Robert Gens

Robert Gens is a researcher at the University of Washington, affiliated with the College of Engineering and the Department of Computer Science and Engineering. His work focuses on advancing machine learning architectures, particularly Sum-Product Networks (SPNs), with applications in computer vision and deep learning.

• Education: S.B. in Electrical Engineering and Computer Science from MIT (2009), Ph.D. in Computer Science and Engineering from the University of Washington (2016).

His research integrates insights from neuroscience, graphics, and mathematics to develop algorithms capable of modeling infinite visual data as stable concepts. Key contributions include structural learning, discriminative training, and computational efficiency in SPNs.

Notable publications span NIPS, ICML, and ICLR venues, with a focus on SPN optimization and compositional modeling. Trends in his work emphasize tractable probabilistic models, neural network efficiency, and cross-disciplinary algorithm design.

Awards include the Google PhD Fellowship in Deep Learning and an NIPS 2012 Outstanding Student Paper Award. Current research involves Deep Symmetry Networks at the Seattle Laboratory of Robotics.