I will be joining the NYU faculty in Fall 2020 and am looking for PhD students!

Brandon Reagen

I am a computer architect interested in hardware acceleration 

for deep learning and privacy-preserving machine learning.

Recent activity


Weightless presented at ICML 2018

Weightless is a novel scheme for lossy weight encoding. The encoding is based on the Bloomier filter, a probabilistic data structure that can save space at the expense of introducing random errors. Leveraging the ability of neural networks to tolerate these imperfections and by re-training around the errors, Weightless compresses weights by up to 496× without loss of model accuracy. This results in up to a 1.51× improvement over the state-of-the-art.


Ares published at DAC 2018! Nominated for Best Paper

Ares is an algorithmic fault injection framework to facilitate an academic understanding of fault tolerance in deep learning models. Ares enable fault tolerance studies across models, structures, and different datatypes. The code is available here.


Successful PhD defense and am joining Facebook as a research scientist!

It has been an amazing 6 years. I've been fortunate enough to have worked with two amazing advisors and collaborated on building simulators, benchmarks, chip design, machine learning, and robotics! I'm excited to start the next phase of my career working with the AI Infrastructure Research team and Kim Hazelwood at Facebook in July!