Picture for Adityanarayanan Radhakrishnan

Adityanarayanan Radhakrishnan

Linear Recursive Feature Machines provably recover low-rank matrices

Add code
Jan 09, 2024
Viaarxiv icon

Mechanism of feature learning in convolutional neural networks

Add code
Sep 01, 2023
Figure 1 for Mechanism of feature learning in convolutional neural networks
Figure 2 for Mechanism of feature learning in convolutional neural networks
Figure 3 for Mechanism of feature learning in convolutional neural networks
Figure 4 for Mechanism of feature learning in convolutional neural networks
Viaarxiv icon

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning

Add code
Jun 07, 2023
Figure 1 for Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
Figure 2 for Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
Figure 3 for Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
Figure 4 for Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
Viaarxiv icon

Feature learning in neural networks and kernel machines that recursively learn features

Add code
Dec 28, 2022
Figure 1 for Feature learning in neural networks and kernel machines that recursively learn features
Figure 2 for Feature learning in neural networks and kernel machines that recursively learn features
Figure 3 for Feature learning in neural networks and kernel machines that recursively learn features
Figure 4 for Feature learning in neural networks and kernel machines that recursively learn features
Viaarxiv icon

Transfer Learning with Kernel Methods

Add code
Nov 01, 2022
Figure 1 for Transfer Learning with Kernel Methods
Figure 2 for Transfer Learning with Kernel Methods
Figure 3 for Transfer Learning with Kernel Methods
Figure 4 for Transfer Learning with Kernel Methods
Viaarxiv icon

Quadratic models for understanding neural network dynamics

Add code
May 24, 2022
Figure 1 for Quadratic models for understanding neural network dynamics
Figure 2 for Quadratic models for understanding neural network dynamics
Figure 3 for Quadratic models for understanding neural network dynamics
Figure 4 for Quadratic models for understanding neural network dynamics
Viaarxiv icon

Wide and Deep Neural Networks Achieve Optimality for Classification

Add code
Apr 29, 2022
Figure 1 for Wide and Deep Neural Networks Achieve Optimality for Classification
Figure 2 for Wide and Deep Neural Networks Achieve Optimality for Classification
Figure 3 for Wide and Deep Neural Networks Achieve Optimality for Classification
Viaarxiv icon

Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size

Add code
Dec 30, 2021
Figure 1 for Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size
Figure 2 for Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size
Viaarxiv icon

Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks

Add code
Jul 31, 2021
Figure 1 for Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks
Figure 2 for Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks
Figure 3 for Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks
Figure 4 for Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks
Viaarxiv icon

A Mechanism for Producing Aligned Latent Spaces with Autoencoders

Add code
Jun 29, 2021
Figure 1 for A Mechanism for Producing Aligned Latent Spaces with Autoencoders
Figure 2 for A Mechanism for Producing Aligned Latent Spaces with Autoencoders
Figure 3 for A Mechanism for Producing Aligned Latent Spaces with Autoencoders
Figure 4 for A Mechanism for Producing Aligned Latent Spaces with Autoencoders
Viaarxiv icon