Image de couverture de livre

Approaching Deep Learning through the Spectral Dynamics of Weights

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yunis, David, Patel, Kumar Kshitij, Wheeler, Samuel, Savarese, Pedro, Vardi, Gal, Livescu, Karen, Maire, Michael, Walter, Matthew R.
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

Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations
par: Zhang, Xiao, et autres
Publié: (2023)

Drop-Connect as a Fault-Tolerance Approach for RRAM-based Deep Neural Network Accelerators
par: Xiang, Mingyuan, et autres
Publié: (2024)

Principled Approximation Methods for Efficient and Scalable Deep Learning
par: Savarese, Pedro
Publié: (2025)

Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
par: Yunis, David, et autres
Publié: (2023)

Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
par: Frei, Spencer, et autres
Publié: (2024)

The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks
par: Gronich, Eitan, et autres
Publié: (2026)

Transformers are almost optimal metalearners for linear classification
par: Magen, Roey, et autres
Publié: (2025)

What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness
par: Patel, Kumar Kshitij
Publié: (2025)

Noisy Interpolation Learning with Shallow Univariate ReLU Networks
par: Joshi, Nirmit, et autres
Publié: (2023)

On the Hardness of Learning Regular Expressions
par: Attias, Idan, et autres
Publié: (2025)

Provable Privacy Attacks on Trained Shallow Neural Networks
par: Smorodinsky, Guy, et autres
Publié: (2024)

Implicit Regularization Towards Rank Minimization in ReLU Networks
par: Timor, Nadav, et autres
Publié: (2022)

Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
par: Medvedev, Marko, et autres
Publié: (2024)

Provable Unlearning with Gradient Ascent on Two-Layer ReLU Neural Networks
par: Melamed, Odelia, et autres
Publié: (2025)

Uncertain fate of pelagic calcifying protists: a cellular perspective on a changing ocean.
par: Shemi, Adva, et autres
Publié: (2025)

To Grok Grokking: Provable Grokking in Ridge Regression
par: Xu, Mingyue, et autres
Publié: (2026)

The Limitations of Model Retraining in the Face of Performativity
par: Kabra, Anmol, et autres
Publié: (2024)

SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale
par: Gueuwou, Shester, et autres
Publié: (2024)

Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling
par: Chou, Ju-Chieh, et autres
Publié: (2025)

Geopolitics and Energy Diplomacy in the Caspian Region
par: Gurbanov, Yunis
Publié: (2024)

EVOLUCIÓN O CREACIÓN, GENOMAS Y CLONACIÓN
par: Emilio Yunis
Publié: (2001)

Extending CDCL-based Model Enumeration with Weights
par: Spallitta, Giuseppe, et autres
Publié: (2026)

Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes
par: Harel, Itamar, et autres
Publié: (2025)

Learning to Think from Multiple Thinkers
par: Joshi, Nirmit, et autres
Publié: (2026)

SONIQ: System-Optimized Noise-Injected Ultra-Low-Precision Quantization with Full-Precision Parity
par: Zhou, Cyrus, et autres
Publié: (2023)

Chunk-Distilled Language Modeling
par: Li, Yanhong, et autres
Publié: (2024)

Structured Tree Alignment for Evaluation of (Speech) Constituency Parsing
par: Shi, Freda, et autres
Publié: (2024)

Trajectory-Optimized Time Reparameterization for Learning-Compatible Reduced-Order Modeling of Stiff Dynamical Systems
par: Standridge, Joe, et autres
Publié: (2026)

ImpMIA: Leveraging Implicit Bias for Membership Inference Attack
par: Golbari, Yuval, et autres
Publié: (2025)

Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
par: Tsilivis, Nikolaos, et autres
Publié: (2024)

Presencia de Piscirickettsia salmonis en Truchas de Cultivo (Oncorhynchus mykiss) en Junín, Perú
par: Jefferson Yunis A.
Publié: (2015)

Geno-geographic origin of Y-specific STR haplotypes in a sample of Caucasian-Mestizo and African-descent male individuals from Colombia
par: Juan J. Yunis
Publié: (2013)

Personalized Federated Training of Diffusion Models with Privacy Guarantees
par: Patel, Kumar Kshitij, et autres
Publié: (2025)

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
par: Zhou, Lijia, et autres
Publié: (2023)

Positive Distribution Shift as a Framework for Understanding Tractable Learning
par: Medvedev, Marko, et autres
Publié: (2026)

Sertulum orientale
par: Maire, R
Publié: (1939)

Reconstructing Training Data From Real World Models Trained with Transfer Learning
par: Oz, Yakir, et autres
Publié: (2024)

Tabular and Deep Reinforcement Learning for Gittins Index
par: Dhankhar, Harshit, et autres
Publié: (2024)

AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement
par: Chou, Ju-Chieh, et autres
Publié: (2023)

On the Predictive Power of Representation Dispersion in Language Models
par: Li, Yanhong, et autres
Publié: (2025)