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 13 / 20 页

  1. NeurIPS 2024Learning-Augmented Dynamic Submodular Maximization
  2. NeurIPS 2024LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
  3. NeurIPS 2024Linguistic Collapse: Neural Collapse in (Large) Language Models
  4. NeurIPS 2024LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
  5. NeurIPS 2024Localized Zeroth-Order Prompt Optimization
  6. NeurIPS 2024LoQT: Low-Rank Adapters for Quantized Pretraining
  7. NeurIPS 2024LoRA-GA: Low-Rank Adaptation with Gradient Approximation
  8. NeurIPS 2024Loss Landscape Characterization of Neural Networks without Over-Parametrization
  9. NeurIPS 2024Low Precision Local Training is Enough for Federated Learning
  10. NeurIPS 2024Make Continual Learning Stronger via C-Flat
  11. NeurIPS 2024Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent
  12. NeurIPS 2024Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
  13. NeurIPS 2024Memory-Efficient LLM Training with Online Subspace Descent
  14. NeurIPS 2024MG-Net: Learn to Customize QAOA with Circuit Depth Awareness
  15. NeurIPS 2024MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
  16. NeurIPS 2024Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
  17. NeurIPS 2024MOTE-NAS: Multi-Objective Training-based Estimate for Efficient Neural Architecture Search
  18. NeurIPS 2024Navigating Extremes: Dynamic Sparsity in Large Output Spaces
  19. NeurIPS 2024Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
  20. NeurIPS 2024Neur2BiLO: Neural Bilevel Optimization
  21. NeurIPS 2024Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
  22. NeurIPS 2024Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?
  23. NeurIPS 2024Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms
  24. NeurIPS 2024Non-geodesically-convex optimization in the Wasserstein space
  25. NeurIPS 2024Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
  26. NeurIPS 2024Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
  27. NeurIPS 2024Nuclear Norm Regularization for Deep Learning
  28. NeurIPS 2024Offline Behavior Distillation
  29. NeurIPS 2024On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
  30. NeurIPS 2024On the Inductive Bias of Stacking Towards Improving Reasoning
  31. NeurIPS 2024Optimization-based Causal Estimation from Heterogeneous Environments
  32. NeurIPS 2024Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport
  33. NeurIPS 2024PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization
  34. NeurIPS 2024Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds
  35. NeurIPS 2024Personalized Federated Learning via Feature Distribution Adaptation
  36. NeurIPS 2024PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
  37. NeurIPS 2024Pre-trained Gaussian Processes for Bayesian Optimization
  38. NeurIPS 2024Quantum Algorithms for Non-smooth Non-convex Optimization
  39. NeurIPS 2024Recurrent neural networks: vanishing and exploding gradients are not the end of the story
  40. NeurIPS 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
  41. NeurIPS 2024Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network
  42. NeurIPS 2024ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization
  43. NeurIPS 2024Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization
  44. NeurIPS 2024Resolving Discrepancies in Compute-Optimal Scaling of Language Models
  45. NeurIPS 2024Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
  46. NeurIPS 2024Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation
  47. NeurIPS 2024S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial Optimization
  48. NeurIPS 2024S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
  49. NeurIPS 2024SAMPa: Sharpness-aware Minimization Parallelized
  50. NeurIPS 2024Scalable Kernel Inverse 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