Nikhil Ghosh | DeepAI

DeepAI AI Chat

Featured Co-authors

Xin Wang
382 publications
Yuxin Chen
101 publications
Yisong Yue
96 publications
Bin Yu
67 publications
Mikhail Belkin
57 publications
Saurabh Garg
39 publications
Song Mei
33 publications
Preetum Nakkiran
27 publications
Boaz Barak
20 publications
Rina Panigrahy
15 publications
Nishanth Dikkala
14 publications

∙ 08/06/2023

The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning

In this work, we investigate the dynamics of stochastic gradient descent...

0 Nikhil Ghosh, et al. ∙

∙ 01/31/2023

The Power of External Memory in Increasing Predictive Model Capacity

One way of introducing sparsity into deep networks is by attaching an ex...

0 Cenk Baykal, et al. ∙

∙ 01/30/2023

Alternating Updates for Efficient Transformers

It is well established that increasing scale in deep transformer network...

0 Cenk Baykal, et al. ∙

∙ 07/23/2022

A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors

In this work we establish an algorithm and distribution independent non-...

0 Nikhil Ghosh, et al. ∙

∙ 02/20/2022

Deconstructing Distributions: A Pointwise Framework of Learning

In machine learning, we traditionally evaluate the performance of a sing...

0 Gal Kaplun, et al. ∙

∙ 11/13/2021

The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods

To understand how deep learning works, it is crucial to understand the t...

22 Nikhil Ghosh, et al. ∙

∙ 10/27/2019

Landmark Ordinal Embedding

In this paper, we aim to learn a low-dimensional Euclidean representatio...

19 Nikhil Ghosh, et al. ∙

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