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 6 / 16 页

  1. ICML 2026Autoregressive Direct Preference Optimization
  2. ICML 2026Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
  3. ICML 2026Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
  4. ICML 2026Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning
  5. ICML 2026Boosting CVaR Policy Optimization with Quantile Gradients
  6. ICML 2026Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete Time
  7. ICML 2026Bridging Spherical Black-Box Optimizers
  8. ICML 2026Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
  9. ICML 2026Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
  10. ICML 2026Certificate-Guided Pruning for Stochastic Lipschitz Optimization
  11. ICML 2026CIRBench: Evaluating Large Language Models as LLVM IR Optimizers
  12. ICML 2026Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers
  13. ICML 2026Compact Conformal Subgraphs
  14. ICML 2026Complexity of Decentralized Optimization with Mixed Affine Constraints
  15. ICML 2026Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
  16. ICML 2026Conformal Prediction for Early Stopping in Mixed Integer Optimization
  17. ICML 2026Constructing Industrial-Scale Optimization Modeling Benchmark
  18. ICML 2026Context Tuning for In-Context Optimization
  19. ICML 2026Convergence Analysis of Decentralized Hessian-/Jacobian-Free Algorithm for Nonconvex Stochastic Bilevel Optimization
  20. ICML 2026Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings
  21. ICML 2026Convergence of Steepest Descent and Adam under Non-Uniform Smoothness
  22. ICML 2026Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-Sided and Two-Sided Preconditioning
  23. ICML 2026Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms
  24. ICML 2026Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
  25. ICML 2026Cost-aware Stopping for Bayesian Optimization
  26. ICML 2026CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
  27. ICML 2026DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers
  28. ICML 2026Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
  29. ICML 2026Data Reconstruction: Identifiability and Optimization with Sample Splitting
  30. ICML 2026Data-driven Mixed Integer Optimization through Probabilistic Multi-variable Branching
  31. ICML 2026DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
  32. ICML 2026DDSVM: A Differentiable Framework for Deep Support Vector Machines with Iterative Geometry-Aware Optimization
  33. ICML 2026Decision-focused Sparse Tangent Portfolio Optimization
  34. ICML 2026DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation
  35. ICML 2026Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization
  36. ICML 2026Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation
  37. ICML 2026Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies
  38. ICML 2026Depth-Progressive Monotonic Learning without Global Backpropagation
  39. ICML 2026Design Linear Constrained Neural Layers with Implicit Convex Optimization
  40. ICML 2026Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes
  41. ICML 2026DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization
  42. ICML 2026Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement
  43. ICML 2026Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
  44. ICML 2026DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
  45. ICML 2026Distributed Stochastic $K$-Level Optimization Over Networks
  46. ICML 2026Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption
  47. ICML 2026Divide and Learn: Multi-Objective Combinatorial Optimization at Scale
  48. ICML 2026Do Transformers Need Three Projections? Systematic Study of QKV Variants
  49. ICML 2026Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
  50. ICML 2026DREAM: A Unified Framework for Drift-Corrected Federated Multi-Objective Learning

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