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 8 / 20 页

  1. NeurIPS 2025BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based Optimization
  2. NeurIPS 2025Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization
  3. NeurIPS 2025Continuous Subspace Optimization for Continual Learning
  4. NeurIPS 2025Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions
  5. NeurIPS 2025Convergence Rates of Constrained Expected Improvement
  6. NeurIPS 2025Differentiable extensions with rounding guarantees for combinatorial optimization over permutations
  7. NeurIPS 2025Enhancing Training Data Attribution with Representational Optimization
  8. NeurIPS 2025Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
  9. NeurIPS 2025Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
  10. NeurIPS 2025Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set
  11. NeurIPS 2025Flat Channels to Infinity in Neural Loss Landscapes
  12. NeurIPS 2025FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
  13. NeurIPS 2025Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
  14. NeurIPS 2025HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
  15. NeurIPS 2025High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
  16. NeurIPS 2025KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
  17. NeurIPS 2025Learn2Mix: Training Neural Networks Using Adaptive Data Integration
  18. NeurIPS 2025Learning (Approximately) Equivariant Networks via Constrained Optimization
  19. NeurIPS 2025Learning Theory for Kernel Bilevel Optimization
  20. NeurIPS 2025Leveraging robust optimization for llm alignment under distribution shifts
  21. NeurIPS 2025MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization
  22. NeurIPS 2025Momentum-SAM: Sharpness Aware Minimization without Computational Overhead
  23. NeurIPS 2025Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization
  24. NeurIPS 2025On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
  25. NeurIPS 2025On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
  26. NeurIPS 2025On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
  27. NeurIPS 2025Online Optimization for Offline Safe Reinforcement Learning
  28. NeurIPS 2025Partial Correlation Network Estimation by Semismooth Newton Methods
  29. NeurIPS 2025PDPO: Parametric Density Path Optimization
  30. NeurIPS 2025Preference Optimization by Estimating the Ratio of the Data Distribution
  31. NeurIPS 2025Probing Neural Combinatorial Optimization Models
  32. NeurIPS 2025Problem-Parameter-Free Decentralized Bilevel Optimization
  33. NeurIPS 2025Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO
  34. NeurIPS 2025Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner
  35. NeurIPS 2025Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
  36. NeurIPS 2025Revisiting Frank-Wolfe for Structured Nonconvex Optimization
  37. NeurIPS 2025Robust Hyperbolic Learning with Curvature-Aware Optimization
  38. NeurIPS 2025Scalable inference of functional neural connectivity at submillisecond timescales
  39. NeurIPS 2025Semi-infinite Nonconvex Constrained Min-Max Optimization
  40. NeurIPS 2025Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
  41. NeurIPS 2025Set Smoothness Unlocks Clarke Hyper-stationarity in Bilevel Optimization
  42. NeurIPS 2025Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints
  43. NeurIPS 2025Solver-Free Decision-Focused Learning for Linear Optimization Problems
  44. NeurIPS 2025Stab-SGD: Noise-Adaptivity in Smooth Optimization with Stability Ratios
  45. NeurIPS 2025Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization
  46. NeurIPS 2025System Prompt Optimization with Meta-Learning
  47. NeurIPS 2025TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
  48. NeurIPS 2025Targeted Maximum Likelihood Learning: An Optimization Perspective
  49. NeurIPS 2025The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective
  50. NeurIPS 2025Theoretical Investigation of Adafactor for Non-Convex Smooth 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