Kyle Reing

I am a first year PhD student in the Department of Computer Science at the University of Sourthern California. I am a member of the Intelligent Systems Department at the USC Information Sciences Institute, where I am coadvised by Aram Galstyan and Greg Ver Steeg. During the Fall 2015 semester, I will be working as a Teaching Assistant for CSCI 109. In Spring 2015 I graduated from the University of Connecticut with a BSE in Computer Science and Engineering.

My research interests mainly lie at the intersection of statistical machine learning and complex networks. More specifically, I'm interested in representation learning, transfer learning, causal inference, time-series modeling, online learning, metric/kernel learning, and many problems related to complex network topology. My advisors have recently published a few exciting papers on an information theoretic approach to unsupervised fearture learning. The method is model-free, and almost perfectly recovers latent structure in large and complex data without any labels. The papers can be found here, here, and here. Currently, I plan on exploring ways of extending the existing method to a wider range of real world data. While doing this, I also hope to investigate the principles underlying the methods stellar performance. In the long term, my main research goal is to try and develop a functional learning framework for artificial general intelligence.

At the moment, I have many small side projects in the works, most of which haven't seen enough progress to merit including on this site. I have a non-technical blog, but I rarely post there. You can find it here. I'm in the process of creating a more technical blog, which I'll probably use more often. On occasion, I answer questions on Quora that I find interesting.

Email: reing [at] usc [dot] edu

Recently arrived in LA after accepting an offer to pursue my doctoral studies at USC!

No official puplications as of yet. Stay tuned!