理论 · optimization论文趋势 2023–2026

学习理论及相关：optimization

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,871 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

理论 · optimization论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20233746355123
2024304123670494
20253181961479670
20261192442147584

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

全部理论 · optimization论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,871 篇，第 20 / 38 页

  1. NeurIPS 2025A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
  2. NeurIPS 2025A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
  3. NeurIPS 2025A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond
  4. NeurIPS 2025A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
  5. NeurIPS 2025Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization
  6. NeurIPS 2025Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion
  7. NeurIPS 2025Accelerating Model-Free Optimization via Averaging of Cost Samples
  8. NeurIPS 2025Accelerating Optimization via Differentiable Stopping Time
  9. NeurIPS 2025Acceleration via silver step-size on Riemannian manifolds with applications to Wasserstein space
  10. NeurIPS 2025Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
  11. NeurIPS 2025Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization
  12. NeurIPS 2025Adaptive Frontier Exploration on Graphs with Applications to Network-Based Disease Testing
  13. NeurIPS 2025Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing
  14. NeurIPS 2025Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance
  15. NeurIPS 2025Agnostic Active Learning Is Always Better Than Passive Learning
  16. NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
  17. NeurIPS 2025An Adaptive Algorithm for Bilevel Optimization on Riemannian Manifolds
  18. NeurIPS 2025An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
  19. NeurIPS 2025An Ellipsoid Algorithm for Online Convex Optimization
  20. NeurIPS 2025Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
  21. NeurIPS 2025Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses
  22. NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
  23. NeurIPS 2025ASGO: Adaptive Structured Gradient Optimization
  24. NeurIPS 2025Attention-based clustering
  25. NeurIPS 2025Autoencoding Random Forests
  26. NeurIPS 2025Balancing Gradient and Hessian Queries in Non-Convex Optimization
  27. NeurIPS 2025Bayesian Optimization with Preference Exploration using a Monotonic Neural Network Ensemble
  28. NeurIPS 2025Benign Overfitting in Single-Head Attention
  29. NeurIPS 2025Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
  30. NeurIPS 2025Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation
  31. NeurIPS 2025Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions
  32. NeurIPS 2025Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond
  33. NeurIPS 2025Block Coordinate Descent for Neural Networks Provably Finds Global Minima
  34. NeurIPS 2025Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-Transport
  35. NeurIPS 2025Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks
  36. NeurIPS 2025CAMO: Convergence-Aware Multi-Fidelity Bayesian Optimization
  37. NeurIPS 2025Can Diffusion Models Disentangle? A Theoretical Perspective
  38. NeurIPS 2025CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization
  39. NeurIPS 2025Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms
  40. NeurIPS 2025Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization
  41. NeurIPS 2025Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees
  42. NeurIPS 2025Constrained Linear Thompson Sampling
  43. NeurIPS 2025Constrained Optimization From a Control Perspective via Feedback Linearization
  44. NeurIPS 2025Contextual Dynamic Pricing with Heterogeneous Buyers
  45. NeurIPS 2025Continuous Subspace Optimization for Continual Learning
  46. NeurIPS 2025Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
  47. NeurIPS 2025Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
  48. NeurIPS 2025Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions
  49. NeurIPS 2025Convergence of the Gradient Flow for Shallow ReLU Networks on Weakly Interacting Data
  50. NeurIPS 2025Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares

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 查理论 · 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": "theory-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理论 · optimization论文？
共 1,871 篇，按年份分别是 2023 年 123 篇、2024 年 494 篇、2025 年 670 篇、2026 年 584 篇。
NeurIPS 2026 有多少篇理论 · optimization论文？
NeurIPS 2026 有 119 篇理论 · optimization论文，上一届是 318 篇。
ICLR 2026 有多少篇理论 · optimization论文？
ICLR 2026 有 244 篇理论 · optimization论文，上一届是 196 篇。
ICML 2026 有多少篇理论 · optimization论文？
ICML 2026 有 214 篇理论 · optimization论文，上一届是 147 篇。
CVPR 2026 有多少篇理论 · optimization论文？
CVPR 2026 有 7 篇理论 · optimization论文，上一届是 9 篇。
哪个会议的理论 · optimization论文最多？
NeurIPS，2023–2026 年共 778 篇。

「理论与统计」下的其他主题