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 191 篇，第 1 / 4 页

1. NeurIPS 2024$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
2. NeurIPS 2024$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
3. NeurIPS 20242DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
4. NeurIPS 20244-bit Shampoo for Memory-Efficient Network Training
5. NeurIPS 2024A Bayesian Approach to Data Point Selection
6. NeurIPS 2024A Framework for Bilevel Optimization on Riemannian Manifolds
7. NeurIPS 2024A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
8. NeurIPS 2024A PID Controller Approach for Adaptive Probability-dependent Gradient Decay in Model Calibration
9. NeurIPS 2024A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
10. NeurIPS 2024A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training
11. NeurIPS 2024Accelerating Matroid Optimization through Fast Imprecise Oracles
12. NeurIPS 2024Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization
13. NeurIPS 2024Activation Map Compression through Tensor Decomposition for Deep Learning
14. NeurIPS 2024Adam with model exponential moving average is effective for nonconvex optimization
15. NeurIPS 2024ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
16. NeurIPS 2024Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
17. NeurIPS 2024AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking
18. NeurIPS 2024An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
19. NeurIPS 2024An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization
20. NeurIPS 2024Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training
21. NeurIPS 2024BitDelta: Your Fine-Tune May Only Be Worth One Bit
22. NeurIPS 2024BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
23. NeurIPS 2024BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
24. NeurIPS 2024Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
25. NeurIPS 2024Can Learned Optimization Make Reinforcement Learning Less Difficult?
26. NeurIPS 2024Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
27. NeurIPS 2024Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift
28. NeurIPS 2024Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
29. NeurIPS 2024CoBo: Collaborative Learning via Bilevel Optimization
30. NeurIPS 2024CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
31. NeurIPS 2024Communication-Efficient Federated Group Distributionally Robust Optimization
32. NeurIPS 2024Conformal Inverse Optimization
33. NeurIPS 2024Constrained Diffusion Models via Dual Training
34. NeurIPS 2024Contextual Linear Optimization with Bandit Feedback
35. NeurIPS 2024Continuous Temporal Domain Generalization
36. NeurIPS 2024Controlling Continuous Relaxation for Combinatorial Optimization
37. NeurIPS 2024CRAYM: Neural Field Optimization via Camera RAY Matching
38. NeurIPS 2024DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
39. NeurIPS 2024Decision-Focused Learning with Directional Gradients
40. NeurIPS 2024Deep linear networks for regression are implicitly regularized towards flat minima
41. NeurIPS 2024Derivatives of Stochastic Gradient Descent in parametric optimization
42. NeurIPS 2024Diffeomorphic interpolation for efficient persistence-based topological optimization
43. NeurIPS 2024DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
44. NeurIPS 2024Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
45. NeurIPS 2024Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks
46. NeurIPS 2024EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
47. NeurIPS 2024Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
48. NeurIPS 2024Efficient Combinatorial Optimization via Heat Diffusion
49. NeurIPS 2024Efficient Prompt Optimization Through the Lens of Best Arm Identification
50. NeurIPS 2024Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction

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。