Maithra Raghu

is this you? claim profile

∙

0 followers

∙

Google

∙

MIT

Featured Co-authors

Quoc V. Le
101 publications
Oriol Vinyals
97 publications
Jon Kleinberg
68 publications
Jascha Sohl-Dickstein
63 publications
Ian Goodfellow
50 publications
Samy Bengio
50 publications
Jacob Andreas
48 publications
Surya Ganguli
47 publications
David Duvenaud
47 publications
Alexey Dosovitskiy
40 publications
Emmanuel Abbe
31 publications

∙ 05/26/2022

Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures

This paper considers the Pointer Value Retrieval (PVR) benchmark introdu...

Emmanuel Abbe, et al. ∙

∙ 02/15/2022

On the Origins of the Block Structure Phenomenon in Neural Network Representations

Recent work has uncovered a striking phenomenon in large-capacity neural...

Thao Nguyen, et al. ∙

∙ 08/19/2021

Do Vision Transformers See Like Convolutional Neural Networks?

Convolutional neural networks (CNNs) have so far been the de-facto model...

Maithra Raghu, et al. ∙

∙ 07/27/2021

Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization

The successes of deep learning critically rely on the ability of neural ...

Chiyuan Zhang, et al. ∙

∙ 11/05/2020

Teaching with Commentaries

Effective training of deep neural networks can be challenging, and there...

Aniruddh Raghu, et al. ∙

∙ 10/29/2020

Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth

A key factor in the success of deep neural networks is the ability to sc...

Thao Nguyen, et al. ∙

∙ 07/14/2020

Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics

A central challenge in developing versatile machine learning systems is ...

Vinay V. Ramasesh, et al. ∙

∙ 03/26/2020

A Survey of Deep Learning for Scientific Discovery

Over the past few years, we have seen fundamental breakthroughs in core ...

Maithra Raghu, et al. ∙

∙ 09/19/2019

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

An important research direction in machine learning has centered around ...

Aniruddh Raghu, et al. ∙

∙ 03/28/2019

The Algorithmic Automation Problem: Prediction, Triage, and Human Effort

In a wide array of areas, algorithms are matching and surpassing the per...

Maithra Raghu, et al. ∙

∙ 02/14/2019

Transfusion: Understanding Transfer Learning with Applications to Medical Imaging

With the increasingly varied applications of deep learning, transfer lea...

Maithra Raghu, et al. ∙

∙ 07/04/2018

Direct Uncertainty Prediction with Applications to Healthcare

Large labeled datasets for supervised learning are frequently constructe...

Maithra Raghu, et al. ∙

∙ 06/14/2018

Insights on representational similarity in neural networks with canonical correlation

Comparing different neural network representations and determining how r...

Ari S. Morcos, et al. ∙

∙ 01/09/2018

Adversarial Spheres

State of the art computer vision models have been shown to be vulnerable...

Justin Gilmer, et al. ∙

∙ 11/07/2017

Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?

Deep reinforcement learning has achieved many recent successes, but our ...

Maithra Raghu, et al. ∙

∙ 06/19/2017

SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

We propose a new technique, Singular Vector Canonical Correlation Analys...

Maithra Raghu, et al. ∙

∙ 04/05/2017

Linear Additive Markov Processes

We introduce LAMP: the Linear Additive Markov Process. Transitions in LA...

Ravi Kumar, et al. ∙

∙ 11/24/2016

Survey of Expressivity in Deep Neural Networks

We survey results on neural network expressivity described in "On the Ex...

Maithra Raghu, et al. ∙

∙ 06/16/2016

Exponential expressivity in deep neural networks through transient chaos

We combine Riemannian geometry with the mean field theory of high dimens...

Ben Poole, et al. ∙

∙ 06/16/2016

On the Expressive Power of Deep Neural Networks

We propose a new approach to the problem of neural network expressivity,...

Maithra Raghu, et al. ∙