非凸优化论文趋势 2023–2026

主要结论

• 非凸优化论文从 2023 年的 346 篇增长到 2026 年的 757 篇，三年间扩大到约 2.2 倍。
• NeurIPS 是发非凸优化论文最多的会议，2023–2026 年共 958 篇，占四个会议总量的 41%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 44 篇。
• 在「优化与缩放」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的缩放定律是 4.1 倍，非凸优化是 2.2 倍。

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

• NeurIPS 2026$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
• ICML 2026$\texttt{MetaDistill}$: Unlocking the Performance Ceiling for Pretrained Optimizers
• ICLR 2026Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction
• CVPR 2026Coverage Optimization for Camera View Selection
• NeurIPS 2025Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation
• ICML 2025A Bregman Proximal Viewpoint on Neural Operators
• ICLR 2025A Truncated Newton Method for Optimal Transport
• CVPR 2025Balanced Rate-Distortion Optimization in Learned Image Compression
• NeurIPS 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
• ICML 2024A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional Optimization
• ICLR 2024Bayesian Coreset Optimization for Personalized Federated Learning
• CVPR 2024FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance
• NeurIPS 2023A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting
• ICML 2023A Distribution Optimization Framework for Confidence Bounds of Risk Measures
• ICLR 2023A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.
• CVPR 2023Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization
• NeurIPS 2026A Doubly Smoothed Decentralized Stochastic Minimax Optimization Algorithm
• ICML 2026A Constrained Optimization Perspective of Unrolled Transformers
• ICLR 2026BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
• CVPR 2026Fully Decentralized Certified Unlearning

全部非凸优化论文

共 286 篇，第 1 / 6 页

1. ICML 2026$\alpha$-PFN: Fast Entropy Search via In-Context Learning
2. ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
3. ICML 2026$\texttt{MetaDistill}$: Unlocking the Performance Ceiling for Pretrained Optimizers
4. ICML 2026A Constrained Optimization Perspective of Unrolled Transformers
5. ICML 2026A Fully First-Order Layer for Differentiable Optimization
6. ICML 2026A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention
7. ICML 2026A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search
8. ICML 2026A Linearly Convergent Proximal Subgradient Algorithm for Sparse Portfolio Optimization with Transaction Cost
9. ICML 2026A proximal ADMM for multiblock problems with block anti-upper triangular constraints
10. ICML 2026A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
11. ICML 2026A Solver-Free Training Method for Predict-then-Optimize
12. ICML 2026A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization
13. ICML 2026A Tight Theory of Error Feedback Algorithms in Distributed Optimization
14. ICML 2026Accelerated and Stable Convergence with Anchored Generalized Optimistic Method
15. ICML 2026Accelerated Dual Method for Distributed Optimization: An Inexact-Gradient View of Local Updates
16. ICML 2026Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional Optimization
17. ICML 2026Achieving Structurally Robust Gromov Wasserstein Distance via Adaptive Dual-Mask
18. ICML 2026Adapting to Evolving Graphs: A Scalable Framework for Dynamic Coarsening
19. ICML 2026Adaptive Momentum and Nonlinear Damping for Neural Network Training
20. ICML 2026Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
21. ICML 2026AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
22. ICML 2026ALAS: Additive Learnable Alpha-Stable Kernels for Flexible Bayesian Optimization
23. ICML 2026All ERMs Can Fail in Stochastic Convex Optimization Lower Bounds in Linear Dimension
24. ICML 2026AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training
25. ICML 2026An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale
26. ICML 2026An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants
27. ICML 2026An Exterior Method for Nonnegative Matrix Factorization
28. ICML 2026ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization
29. ICML 2026Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
30. ICML 2026Autoregressive Direct Preference Optimization
31. ICML 2026Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
32. ICML 2026Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
33. ICML 2026Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning
34. ICML 2026Boosting CVaR Policy Optimization with Quantile Gradients
35. ICML 2026Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete Time
36. ICML 2026Bridging Spherical Black-Box Optimizers
37. ICML 2026Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
38. ICML 2026Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
39. ICML 2026Certificate-Guided Pruning for Stochastic Lipschitz Optimization
40. ICML 2026CIRBench: Evaluating Large Language Models as LLVM IR Optimizers
41. ICML 2026Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers
42. ICML 2026Compact Conformal Subgraphs
43. ICML 2026Complexity of Decentralized Optimization with Mixed Affine Constraints
44. ICML 2026Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
45. ICML 2026Conformal Prediction for Early Stopping in Mixed Integer Optimization
46. ICML 2026Constructing Industrial-Scale Optimization Modeling Benchmark
47. ICML 2026Context Tuning for In-Context Optimization
48. ICML 2026Convergence Analysis of Decentralized Hessian-/Jacobian-Free Algorithm for Nonconvex Stochastic Bilevel Optimization
49. ICML 2026Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings
50. ICML 2026Convergence of Steepest Descent and Adam under Non-Uniform Smoothness

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。