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 4 / 20 页

  1. NeurIPS 2026Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets
  2. NeurIPS 2026Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
  3. NeurIPS 2026Ordered Policy Optimization
  4. NeurIPS 2026Orthogonal Updates for the Win: Towards Accelerated Adaptive Minimax Optimization
  5. NeurIPS 2026PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial Optimization
  6. NeurIPS 2026PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery
  7. NeurIPS 2026Pairwise AUC Optimization Needs Corrective Power: A Unified View
  8. NeurIPS 2026Parallel Computation Algorithms and Convergence Guarantees for Mean-Field Langevin Dynamics
  9. NeurIPS 2026ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization
  10. NeurIPS 2026Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
  11. NeurIPS 2026Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
  12. NeurIPS 2026PISG: Constraint-Aligned Signal Amplification for Diffusion-Based Combinatorial Optimization
  13. NeurIPS 2026Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions
  14. NeurIPS 2026POME: Post Optimization Model Edit via Muon-Style Projection
  15. NeurIPS 2026Position: Lottery Tickets Do Not Explain Overparameterization. How About Escape Dimensions?
  16. NeurIPS 2026Posterior Alternative Calibration in Ambiguous Inverse Problems
  17. NeurIPS 2026Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
  18. NeurIPS 2026Principled Policy Optimization for LLMs via Self-Normalized Importance Sampling
  19. NeurIPS 2026Quality-Diversity Optimization as Multi-Objective Optimization
  20. NeurIPS 2026Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise
  21. NeurIPS 2026Randomized Kriging Believer For Parallel Bayesian Optimization With Regret Bounds
  22. NeurIPS 2026Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
  23. NeurIPS 2026Rectified Policy Rollouts with Hierarchical Expert Guidance for Neural Combinatorial Optimization
  24. NeurIPS 2026Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
  25. NeurIPS 2026Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization
  26. NeurIPS 2026Regularization Paths for Continuous DAG Learning
  27. NeurIPS 2026Regularized Large Neighborhood Search
  28. NeurIPS 2026Reinforcement Learning for Code Optimization
  29. NeurIPS 2026Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
  30. NeurIPS 2026ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
  31. NeurIPS 2026Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
  32. NeurIPS 2026Replay-buffer engineering for noise-robust quantum circuit optimization
  33. NeurIPS 2026RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
  34. NeurIPS 2026Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
  35. NeurIPS 2026Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations
  36. NeurIPS 2026Rethinking Gradient Approximation in Quantization: A Zeroth-Order Expectation Perspective
  37. NeurIPS 2026Rethinking Language Model Scaling under Transferable Hypersphere Optimization
  38. NeurIPS 2026Revisiting Decentralized Online Convex Optimization with Compressed Communication
  39. NeurIPS 2026Riemannian Bilevel Optimization under the Polyak–Łojasiewicz Condition
  40. NeurIPS 2026Riemannian Lyapunov Framework: Optimization as Closed-Loop Control on Riemannian Manifolds
  41. NeurIPS 2026Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
  42. NeurIPS 2026Robust Latent Space Bayesian Optimization with Marginalized Kernel
  43. NeurIPS 2026Robust Noisy Inductive Matrix Completion with Local Linear Convergence
  44. NeurIPS 2026Robust Policy Optimization to Prevent Catastrophic Forgetting
  45. NeurIPS 2026ROCKET: Rapid Optimization via Calibration-guided Knapsack-Enhanced Truncation for Efficient Model Compression
  46. NeurIPS 2026RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology
  47. NeurIPS 2026Sample complexity of stochastic optimization with integer variables
  48. NeurIPS 2026Sample-Efficient Optimization over Generative Priors via Coarse Learnability
  49. NeurIPS 2026SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
  50. NeurIPS 2026Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits

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