深度学习 · optimization论文趋势 2023–2026

ICML/NeurIPS 深度学习方向：optimization

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 953 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

深度学习 · optimization论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202314434708256
202419130721294
20256251446163
202610344867240

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

全部深度学习 · optimization论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 953 篇，第 14 / 20 页

  1. NeurIPS 2024Scalable Optimization in the Modular Norm
  2. NeurIPS 2024ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
  3. NeurIPS 2024Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations
  4. NeurIPS 2024Semidefinite Relaxations of the Gromov-Wasserstein Distance
  5. NeurIPS 2024SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
  6. NeurIPS 2024SGD vs GD: Rank Deficiency in Linear Networks
  7. NeurIPS 2024Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization
  8. NeurIPS 2024Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
  9. NeurIPS 2024Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization
  10. NeurIPS 2024SIRIUS : Contexual Sparisty with Correction for Efficient LLMs
  11. NeurIPS 2024Sketching for Distributed Deep Learning: A Sharper Analysis
  12. NeurIPS 2024SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
  13. NeurIPS 2024SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
  14. NeurIPS 2024Sparse maximal update parameterization: A holistic approach to sparse training dynamics
  15. NeurIPS 2024Stabilized Proximal-Point Methods for Federated Optimization
  16. NeurIPS 2024Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
  17. NeurIPS 2024Stepping Forward on the Last Mile
  18. NeurIPS 2024Stepping on the Edge: Curvature Aware Learning Rate Tuners
  19. NeurIPS 2024Stochastic Newton Proximal Extragradient Method
  20. NeurIPS 2024Super Consistency of Neural Network Landscapes and Learning Rate Transfer
  21. NeurIPS 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains
  22. NeurIPS 2024The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
  23. NeurIPS 2024The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
  24. NeurIPS 2024The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
  25. NeurIPS 2024The Implicit Bias of Adam on Separable Data
  26. NeurIPS 2024The Prevalence of Neural Collapse in Neural Multivariate Regression
  27. NeurIPS 2024The Road Less Scheduled
  28. NeurIPS 2024Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
  29. NeurIPS 2024There is No Silver Bullet: Benchmarking Methods in Predictive Combinatorial Optimization
  30. NeurIPS 2024Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
  31. NeurIPS 2024This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
  32. NeurIPS 2024Topological obstruction to the training of shallow ReLU neural networks
  33. NeurIPS 2024TorchOpt: An Efficient Library for Differentiable Optimization
  34. NeurIPS 2024Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
  35. NeurIPS 2024Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
  36. NeurIPS 2024TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
  37. NeurIPS 2024Universal Neural Functionals
  38. NeurIPS 2024Unraveling the Gradient Descent Dynamics of Transformers
  39. NeurIPS 2024Unveiling LoRA Intrinsic Ranks via Salience Analysis
  40. NeurIPS 2024UQ-Guided Hyperparameter Optimization for Iterative Learners
  41. NeurIPS 2024VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
  42. NeurIPS 2024Warm-starting Push-Relabel
  43. NeurIPS 2024Weight decay induces low-rank attention layers
  44. NeurIPS 2024Where Do Large Learning Rates Lead Us?
  45. NeurIPS 2024Why Do We Need Weight Decay in Modern Deep Learning?
  46. NeurIPS 2024Why Transformers Need Adam: A Hessian Perspective
  47. NeurIPS 2024Why Warmup the Learning Rate? Underlying Mechanisms and Improvements
  48. CVPR 2023Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization
  49. CVPR 2023Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision
  50. CVPR 2023Elastic Aggregation for Federated Optimization

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查深度学习 · optimization在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "dl-optimization"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「深度学习」下的其他主题