深度学习 · optimization论文趋势 2023–2026

主要结论

• 深度学习 · optimization论文从 2023 年的 256 篇降到 2026 年的 240 篇，热度在回落。
• NeurIPS 是发深度学习 · optimization论文最多的会议，2023–2026 年共 500 篇，占四个会议总量的 52%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 23 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 6；同组增长最快的扩散模型是 4.1 倍，深度学习 · optimization是 0.9 倍。

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

• NeurIPS 2026Achieving Directional-Stationarity from a Single Random Direction Step
• ICML 2026Bottleneck Communication Delay Minimization for Communication-Efficient Decentralized Learning
• ICLR 2026From Sorting Algorithms to Scalable Kernels: Bayesian Optimization in High-Dimensional Permutation Spaces
• CVPR 2026Coverage Optimization for Camera View Selection
• NeurIPS 2025High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
• ICML 2025Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions
• ICLR 2025Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems
• CVPR 2025HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
• NeurIPS 2024$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
• ICML 2024Barrier Algorithms for Constrained Non-Convex Optimization
• ICLR 2024Bayesian Coreset Optimization for Personalized Federated Learning
• CVPR 2024Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization
• NeurIPS 2023$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning
• ICML 2023Buying Information for Stochastic Optimization
• ICLR 2023Alternating Differentiation for Optimization Layers
• CVPR 2023Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization
• NeurIPS 2026Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
• ICML 2026Riemannian Optimization for Fair Spectral Clustering
• ICLR 2026Gradient-Based Diversity Optimization with Differentiable Top-$k$ Objective
• CVPR 2026Its Never Too Late Noise Optimization for Collapse Recovery in

全部深度学习 · optimization论文

共 953 篇，第 12 / 20 页

551. NeurIPS 2024Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks
552. NeurIPS 2024EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
553. NeurIPS 2024Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
554. NeurIPS 2024Efficient Combinatorial Optimization via Heat Diffusion
555. NeurIPS 2024Efficient Prompt Optimization Through the Lens of Best Arm Identification
556. NeurIPS 2024Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
557. NeurIPS 2024EMR-Merging: Tuning-Free High-Performance Model Merging
558. NeurIPS 2024ESPACE: Dimensionality Reduction of Activations for Model Compression
559. NeurIPS 2024Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
560. NeurIPS 2024Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
561. NeurIPS 2024Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
562. NeurIPS 2024Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
563. NeurIPS 2024Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints
564. NeurIPS 2024Fetch and Forge: Efficient Dataset Condensation for Object Detection
565. NeurIPS 2024Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
566. NeurIPS 2024First-Order Methods for Linearly Constrained Bilevel Optimization
567. NeurIPS 2024First-Order Minimax Bilevel Optimization
568. NeurIPS 2024Fully Unconstrained Online Learning
569. NeurIPS 2024Functionally Constrained Algorithm Solves Convex Simple Bilevel Problem
570. NeurIPS 2024GACL: Exemplar-Free Generalized Analytic Continual Learning
571. NeurIPS 2024Generalized Fast Exact Conformalization
572. NeurIPS 2024Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables
573. NeurIPS 2024Geometry-aware training of factorized layers in tensor Tucker format
574. NeurIPS 2024Global Convergence in Training Large-Scale Transformers
575. NeurIPS 2024Globally Q-linear Gauss-Newton Method for Overparameterized Non-convex Matrix Sensing
576. NeurIPS 2024GO4Align: Group Optimization for Multi-Task Alignment
577. NeurIPS 2024Gradient Rewiring for Editable Graph Neural Network Training
578. NeurIPS 2024Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
579. NeurIPS 2024Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame
580. NeurIPS 2024Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
581. NeurIPS 2024How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks
582. NeurIPS 2024Implicit Optimization Bias of Next-token Prediction in Linear Models
583. NeurIPS 2024Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
584. NeurIPS 2024Improved Regret for Bandit Convex Optimization with Delayed Feedback
585. NeurIPS 2024Improving Deep Learning Optimization through Constrained Parameter Regularization
586. NeurIPS 2024Improving Equivariant Model Training via Constraint Relaxation
587. NeurIPS 2024Improving Generalization and Convergence by Enhancing Implicit Regularization
588. NeurIPS 2024Improving robustness to corruptions with multiplicative weight perturbations
589. NeurIPS 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
590. NeurIPS 2024In-Context Learning with Representations: Contextual Generalization of Trained Transformers
591. NeurIPS 2024Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
592. NeurIPS 2024Infinite Limits of Multi-head Transformer Dynamics
593. NeurIPS 2024Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
594. NeurIPS 2024Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
595. NeurIPS 2024Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
596. NeurIPS 2024Learn more, but bother less: parameter efficient continual learning
597. NeurIPS 2024Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
598. NeurIPS 2024Learning Generalized Linear Programming Value Functions
599. NeurIPS 2024Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way
600. NeurIPS 2024Learning with Fitzpatrick Losses

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。