Adityanarayanan Radhakrishnan | DeepAI

DeepAI AI Chat

Featured Co-authors

Mikhail Belkin
57 publications
Caroline Uhler
49 publications
Parthe Pandit
16 publications
Chaoyue Liu
12 publications
Eshaan Nichani
9 publications
Libin Zhu
8 publications
Saachi Jain
7 publications
Daniel Beaglehole
5 publications
Neha Prasad
3 publications
Daniel Bernstein
2 publications
George Stefanakis
1 publication

∙ 09/01/2023

Mechanism of feature learning in convolutional neural networks

Understanding the mechanism of how convolutional neural networks learn f...

0 Daniel Beaglehole, et al. ∙

∙ 06/07/2023

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

In this paper, we first present an explanation regarding the common occu...

0 Libin Zhu, et al. ∙

∙ 12/28/2022

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

Neural networks have achieved impressive results on many technological a...

0 Adityanarayanan Radhakrishnan, et al. ∙

∙ 11/01/2022

Transfer Learning with Kernel Methods

Transfer learning refers to the process of adapting a model trained on a...

0 Adityanarayanan Radhakrishnan, et al. ∙

∙ 05/24/2022

Quadratic models for understanding neural network dynamics

In this work, we propose using a quadratic model as a tool for understan...

0 Libin Zhu, et al. ∙

∙ 04/29/2022

Wide and Deep Neural Networks Achieve Optimality for Classification

While neural networks are used for classification tasks across domains, ...

0 Adityanarayanan Radhakrishnan, et al. ∙

∙ 12/30/2021

Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size

Establishing a fast rate of convergence for optimization methods is cruc...

0 Adityanarayanan Radhakrishnan, et al. ∙

∙ 07/31/2021

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

Matrix completion problems arise in many applications including recommen...

15 Adityanarayanan Radhakrishnan, et al. ∙

∙ 06/29/2021

A Mechanism for Producing Aligned Latent Spaces with Autoencoders

Aligned latent spaces, where meaningful semantic shifts in the input spa...

0 Saachi Jain, et al. ∙

∙ 10/19/2020

Do Deeper Convolutional Networks Perform Better?

Over-parameterization is a recent topic of much interest in the machine ...

0 Eshaan Nichani, et al. ∙

∙ 09/18/2020

Linear Convergence and Implicit Regularization of Generalized Mirror Descent with Time-Dependent Mirrors

The following questions are fundamental to understanding the properties ...

8 Adityanarayanan Radhakrishnan, et al. ∙

∙ 03/13/2020

Balancedness and Alignment are Unlikely in Linear Neural Networks

We study the invariance properties of alignment in linear neural network...

0 Adityanarayanan Radhakrishnan, et al. ∙

∙ 09/26/2019

Overparameterized Neural Networks Can Implement Associative Memory

Identifying computational mechanisms for memorization and retrieval is a...

8 Adityanarayanan Radhakrishnan, et al. ∙

∙ 10/16/2018

Downsampling leads to Image Memorization in Convolutional Autoencoders

Memorization of data in deep neural networks has become a subject of sig...

0 Adityanarayanan Radhakrishnan, et al. ∙

∙ 05/23/2017

Patchnet: Interpretable Neural Networks for Image Classification

The ability to visually understand and interpret learned features from c...

0 Adityanarayanan Radhakrishnan, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world