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 177 篇，第 2 / 4 页

51. ICLR 2025Deep Distributed Optimization for Large-Scale Quadratic Programming
52. ICLR 2025DeepTAGE: Deep Temporal-Aligned Gradient Enhancement for Optimizing Spiking Neural Networks
53. ICLR 2025Differentially private optimization for non-decomposable objective functions
54. ICLR 2025Diffusion Models are Evolutionary Algorithms
55. ICLR 2025Dimension Agnostic Neural Processes
56. ICLR 2025DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
57. ICLR 2025DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max Optimization
58. ICLR 2025Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism
59. ICLR 2025Does SGD really happen in tiny subspaces?
60. ICLR 2025Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
61. ICLR 2025Efficient and Robust Neural Combinatorial Optimization via Wasserstein-Based Coresets
62. ICLR 2025Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs
63. ICLR 2025Efficient Sparse PCA via Block-Diagonalization
64. ICLR 2025Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions
65. ICLR 2025Fair Submodular Cover
66. ICLR 2025Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization
67. ICLR 2025FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
68. ICLR 2025FLOPS: Forward Learning with OPtimal Sampling
69. ICLR 2025From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQ
70. ICLR 2025From Promise to Practice: Realizing High-performance Decentralized Training
71. ICLR 2025Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
72. ICLR 2025Generating Likely Counterfactuals Using Sum-Product Networks
73. ICLR 2025Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture
74. ICLR 2025Global Convergence in Neural ODEs: Impact of Activation Functions
75. ICLR 2025GOAL: A Generalist Combinatorial Optimization Agent Learner
76. ICLR 2025Gradient correlation is a key ingredient to accelerate SGD with momentum
77. ICLR 2025Gradient descent with generalized Newton’s method
78. ICLR 2025How Does Critical Batch Size Scale in Pre-training?
79. ICLR 2025Improved Approximation Algorithms for $k$-Submodular Maximization via Multilinear Extension
80. ICLR 2025Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
81. ICLR 2025Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization
82. ICLR 2025Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective Optimization
83. ICLR 2025LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace
84. ICLR 2025Last Iterate Convergence of Incremental Methods as a Model of Forgetting
85. ICLR 2025Latent Bayesian Optimization via Autoregressive Normalizing Flows
86. ICLR 2025LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics
87. ICLR 2025Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial Optimization
88. ICLR 2025Learning to Solve Differential Equation Constrained Optimization Problems
89. ICLR 2025Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling
90. ICLR 2025LICO: Large Language Models for In-Context Molecular Optimization
91. ICLR 2025LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch
92. ICLR 2025Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold
93. ICLR 2025Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
94. ICLR 2025Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression
95. ICLR 2025LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
96. ICLR 2025Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment
97. ICLR 2025Mask in the Mirror: Implicit Sparsification
98. ICLR 2025Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity
99. ICLR 2025Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
100. ICLR 2025MGDA Converges under Generalized Smoothness, Provably

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。