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 5 / 20 页

  1. NeurIPS 2026Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations
  2. NeurIPS 2026Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization
  3. NeurIPS 2026Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets
  4. NeurIPS 2026Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
  5. NeurIPS 2026Sharper Guarantees for Misspecified Kernelized Bandit Optimization
  6. NeurIPS 2026Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise
  7. NeurIPS 2026Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks
  8. NeurIPS 2026Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization
  9. NeurIPS 2026Skill-Coupled Policy Optimization with Calibrated Group-Wise Advantage Estimation
  10. NeurIPS 2026Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates
  11. NeurIPS 2026Sliced Wasserstein Meets Quantum Optics: Provable Wavefunctions Tomography with Scarce Noisy Measurements
  12. NeurIPS 2026SMOG: Scalable Meta-Learning for Multi-Objective Bayesian Optimization
  13. NeurIPS 2026Solving Stochastic Control under Multiplicative and Internal Noise via Constrained Optimization
  14. NeurIPS 2026SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
  15. NeurIPS 2026Spectral Annealing: Normalization-Path Exploration for Large-Scale Ising Optimization
  16. NeurIPS 2026Stabilizing Policy Optimization via Logits Convexity
  17. NeurIPS 2026Stable and Granular Policy Optimization for Generative Recommendation
  18. NeurIPS 2026Stochastic Approximation Approach for Decentralized Optimization on Time Varying Random Networks
  19. NeurIPS 2026Stochastic Dynamic Barrier Perturbed Gradient Methods for Nonconvex Simple Bilevel Optimization
  20. NeurIPS 2026Stochastic Optimization with Random Search
  21. NeurIPS 2026Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise
  22. NeurIPS 2026Structure vs. Chaos: Asymmetric Entropic Optimization for Enforcing Instruction Hierarchy
  23. NeurIPS 2026SWE-Pro: A Benchmark for Evaluating LLMs on Performance-Oriented Repository-Level Optimization
  24. NeurIPS 2026TagBO: LLM-Driven Task-Aware Graph Bayesian Optimization for Scientific Discovery
  25. NeurIPS 2026Take It or Leave It: Intent-Controlled Partial Optimal Transport
  26. NeurIPS 2026Taming the Tails: Why Distributionally Robust Optimization Needs New Theory for Imbalanced Regression
  27. NeurIPS 2026TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting
  28. NeurIPS 2026TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks
  29. NeurIPS 2026The Denoising Wrapper: A Modular Post-Processing Framework for Noisy First-Order Optimizers
  30. NeurIPS 2026The Hidden Power of Scaling Factor in LoRA Optimization
  31. NeurIPS 2026The Optimization Prior: Instilling depth for shallow networks, detail for coarse networks
  32. NeurIPS 2026Tight Generalization Bounds for Noiseless Inverse Optimization
  33. NeurIPS 2026Towards Convergence of PPO: An Approximate Descent Approach
  34. NeurIPS 2026Towards Hyperparameter Transfer for Differentially Private Optimization
  35. NeurIPS 2026Towards Settling the Complexity of Non-Euclidean Parallel Convex Optimization
  36. NeurIPS 2026TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization
  37. NeurIPS 2026Training Optimal Large Diffusion Language Models
  38. NeurIPS 2026Tree-Ensemble Repair through Constrained Optimization
  39. NeurIPS 2026TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
  40. NeurIPS 2026Truncated Riemannian (1+1)-ES for Black-Box Optimization with Intrinsic Dimension Guarantees
  41. NeurIPS 2026UECO: A Unified Encoder with Structure-Aware Attention Mixture via Iterative Edge Evolving for Neural Combinatorial Optimization
  42. NeurIPS 2026Unifying Sparsity and Discreteness: One-Shot Pruning for Quantized LLMs via Discrete Optimization
  43. NeurIPS 2026Universal Adaptive Proximal Gradient Methods via Gradient Mapping Accumulation
  44. NeurIPS 2026Variational Active Flow Matching for Discrete Online Black-Box Optimization
  45. NeurIPS 2026Variational Trajectory Optimization of Anisotropic Diffusion Schedules
  46. NeurIPS 2026VESPO: Variational Sequence-level Soft Policy Optimization for Off-Policy LLM Training
  47. NeurIPS 2026Virtual Double Oracle: Faster Convergence by Leveraging Strategies That Were Watching All Along
  48. NeurIPS 2026VSPO: Vector-Steered Policy Optimization for Controllable Model Behavior
  49. NeurIPS 2026Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-Training
  50. NeurIPS 2026Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel 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