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 44 篇，第 1 / 1 页

1. ICML 2025A Bregman Proximal Viewpoint on Neural Operators
2. ICML 2025A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models
3. ICML 2025A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization
4. ICML 2025Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators
5. ICML 2025Attention-Only Transformers via Unrolled Subspace Denoising
6. ICML 2025BackSlash: Rate Constrained Optimized Training of Large Language Models
7. ICML 2025Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
8. ICML 2025BSO: Binary Spiking Online Optimization Algorithm
9. ICML 2025Decoupled SGDA for Games with Intermittent Strategy Communication
10. ICML 2025DTZO: Distributed Trilevel Zeroth Order Learning with Provable Non-Asymptotic Convergence
11. ICML 2025Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method
12. ICML 2025Enabling Optimal Decisions in Rehearsal Learning under CARE Condition
13. ICML 2025Enhancing Parallelism in Decentralized Stochastic Convex Optimization
14. ICML 2025Ensemble Learned Bloom Filters: Two Oracles are Better than One
15. ICML 2025Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization
16. ICML 2025Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions
17. ICML 2025FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
18. ICML 2025Generalized additive models via direct optimization of regularized decision stump forests
19. ICML 2025Generalized Smooth Bilevel Optimization with Nonconvex Lower-Level
20. ICML 2025Global curvature for second-order optimization of neural networks
21. ICML 2025Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
22. ICML 2025Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems
23. ICML 2025Inverse Optimization via Learning Feasible Regions
24. ICML 2025Joker: Joint Optimization Framework for Lightweight Kernel Machines
25. ICML 2025Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms
26. ICML 2025Meta-Black-Box-Optimization through Offline Q-function Learning
27. ICML 2025Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization
28. ICML 2025Neural Solver Selection for Combinatorial Optimization
29. ICML 2025Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
30. ICML 2025Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization
31. ICML 2025Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
32. ICML 2025PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
33. ICML 2025Probabilistic Group Mask Guided Discrete Optimization for Incremental Learning
34. ICML 2025Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent
35. ICML 2025Radio: Rate–Distortion Optimization for Large Language Model Compression
36. ICML 2025Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
37. ICML 2025Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
38. ICML 2025Scalable Meta-Learning via Mixed-Mode Differentiation
39. ICML 2025SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
40. ICML 2025Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
41. ICML 2025Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints
42. ICML 2025Subspace Optimization for Large Language Models with Convergence Guarantees
43. ICML 2025The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
44. ICML 2025TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization

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。