Gaurav Menghani

activity

20192026

most citedEfficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better

571 citations · 585 across the 12 of their papers we have counts for

collaborators

Showing 2019Show all

2 papers · 1 filter

cs.LG2019★ 5 cited

Learning from a Teacher using Unlabeled Data

Gaurav Menghani, Sujith Ravi

Knowledge distillation is a widely used technique for model compression. We posit that the teacher model used in a distillation setup, captures relationships between classes, that…

cs.DS2019

A Simple Solution to the Level-Ancestor Problem

Gaurav Menghani, Dhruv Matani

A Level Ancestory query LA( $u$ , $d$ ) asks for the the ancestor of the node $u$ at a depth $d$ . We present a simple solution, which pre-processes the tree in $O (n)$ time with $O (n)$ …