I currently work on machine learning research and engineering at Microsoft Research AI. Previously, I was a software developer at Wolfram Research, working on large scale natural language processing and data mining of technical literature, primarily in math, using a variety of techniques in supervised and unsupervised learning, and creating scalable data processing and retrieval pipelines with e.g. Java, Python, and SQL.
My interests primarily lie in two areas: 1) develop algorithms to understand and process high-dimensional, large-scale data, and 2) deep learning. Towards 1) I have co-developed algorithms for efficient outlier detection in high dimensions, and methods for neural-assisted locality sensitive hashing. Towards 2) I have explored various large-scale network architectures for language classification and text-image retrieval on web-scale data. In general I enjoy applying classical and mathematical methods to improve model building. Please refer to my papers for more details. At the moment I'm working on learning universal vision-language representations to improve core relevance algorithms for Bing.
I have also built different classifiers of various textual data using neural networks to predict characteristics such as the character encoding or the mathematical subject classification.
I studied math at Princeton (undergraduate) and the University of Wisconsin - Madison (graduate).
I am also broadly interested in current research developments in machine learning. I enjoy figuring out and implementing new algorithms.