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 5 / 20 页

  1. NeurIPS 2026Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
  2. NeurIPS 2026Orthogonal Updates for the Win: Towards Accelerated Adaptive Minimax Optimization
  3. NeurIPS 2026PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial Optimization
  4. NeurIPS 2026Pairwise AUC Optimization Needs Corrective Power: A Unified View
  5. NeurIPS 2026ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization
  6. NeurIPS 2026Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
  7. NeurIPS 2026POME: Post Optimization Model Edit via Muon-Style Projection
  8. NeurIPS 2026Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise
  9. NeurIPS 2026Randomized Kriging Believer For Parallel Bayesian Optimization With Regret Bounds
  10. NeurIPS 2026Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization
  11. NeurIPS 2026Regularization Paths for Continuous DAG Learning
  12. NeurIPS 2026Regularized Large Neighborhood Search
  13. NeurIPS 2026Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
  14. NeurIPS 2026Rethinking Language Model Scaling under Transferable Hypersphere Optimization
  15. NeurIPS 2026Revisiting Decentralized Online Convex Optimization with Compressed Communication
  16. NeurIPS 2026Riemannian Bilevel Optimization under the Polyak–Łojasiewicz Condition
  17. NeurIPS 2026Riemannian Lyapunov Framework: Optimization as Closed-Loop Control on Riemannian Manifolds
  18. NeurIPS 2026Robust Latent Space Bayesian Optimization with Marginalized Kernel
  19. NeurIPS 2026Route-Consistent Adaptation for Stable Quantization of Mixture-of-Experts Models with Theoretical Guarantees
  20. NeurIPS 2026Sample complexity of stochastic optimization with integer variables
  21. NeurIPS 2026SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
  22. NeurIPS 2026Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets
  23. NeurIPS 2026Sharper Guarantees for Misspecified Kernelized Bandit Optimization
  24. NeurIPS 2026Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise
  25. NeurIPS 2026Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates
  26. NeurIPS 2026Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks
  27. NeurIPS 2026Spectral Annealing: Normalization-Path Exploration for Large-Scale Ising Optimization
  28. NeurIPS 2026Stochastic Approximation Approach for Decentralized Optimization on Time Varying Random Networks
  29. NeurIPS 2026Stochastic Dynamic Barrier Perturbed Gradient Methods for Nonconvex Simple Bilevel Optimization
  30. NeurIPS 2026Stochastic Reconfiguration as Statistical Filtering for Overparameterized Neural Quantum States
  31. NeurIPS 2026Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise
  32. NeurIPS 2026Structure vs. Chaos: Asymmetric Entropic Optimization for Enforcing Instruction Hierarchy
  33. NeurIPS 2026Taming the Tails: Why Distributionally Robust Optimization Needs New Theory for Imbalanced Regression
  34. NeurIPS 2026The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning
  35. NeurIPS 2026The Optimization Prior: Instilling depth for shallow networks, detail for coarse networks
  36. NeurIPS 2026Towards Hyperparameter Transfer for Differentially Private Optimization
  37. NeurIPS 2026Towards Settling the Complexity of Non-Euclidean Parallel Convex Optimization
  38. NeurIPS 2026Truncated Riemannian (1+1)-ES for Black-Box Optimization with Intrinsic Dimension Guarantees
  39. NeurIPS 2026Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-Training
  40. NeurIPS 2026Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel Optimization
  41. CVPR 2025Balanced Rate-Distortion Optimization in Learned Image Compression
  42. CVPR 2025CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation
  43. CVPR 2025HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
  44. CVPR 2025Instance-wise Supervision-level Optimization in Active Learning
  45. CVPR 2025Locally Orderless Images for Optimization in Differentiable Rendering
  46. CVPR 2025PIDLoc: Cross-View Pose Optimization Network Inspired by PID Controllers
  47. ICLR 2025A Coefficient Makes SVRG Effective
  48. ICLR 2025A Stochastic Approach to the Subset Selection Problem via Mirror Descent
  49. ICLR 2025A Tight Convergence Analysis of Inexact Stochastic Proximal Point Algorithm for Stochastic Composite Optimization Problems
  50. ICLR 2025A Truncated Newton Method for Optimal Transport

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