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 192 篇，第 3 / 4 页

101. ICML 2025Learning Curves of Stochastic Gradient Descent in Kernel Regression
102. ICML 2025Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback
103. ICML 2025Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms
104. ICML 2025Learning Mixtures of Experts with EM: A Mirror Descent Perspective
105. ICML 2025Learning Robust Neural Processes with Risk-Averse Stochastic Optimization
106. ICML 2025Linear convergence of Sinkhorn's algorithm for generalized static Schrödinger bridge
107. ICML 2025LLM Data Selection and Utilization via Dynamic Bi-level Optimization
108. ICML 2025Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization
109. ICML 2025MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
110. ICML 2025Meta-Black-Box-Optimization through Offline Q-function Learning
111. ICML 2025MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
112. ICML 2025MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES
113. ICML 2025MixMin: Finding Data Mixtures via Convex Minimization
114. ICML 2025Model Immunization from a Condition Number Perspective
115. ICML 2025Multi-Objective Causal Bayesian Optimization
116. ICML 2025Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks
117. ICML 2025Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion
118. ICML 2025Multiobjective distribution matching
119. ICML 2025Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization
120. ICML 2025Nesterov Method for Asynchronous Pipeline Parallel Optimization
121. ICML 2025Neural Event-Triggered Control with Optimal Scheduling
122. ICML 2025Neural Solver Selection for Combinatorial Optimization
123. ICML 2025Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails
124. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
125. ICML 2025Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
126. ICML 2025On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms
127. ICML 2025On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
128. ICML 2025On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning
129. ICML 2025One-Step Generalization Ratio Guided Optimization for Domain Generalization
130. ICML 2025Online Conformal Prediction via Online Optimization
131. ICML 2025Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization
132. ICML 2025Optimization for Neural Operators can Benefit from Width
133. ICML 2025Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
134. ICML 2025Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach
135. ICML 2025PARQ: Piecewise-Affine Regularized Quantization
136. ICML 2025PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
137. ICML 2025Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks
138. ICML 2025Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization
139. ICML 2025Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion
140. ICML 2025Preference Optimization for Combinatorial Optimization Problems
141. ICML 2025Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation
142. ICML 2025Probabilistic Group Mask Guided Discrete Optimization for Incremental Learning
143. ICML 2025Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent
144. ICML 2025Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity
145. ICML 2025Quantum Optimization via Gradient-Based Hamiltonian Descent
146. ICML 2025R.I.P.: Better Models by Survival of the Fittest Prompts
147. ICML 2025Radio: Rate–Distortion Optimization for Large Language Model Compression
148. ICML 2025Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures
149. ICML 2025Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
150. ICML 2025Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization

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。