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 2 / 20 页

  1. NeurIPS 2026Decoupled Optimization for Teacher-Student Semi-Supervised Learning via a Pioneer Student
  2. NeurIPS 2026Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
  3. NeurIPS 2026Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty Aware Differentiable Optimization
  4. NeurIPS 2026Diffusion Transformers with Residual Adaptive Layer Normalization
  5. NeurIPS 2026Diffusion-State Policy Optimization for Masked Diffusion Language Models
  6. NeurIPS 2026DisCoMBO: Steering Expert-in-the-Loop Black Box Optimization via Distributional Conformance
  7. NeurIPS 2026Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
  8. NeurIPS 2026Disentangling Optimization Geometry via Hierarchical Polar Adapters for Class-Incremental Learning
  9. NeurIPS 2026Distribution-Adaptive Policy Optimization
  10. NeurIPS 2026Distributionally Robust Black Box Optimization-based Bidding Strategy in Auction-based Federated Learning
  11. NeurIPS 2026Distributionally Robust Listwise Preference Optimization
  12. NeurIPS 2026Distributionally Robust Token Optimization in RLHF
  13. NeurIPS 2026Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods
  14. NeurIPS 2026Don't Waste Population: Post-Anneal Refinement for Combinatorial Optimization
  15. NeurIPS 2026DP-EGGROLL: Centered Fitness-Vector Privatization for Backprop-Free Differentially Private Optimization
  16. NeurIPS 2026DrPO: Drifting Preference Optimization for One-Step Generative Models
  17. NeurIPS 2026DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization
  18. NeurIPS 2026E-GEO: A Testbed for Generative Engine Optimization in E-Commerce
  19. NeurIPS 2026EDISCO: Equivariant Discrete Diffusion for Euclidean Combinatorial Optimization
  20. NeurIPS 2026EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning Optimization
  21. NeurIPS 2026ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning
  22. NeurIPS 2026EpiPivot: Learning to Control the Simplex Method under Epistemic Uncertainty
  23. NeurIPS 2026Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
  24. NeurIPS 2026Exploration as Constrained Policy-Space Optimization
  25. NeurIPS 2026Federated Distributionally Robust Neural Combinatorial Optimization with Convergence Guarantees
  26. NeurIPS 2026Finding Simple Proofs for First-Order Optimization
  27. NeurIPS 2026Finite-Resolution Decision Sufficiency for Linear Optimization
  28. NeurIPS 2026Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints
  29. NeurIPS 2026Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models
  30. NeurIPS 2026Follow the Regularized Leader Does Not Converge in Constrained Optimization
  31. NeurIPS 2026From Cursed to Competitive: Closing the ZO–FO Gap via Input-to-State Stability
  32. NeurIPS 2026From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
  33. NeurIPS 2026Fully First-Order Algorithms for Online Non-Convex Bilevel Optimization
  34. NeurIPS 2026Functional Gradient Descent with Adaptive Representations
  35. NeurIPS 2026Geometry-Aware Zeroth-Order Optimization for Fine-Tuning Quantized LLMs
  36. NeurIPS 2026Global Convergence in Deep Networks via the Second Law of Thermodynamics
  37. NeurIPS 2026Global Convergence of Four-Layer Matrix Factorization under Random Initialization
  38. NeurIPS 2026Gradient Descent’s Last Iterate is Often (slightly) Suboptimal
  39. NeurIPS 2026Gradient Regularized Newton Boosting Trees with Global Convergence
  40. NeurIPS 2026Group Distributionally Robust Optimization with Flexible Sample Queries
  41. NeurIPS 2026Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
  42. NeurIPS 2026Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold
  43. NeurIPS 2026HALO: Homotopy-Augmented Layer Optimization for Stable LLM Supervised Post-training
  44. NeurIPS 2026Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal Supervision
  45. NeurIPS 2026How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
  46. NeurIPS 2026Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization
  47. NeurIPS 2026Improving Quantized Zeroth-Order Optimization through Reconstructed Low-Rank Structures
  48. NeurIPS 2026Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates
  49. NeurIPS 2026In-Context Black-Box Optimization with Unreliable Feedback
  50. NeurIPS 2026In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise

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