Cameron R. Wolfe PhD Student in Machine Learning, Rice University

About Me

Professional Headshot

I am a PhD student in Computer Science at Rice University in Houston, TX. I am currently advised by Dr. Anastasios Kyrillidis. My interests are loosely related to math and machine learning. Currently, my main interests include non-convex optimization theory, provable neural network pruning techniques, and quantum computing. This list is definitely not exhaustive, however, as my interests change and expand as I find new and interesting projects. Outside of academia, I am a Research Scientist at Alegion, a software startup based in Austin, TX. At Alegion, I focus on the development of long term, practical research projects in several areas, including online training of neural networks, deep learning in video, and evaluating the quality of video-based annotations for computer vision applications.

Prior to coming to Rice, I was an undergraduate student in Computer Science at UT Austin. During my time at UT, I did research alongisde the neural networks research group. My research interests were mostly related to genetic algorithms, and I was advised by Dr. Cem C. Tutum.

Publications

Provably Efficient Lottery Ticket Discovery

Currently under review.

Access on Arxiv

Exceeding the Limits of Visual-Linguistic Multi-Task Learning

Internship project.

Access on Arxiv

REX: Revisiting Budgeted Training with an Improved Schedule

Currently under review.

Access on Arxiv

Momentum-inspired Low-Rank Coordinate Descent for Diagonally Constrained SDPs

Currently under review.

Access on Arxiv

ResIST: Layer-Wise Decomposition of ResNets for Distributed Training

Currently under review.

Access on Arxiv

GIST: Distributed Training for Large-Scale Graph Convolutional Networks

Currently under review.

Access on Arxiv View Code

Distributed Learning of Deep Neural Networks using Independent Subnet Training

Currently under review.

Access on Arxiv

Demon: Momentum Decay for Improved Neural Network Training

Currently under review.

Access on Arxiv

E-Stitchup: Data Augmentation for Pre-Trained Embeddings

Accepted as Undergraduate Honors Thesis, UT Austin (2020).

Access on Arxiv

Functional Generative Design of Mechanisms with RNNs and Novelty Search

Accepted as a Conference Paper at GECCO (2019).

Access on Arxiv View Code

Tutorials

In my free time, I enjoy making video tutorials regarding research topics that I find interesting. These videos are all published on my ResearchMadeSimple channel on YouTube, and all slides for the presentations can be found here. I aim to provide very clear explanations and background information so that even beginners can understand complex research topics.

Introduction to Graph Independent Subnetwork Training

View on YouTube

Optimization Analysis with Polynomials

View on YouTube

Introduction to Graph Convolutional Networks

View on YouTube

Introduction to AdaScaleSGD

View on YouTube