I currently work at UC Berkeley with Prof. Dawn Song. Previously I was at UC San Diego, where I worked closely with Prof. Julian McAuley and Prof. Kamalika Chaudhuri. I have also collaborated with Prof. Larry Holder at Washington State University. A few years ago I interned at Microsoft Silicon Valley and Qualcomm in San Diego.
Differentiable neural network architecture search.
Richard Shin*, Charles Packer*, Dawn Song.
ICLR Workshop, 2018.
The successes of deep learning in recent years has been fueled by the development of innovative new neural network architectures. We propose a method for transforming a discrete neural network architecture space into a continuous and differentiable form, which enables the use of standard gradient-based optimization techniques for this problem, and allows us to learn the architecture and the parameters simultaneously.
GraphZip: Mining graph streams using dictionary-based compression.
Charles Packer, Larry Holder.
Mining and Learning with Graphs (MLG), 2017.
[summary] [bibtex] [code+data]
A massive amount of data generated today on platforms such as social networks, telecommunication networks, and the internet in general can be represented as graph streams. GraphZip is a scalable method for mining interesting patterns in graph streams, based on the Lempel-Ziv class of compression algorithms.
Learning compatibility across categories for heterogeneous item recommendation.
Ruining He, Charles Packer, Julian McAuley.
International Conference on Data Mining (ICDM), 2016.
[summary] [bibtex] [data]
We propose a method for learning complex, non-metric relationships between items in a product recommendation setting. Our method, Monomer, is able to model human visual preferences by projecting image data into low-dimensional embeddings ('style' spaces).