Image de couverture de livre

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tu, Zhenfeng, Aranguri, Santiago, Jacot, Arthur
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training
par: Xiao, Frank, et autres
Publié: (2026)

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff
par: Jacot, Arthur
Publié: (2023)

Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
par: Bantzis, Ioannis, et autres
Publié: (2025)

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
par: Jacot, Arthur, et autres
Publié: (2024)

Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
par: Wen, Yuxiao, et autres
Publié: (2024)

Inference-Time Toxicity Mitigation in Protein Language Models
par: Burda, Manuel Fernández, et autres
Publié: (2026)

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning
par: Jacot, Arthur, et autres
Publié: (2024)

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers
par: Shen, Xuan, et autres
Publié: (2024)

Diffmv: A Unified Diffusion Framework for Healthcare Predictions with Random Missing Views and View Laziness
par: Zhao, Chuang, et autres
Publié: (2025)

The Importance of Being Lazy: Scaling Limits of Continual Learning
par: Graldi, Jacopo, et autres
Publié: (2025)

Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data
par: Rokvic, Ljubomir, et autres
Publié: (2025)

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
par: Fu, Qichen, et autres
Publié: (2024)

Fast Sampling for Flows and Diffusions with Lazy and Point Mass Stochastic Interpolants
par: Damsholt, Gabriel, et autres
Publié: (2026)

Laziness, Barren Plateau, and Noise in Machine Learning
par: Liu, Junyu, et autres
Publié: (2022)

Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models
par: Aranguri, Santiago, et autres
Publié: (2024)

Dynamic Graph Condensation
par: Chen, Dong, et autres
Publié: (2025)

ORLA*: Mobile Manipulator-Based Object Rearrangement with Lazy A Star
par: Gao, Kai, et autres
Publié: (2023)

SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
par: Mozaffari, Mohammad, et autres
Publié: (2024)

SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learning
par: Chen, Dong, et autres
Publié: (2024)

Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination
par: Luo, Zhiyao, et autres
Publié: (2024)

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
par: Zhang, Tongcheng, et autres
Publié: (2026)

Dynamic Meta-Learning for Adaptive XGBoost-Neural Ensembles
par: Sedek, Arthur
Publié: (2025)

Linear Transformers Implicitly Discover Unified Numerical Algorithms
par: Lutz, Patrick, et autres
Publié: (2025)

Dynamical Systems Analysis Reveals Functional Regimes in Large Language Models
par: Ugail, Hassan, et autres
Publié: (2026)

Unveiling the Training Dynamics of ReLU Networks through a Linear Lens
par: Ye, Longqing
Publié: (2025)

A Unifying View of Coverage in Linear Off-Policy Evaluation
par: Amortila, Philip, et autres
Publié: (2026)

Neural Network Optimal Power Flow via Energy Gradient Flow and Unified Dynamics
par: Liu, Xuezhi
Publié: (2025)

Graph Mixing Additive Networks
par: Bechler-Speicher, Maya, et autres
Publié: (2025)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
par: Chou, Yuhong, et autres
Publié: (2024)

Scalable Production Scheduling: Linear Complexity via Unified Homogeneous Graphs
par: Hoss, Jonathan, et autres
Publié: (2026)

Fast and Interpretable Mixed-Integer Linear Program Solving by Learning Model Reduction
par: Li, Yixuan, et autres
Publié: (2024)

UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining
par: Wang, Changhao, et autres
Publié: (2026)

An Active Diffusion Neural Network for Graphs
par: Jiang, Mengying
Publié: (2025)

DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime
par: Luo, Zhiyao, et autres
Publié: (2024)

RegimeNAS: Regime-Aware Differentiable Architecture Search With Theoretical Guarantees for Financial Trading
par: Devadiga, Prathamesh, et autres
Publié: (2025)

Three Quantization Regimes for ReLU Networks
par: Ou, Weigutian, et autres
Publié: (2024)

Adversarial Graph Disentanglement
par: Zheng, Shuai, et autres
Publié: (2021)

Novel Kernel Models and Exact Representor Theory for Neural Networks Beyond the Over-Parameterized Regime
par: Shilton, Alistair, et autres
Publié: (2024)

Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method
par: Jacot, Arthur
Publié: (2026)

Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets
par: Jacot, Arthur
Publié: (2025)