Search Results for author: Chas Leichner

Found 2 papers, 1 papers with code

Data-Free Neural Architecture Search via Recursive Label Calibration

no code implementations • 3 Dec 2021 • Zechun Liu, Zhiqiang Shen, Yun Long, Eric Xing, Kwang-Ting Cheng, Chas Leichner

Then we use the synthesized data and their predicted soft-labels to guide neural architecture search.

Paper
Add Code

Pareto-Optimal Quantized ResNet Is Mostly 4-bit

1 code implementation • 7 May 2021 • Amirali Abdolrashidi, Lisa Wang, Shivani Agrawal, Jonathan Malmaud, Oleg Rybakov, Chas Leichner, Lukasz Lew

In this work, we use ResNet as a case study to systematically investigate the effects of quantization on inference compute cost-quality tradeoff curves.

Quantization

23,465

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.