurIPS 2026Match the Geometry, Skip the Surrogate: Extreme Low-Budget Optimization in High Dimensions
  35. NeurIPS 2026Median-of-Means under Structured Heavy-Tailed Noise: High-Probability Bounds for Clipped Stochastic Optimization
  36. NeurIPS 2026Minimax Optimization without Spurious Solutions in Optimal Transport Learning
  37. NeurIPS 2026Mirror Descent-Ascent for mean-field min-max problems
  38. NeurIPS 2026Mitigating Data Heterogeneity Effect in Client-Reshuffling-Based Federated Learning
  39. NeurIPS 2026Mix-Opt: Mixed Optimization for Memory-Efficient Personalization of Text-to-Image Diffusion Models
  40. NeurIPS 2026MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling
  41. NeurIPS 2026MOBO-CAPS: Multi-objective Bayesian Optimization with Cardinality-Aware Pareto Selection
  42. NeurIPS 2026Mode-Controlled Policy Optimization: A Geometry-Aware Recipe for LLM Post-Training
  43. NeurIPS 2026Module-Aware Optimization for Graph Neural Networks
  44. NeurIPS 2026MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens
  45. NeurIPS 2026Multi-Nonsmooth-Nonconvex-Objective Optimization
  46. NeurIPS 2026Nerve-Skeleton Message Passing for Federated Optimization with Overlapping Parameters
  47. NeurIPS 2026Never Go Full Batch: Stochastic TMLE for Large-Scale Debiased Inference
  48. NeurIPS 2026NLD4CO: Neural Langevin Dynamics for Combinatorial Optimization
  49. NeurIPS 2026Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise
  50. NeurIPS 2026Offline Materials Optimization with CliqueFlowmer

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