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 667 篇，第 2 / 14 页

51. ICLR 2025Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
52. ICLR 2025Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models
53. ICLR 2025Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems
54. ICLR 2025Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in Games
55. ICLR 2025Bounds on $L_p$ Errors in Density Ratio Estimation via $f$-Divergence Loss Functions
56. ICLR 2025BP-Modified Local Loss for Efficient Training of Deep Neural Networks
57. ICLR 2025Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
58. ICLR 2025Can Reinforcement Learning Solve Asymmetric Combinatorial-Continuous Zero-Sum Games?
59. ICLR 2025Cauchy-Schwarz Regularizers
60. ICLR 2025Causal Discovery via Bayesian Optimization
61. ICLR 2025CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
62. ICLR 2025Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models
63. ICLR 2025Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
64. ICLR 2025CONGO: Compressive Online Gradient Optimization
65. ICLR 2025Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained Optimization
66. ICLR 2025Convergence of Distributed Adaptive Optimization with Local Updates
67. ICLR 2025Decentralized Optimization with Coupled Constraints
68. ICLR 2025Decision Information Meets Large Language Models: The Future of Explainable Operations Research
69. ICLR 2025Deconstructing What Makes a Good Optimizer for Autoregressive Language Models
70. ICLR 2025Deep Distributed Optimization for Large-Scale Quadratic Programming
71. ICLR 2025DeepTAGE: Deep Temporal-Aligned Gradient Enhancement for Optimizing Spiking Neural Networks
72. ICLR 2025Differentially private optimization for non-decomposable objective functions
73. ICLR 2025Diffusion Models are Evolutionary Algorithms
74. ICLR 2025Dimension Agnostic Neural Processes
75. ICLR 2025DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
76. ICLR 2025DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max Optimization
77. ICLR 2025Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism
78. ICLR 2025Does SGD really happen in tiny subspaces?
79. ICLR 2025Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
80. ICLR 2025Efficient and Robust Neural Combinatorial Optimization via Wasserstein-Based Coresets
81. ICLR 2025Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs
82. ICLR 2025Efficient Sparse PCA via Block-Diagonalization
83. ICLR 2025Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions
84. ICLR 2025Fair Submodular Cover
85. ICLR 2025Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization
86. ICLR 2025FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
87. ICLR 2025FLOPS: Forward Learning with OPtimal Sampling
88. ICLR 2025From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQ
89. ICLR 2025From Promise to Practice: Realizing High-performance Decentralized Training
90. ICLR 2025Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
91. ICLR 2025Generating Likely Counterfactuals Using Sum-Product Networks
92. ICLR 2025Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture
93. ICLR 2025Global Convergence in Neural ODEs: Impact of Activation Functions
94. ICLR 2025GOAL: A Generalist Combinatorial Optimization Agent Learner
95. ICLR 2025Gradient correlation is a key ingredient to accelerate SGD with momentum
96. ICLR 2025Gradient descent with generalized Newton’s method
97. ICLR 2025How Does Critical Batch Size Scale in Pre-training?
98. ICLR 2025Improved Approximation Algorithms for $k$-Submodular Maximization via Multilinear Extension
99. ICLR 2025Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
100. ICLR 2025Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization

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。