I am a postdoctoral researcher at Facebook AI Research in Menlo Park. I joined Facebook in 2018 after earning my PhD in physics from Yale University under the supervision of Paul Tipton. During my graduate studies, I worked on the design, development and deployment of deep learning algorithms for the ATLAS experiment at CERN, with a focus on computer vision and generative modeling. While in my PhD, I was an affiliate at Lawrence Berkeley National Lab, where I collaborated with the NERSC DAS team. Prior to that, in 2013, I graduated from the University of California, Berkeley with degrees in physics and astrophysics.
Interests
AI, machine learning, dynamics of learning, optimization and deep generative modeling
Latest Publications
ICLR workshop on Practical ML for Developing Countries - April 26, 2020
Streamlining Tensor and Network Pruning in PyTorch
Michela Paganini, Jessica Forde
ICLR workshop on Practical ML for Developing Countries - April 26, 2020
On Iterative Neural Network Pruning, Reinitialization, and the Similarity of Masks
Michela Paganini, Jessica Zosa Forde
NeurIPS - December 10, 2019
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
Ari Morcos, Haonan Yu, Michela Paganini, Yuandong Tian
Debugging Machine Learning Models Workshop at ICLR - May 6, 2019
The Scientific Method in the Science of Machine Learning
Jessica Zosa Forde, Michela Paganini