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 86 篇，第 2 / 2 页

51. ICML 2026Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems
52. ICML 2026On the Convergence of Decentralized Stochastic Minimax Optimization Algorithm with Compressed Communication
53. ICML 2026On the Optimization Trajectory of DeepWalk Embeddings
54. ICML 2026On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
55. ICML 2026Optimal Transport with Symmetry Groups
56. ICML 2026PASO: Step Parallel Stochastic Optimization
57. ICML 2026PepCompass: Navigating Peptide Embedding Spaces Using Riemannian Geometry
58. ICML 2026Projection-Free Algorithms for Minimax Problems
59. ICML 2026pTNAS: Progressive Neural Architecture Search for Tabular Data
60. ICML 2026Reducing Per-Sample Harm in Stochastic Optimization
61. ICML 2026Reflect-then-Correct: Rebalancing Task Optimization for Generalizable Meta-Reinforcement Learning via Distributional Value Error Reduction
62. ICML 2026Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models
63. ICML 2026Riemannian Dueling Optimization
64. ICML 2026Riemannian Optimization for Fair Spectral Clustering
65. ICML 2026Riemannian stochastic optimization for sufficient dimension reduction
66. ICML 2026RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
67. ICML 2026Robust Contextual Optimization with Missing Covariates
68. ICML 2026Robust Learning via Nested Distributionally Robust Optimization
69. ICML 2026Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
70. ICML 2026Second-Order Bilevel Optimization with Accelerated Convergence Rates
71. ICML 2026Sharpness-Aware Minimization Can Hallucinate Minimizers
72. ICML 2026SimpleGPT: Improving GPT via A Simple Normalization Strategy
73. ICML 2026Simultaneous Confidence Bounds for Aggregated Effects via Exact Subset Optimization
74. ICML 2026SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
75. ICML 2026Solving Stochastic Variational Inequalities without the Bounded Variance Assumption
76. ICML 2026Step-Size Stability in Stochastic Optimization: A Theoretical Perspective
77. ICML 2026Stochastic Gradient Methods under Heavy-Tailed Noises in Weakly Convex Optimization
78. ICML 2026Submodular Optimization for Minimal Augmentation in Robust Language Model Alignment
79. ICML 2026SVRG and Beyond via Posterior Correction
80. ICML 2026TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
81. ICML 2026TSP with Predictions: Heatmap to Tour with Provable Guarantees
82. ICML 2026Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
83. ICML 2026Variable Clustering via Distributionally Robust Nodewise Regression
84. ICML 2026Weight Decay Improves Language Model Plasticity
85. ICML 2026Why Do We Need Warm-up? A Theoretical Perspective
86. ICML 2026Zeroth-Order Optimization at the Edge of Stability

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。