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 70 篇，第 1 / 2 页

1. ICML 2023A Distribution Optimization Framework for Confidence Bounds of Risk Measures
2. ICML 2023A Fully First-Order Method for Stochastic Bilevel Optimization
3. ICML 2023Accelerated Cyclic Coordinate Dual Averaging with Extrapolation for Composite Convex Optimization
4. ICML 2023Accelerated Stochastic Optimization Methods under Quasar-convexity
5. ICML 2023Automatically Auditing Large Language Models via Discrete Optimization
6. ICML 2023Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization
7. ICML 2023Beyond Reward: Offline Preference-guided Policy Optimization
8. ICML 2023Beyond Uniform Lipschitz Condition in Differentially Private Optimization
9. ICML 2023Bilevel Optimization with Coupled Decision-Dependent Distributions
10. ICML 2023Bit Allocation using Optimization
11. ICML 2023Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization
12. ICML 2023Buying Information for Stochastic Optimization
13. ICML 2023Competitive Gradient Optimization
14. ICML 2023Constrained Efficient Global Optimization of Expensive Black-box Functions
15. ICML 2023Continuation Path Learning for Homotopy Optimization
16. ICML 2023Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data
17. ICML 2023Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization
18. ICML 2023DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization
19. ICML 2023Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity
20. ICML 2023Differentially Private Optimization on Large Model at Small Cost
21. ICML 2023Differentially Private Stochastic Convex Optimization under a Quantile Loss Function
22. ICML 2023Diffusion Models for Black-Box Optimization
23. ICML 2023Dynamic Constrained Submodular Optimization with Polylogarithmic Update Time
24. ICML 2023Efficient displacement convex optimization with particle gradient descent
25. ICML 2023Escaping saddle points in zeroth-order optimization: the power of two-point estimators
26. ICML 2023Fast as CHITA: Neural Network Pruning with Combinatorial Optimization
27. ICML 2023Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization
28. ICML 2023Faster Rates of Convergence to Stationary Points in Differentially Private Optimization
29. ICML 2023FedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization
30. ICML 2023FeDXL: Provable Federated Learning for Deep X-Risk Optimization
31. ICML 2023Generalized Polyak Step Size for First Order Optimization with Momentum
32. ICML 2023Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization
33. ICML 2023Generative Pretraining for Black-Box Optimization
34. ICML 2023Global Optimization with Parametric Function Approximation
35. ICML 2023Global Selection of Contrastive Batches via Optimization on Sample Permutations
36. ICML 2023Improving Bi-level Optimization Based Methods with Inspiration from Humans' Classroom Study Techniques
37. ICML 2023Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation
38. ICML 2023Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement
39. ICML 2023Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach
40. ICML 2023Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability
41. ICML 2023Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization
42. ICML 2023Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes
43. ICML 2023Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime
44. ICML 2023Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization
45. ICML 2023Neural Network Accelerated Implicit Filtering: Integrating Neural Network Surrogates With Provably Convergent Derivative Free Optimization Methods
46. ICML 2023Omnipredictors for Constrained Optimization
47. ICML 2023On User-Level Private Convex Optimization
48. ICML 2023Optimal Shrinkage for Distributed Second-Order Optimization
49. ICML 2023Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion
50. ICML 2023Optimization for Amortized Inverse Problems

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。