Jonathan Frankle

PhD candidate

Jonathan Frankle is a PhD student in MIT’s Department of Electrical Engineering and Computer Science, where he studies empirical deep learning. His current research focus is on the properties of sparse networks that allow them to train effectively as embodied by his “Lottery Ticket Hypothesis” which received a best paper award at ICLR 2019. He also works closely with lawyers, journalists, and policymakers on topics in AI policy and has taught at the Georgetown University Law Center. He earned a BSE and MSE in computer science at Princeton University.

Publications

Media

Top Work

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

Efficient AI

Learning Rate Rewinding for elegant neural network pruning

Learning Rate Rewinding for elegant neural network pruning

Efficient AI

Publications with the MIT-IBM Watson AI Lab

Do Neural Networks Really Need to Be So Big?
Do Neural Networks Really Need to Be So Big?
 
The Lottery Ticket Hypothesis for the Pre-trained BERT Networks
The Lottery Ticket Hypothesis for the Pre-trained BERT Networks
 
Learning Rate Rewinding for elegant neural network pruning
Learning Rate Rewinding for elegant neural network pruning
 
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks