深度学习 · optimization论文趋势 2023–2026

主要结论

• 深度学习 · optimization论文从 2023 年的 256 篇降到 2026 年的 240 篇，热度在回落。
• NeurIPS 是发深度学习 · optimization论文最多的会议，2023–2026 年共 500 篇，占四个会议总量的 52%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 23 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 6；同组增长最快的扩散模型是 4.1 倍，深度学习 · optimization是 0.9 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 2026Achieving Directional-Stationarity from a Single Random Direction Step
• ICML 2026Bottleneck Communication Delay Minimization for Communication-Efficient Decentralized Learning
• ICLR 2026From Sorting Algorithms to Scalable Kernels: Bayesian Optimization in High-Dimensional Permutation Spaces
• CVPR 2026Coverage Optimization for Camera View Selection
• NeurIPS 2025High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
• ICML 2025Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions
• ICLR 2025Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems
• CVPR 2025HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
• NeurIPS 2024$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
• ICML 2024Barrier Algorithms for Constrained Non-Convex Optimization
• ICLR 2024Bayesian Coreset Optimization for Personalized Federated Learning
• CVPR 2024Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization
• NeurIPS 2023$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning
• ICML 2023Buying Information for Stochastic Optimization
• ICLR 2023Alternating Differentiation for Optimization Layers
• CVPR 2023Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization
• NeurIPS 2026Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
• ICML 2026Riemannian Optimization for Fair Spectral Clustering
• ICLR 2026Gradient-Based Diversity Optimization with Differentiable Top-$k$ Objective
• CVPR 2026Its Never Too Late Noise Optimization for Collapse Recovery in

全部深度学习 · optimization论文

共 144 篇，第 2 / 3 页

51. NeurIPS 2023Encoding Human Behavior in Information Design through Deep Learning
52. NeurIPS 2023Enhancing Sharpness-Aware Optimization Through Variance Suppression
53. NeurIPS 2023ExPT: Synthetic Pretraining for Few-Shot Experimental Design
54. NeurIPS 2023Faster Differentially Private Convex Optimization via Second-Order Methods
55. NeurIPS 2023Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case
56. NeurIPS 2023Faster Margin Maximization Rates for Generic Optimization Methods
57. NeurIPS 2023Federated Compositional Deep AUC Maximization
58. NeurIPS 2023Federated Conditional Stochastic Optimization
59. NeurIPS 2023FedL2P: Federated Learning to Personalize
60. NeurIPS 2023FedNAR: Federated Optimization with Normalized Annealing Regularization
61. NeurIPS 2023Finding Local Minima Efficiently in Decentralized Optimization
62. NeurIPS 2023Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization
63. NeurIPS 2023First Order Stochastic Optimization with Oblivious Noise
64. NeurIPS 2023Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs
65. NeurIPS 2023Fractal Landscapes in Policy Optimization
66. NeurIPS 2023Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization
67. NeurIPS 2023Global Identifiability of $\ell_1$-based Dictionary Learning via Matrix Volume Optimization
68. NeurIPS 2023GloptiNets: Scalable Non-Convex Optimization with Certificates
69. NeurIPS 2023Graph of Circuits with GNN for Exploring the Optimal Design Space
70. NeurIPS 2023Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses
71. NeurIPS 2023Hybrid Policy Optimization from Imperfect Demonstrations
72. NeurIPS 2023Hypervolume Maximization: A Geometric View of Pareto Set Learning
73. NeurIPS 2023Importance-aware Co-teaching for Offline Model-based Optimization
74. NeurIPS 2023Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
75. NeurIPS 2023Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
76. NeurIPS 2023Joint Prompt Optimization of Stacked LLMs using Variational Inference
77. NeurIPS 2023Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
78. NeurIPS 2023L2T-DLN: Learning to Teach with Dynamic Loss Network
79. NeurIPS 2023Learning Cuts via Enumeration Oracles
80. NeurIPS 2023Learning the Efficient Frontier
81. NeurIPS 2023Learning to Configure Separators in Branch-and-Cut
82. NeurIPS 2023LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction
83. NeurIPS 2023LogSpecT: Feasible Graph Learning Model from Stationary Signals with Recovery Guarantees
84. NeurIPS 2023Macro Placement by Wire-Mask-Guided Black-Box Optimization
85. NeurIPS 2023Making Scalable Meta Learning Practical
86. NeurIPS 2023Mechanic: A Learning Rate Tuner
87. NeurIPS 2023Memory-Constrained Algorithms for Convex Optimization
88. NeurIPS 2023MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning
89. NeurIPS 2023Momentum Provably Improves Error Feedback!
90. NeurIPS 2023Neural Fields with Hard Constraints of Arbitrary Differential Order
91. NeurIPS 2023Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization
92. NeurIPS 2023Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement
93. NeurIPS 2023Non-Convex Bilevel Optimization with Time-Varying Objective Functions
94. NeurIPS 2023Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization
95. NeurIPS 2023Online Control for Meta-optimization
96. NeurIPS 2023Online Convex Optimization with Unbounded Memory
97. NeurIPS 2023Online Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization
98. NeurIPS 2023Online Learning under Adversarial Nonlinear Constraints
99. NeurIPS 2023Optimization of Inter-group criteria for clustering with minimum size constraints
100. NeurIPS 2023Outlier-Robust Gromov-Wasserstein for Graph Data

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · optimization论文？

共 953 篇，按年份分别是 2023 年 256 篇、2024 年 294 篇、2025 年 163 篇、2026 年 240 篇。

NeurIPS 2026 有多少篇深度学习 · optimization论文？

NeurIPS 2026 有 103 篇深度学习 · optimization论文，上一届是 62 篇。

ICLR 2026 有多少篇深度学习 · optimization论文？

ICLR 2026 有 44 篇深度学习 · optimization论文，上一届是 51 篇。

ICML 2026 有多少篇深度学习 · optimization论文？

ICML 2026 有 86 篇深度学习 · optimization论文，上一届是 44 篇。

CVPR 2026 有多少篇深度学习 · optimization论文？

CVPR 2026 有 7 篇深度学习 · optimization论文，上一届是 6 篇。

哪个会议的深度学习 · optimization论文最多？

NeurIPS，2023–2026 年共 500 篇。