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 294 篇，第 4 / 6 页

  1. NeurIPS 2024Efficient Combinatorial Optimization via Heat Diffusion
  2. NeurIPS 2024Efficient Prompt Optimization Through the Lens of Best Arm Identification
  3. NeurIPS 2024Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
  4. NeurIPS 2024EMR-Merging: Tuning-Free High-Performance Model Merging
  5. NeurIPS 2024ESPACE: Dimensionality Reduction of Activations for Model Compression
  6. NeurIPS 2024Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
  7. NeurIPS 2024Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
  8. NeurIPS 2024Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
  9. NeurIPS 2024Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
  10. NeurIPS 2024Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints
  11. NeurIPS 2024Fetch and Forge: Efficient Dataset Condensation for Object Detection
  12. NeurIPS 2024Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
  13. NeurIPS 2024First-Order Methods for Linearly Constrained Bilevel Optimization
  14. NeurIPS 2024First-Order Minimax Bilevel Optimization
  15. NeurIPS 2024Fully Unconstrained Online Learning
  16. NeurIPS 2024Functionally Constrained Algorithm Solves Convex Simple Bilevel Problem
  17. NeurIPS 2024GACL: Exemplar-Free Generalized Analytic Continual Learning
  18. NeurIPS 2024Generalized Fast Exact Conformalization
  19. NeurIPS 2024Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables
  20. NeurIPS 2024Geometry-aware training of factorized layers in tensor Tucker format
  21. NeurIPS 2024Global Convergence in Training Large-Scale Transformers
  22. NeurIPS 2024Globally Q-linear Gauss-Newton Method for Overparameterized Non-convex Matrix Sensing
  23. NeurIPS 2024GO4Align: Group Optimization for Multi-Task Alignment
  24. NeurIPS 2024Gradient Rewiring for Editable Graph Neural Network Training
  25. NeurIPS 2024Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
  26. NeurIPS 2024Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame
  27. NeurIPS 2024Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
  28. NeurIPS 2024How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks
  29. NeurIPS 2024Implicit Optimization Bias of Next-token Prediction in Linear Models
  30. NeurIPS 2024Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
  31. NeurIPS 2024Improved Regret for Bandit Convex Optimization with Delayed Feedback
  32. NeurIPS 2024Improving Deep Learning Optimization through Constrained Parameter Regularization
  33. NeurIPS 2024Improving Equivariant Model Training via Constraint Relaxation
  34. NeurIPS 2024Improving Generalization and Convergence by Enhancing Implicit Regularization
  35. NeurIPS 2024Improving robustness to corruptions with multiplicative weight perturbations
  36. NeurIPS 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
  37. NeurIPS 2024In-Context Learning with Representations: Contextual Generalization of Trained Transformers
  38. NeurIPS 2024Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
  39. NeurIPS 2024Infinite Limits of Multi-head Transformer Dynamics
  40. NeurIPS 2024Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
  41. NeurIPS 2024Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
  42. NeurIPS 2024Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
  43. NeurIPS 2024Learn more, but bother less: parameter efficient continual learning
  44. NeurIPS 2024Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
  45. NeurIPS 2024Learning Generalized Linear Programming Value Functions
  46. NeurIPS 2024Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way
  47. NeurIPS 2024Learning with Fitzpatrick Losses
  48. NeurIPS 2024Learning-Augmented Dynamic Submodular Maximization
  49. NeurIPS 2024LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
  50. NeurIPS 2024Linguistic Collapse: Neural Collapse in (Large) Language Models

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