I recently completed my PhD in Computer Science and Engineering at the University of Washington, advised by Pedro Domingos. My current research is on developing highly-expressive but tractable machine learning models and algorithms in order to build more intelligent systems and tools. Applications include deep learning, probabilistic modeling, computer vision, nonconvex optimization, and protein folding. In previous work, I have explored nonparametric Bayesian modeling, planning and decision making, reinforcement learning, imitation, and goal inference. I've had the pleasure of being advised by both Rajesh Rao and David Wingate, and have had the good fortune to visit other research labs, including MIT in the labs of Leslie Kaelbling and Josh Tenenbaum, Berkeley with Tom Griffiths in the Computational Cognitive Science Lab, and an internship at Intel Labs in Seattle, working with Dieter Fox on Human Robot Interaction. Here is a link to my CV and my github. ## Recent News1/29/2018 -Our paper "Deep Learning as a Mixed Convex-Combinatorial Optimization Problem" was accepted to ICLR 2018! Code is now available on my github repo.
12/12/2017 - I successfully defended my thesis and am graduating this quarter!
8/3/2017 - Our paper "Unifying sum-product networks and submodular fields" was accepted to the PADL workshop at ICML 2017.
4/25/2016 - Our paper "The Sum-Product Theorem: A Foundation for Learning Tractable Models" was accepted to ICML 2016!
7/27/2015 - The code for RDIS is available! (from our Distinguished Paper on "Recursive Decomposition for Nonconvex Optimization") Get it from my github repo here.
6/3/2015 - Our paper on Recursive Decomposition for Nonconvex Optimization was chosen as the winner of the Distinguished Paper Award at IJCAI 2015!
## PublicationsDeep Learning as a Mixed Convex-Combinatorial Optimization Problem.Abram L. Friesen and Pedro Domingos (2018). In Proceedings of the 6th International Conference on Learning Representations (ICLR). Vancouver, Canada. April, 2018.
(pdf) (code) (poster) Unifying Sum-Product Networks and Submodular Fields.Abram L. Friesen and Pedro Domingos (2017). In Proceedings of the 1st Workshop on Principled Approaches to Deep Learning at the International Conference on Machine Learning (PADL at ICML). Sydney, Australia. August, 2017.
(pdf) (supplement) (poster) The Sum-Product Theorem: A Foundation for Learning Tractable Models. Abram L. Friesen and Pedro Domingos (2016). In Proceedings of the 33rd International Conference on Machine Learning (ICML). New York, New York. June, 2016.
(pdf) (supplement) (poster) Recursive Decomposition for Nonconvex Optimization.
Winner of the Distinguished Paper Award! Abram L. Friesen and Pedro Domingos (2015). In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI). Buenos Aires, Argentina. July, 2015.
(pdf) (supplement) (code) (poster) Exploiting Structure for Tractable Nonconvex Optimization. Abram L. Friesen and Pedro Domingos (2014). In Proceedings of the 1st Workshop on Learning Tractable Probabilistic Models at ICML 2014 (LTPM at ICML). Beijing, China. June, 2014.
(pdf) Nonconvex Optimization is Combinatorial Optimization. Abram L. Friesen and Pedro Domingos (2013). In Proceedings of the 6th Workshop on Optimization for Machine Learning at NIPS 2013 (OPT at NIPS). Lake Tahoe, Nevada. December, 2013.
(pdf) How prior probability influences decision making: a unifying probabilistic model. Yanping Huang, Abram L. Friesen, Timothy D. Hanks, Michael N. Shadlen, and Rajesh P. N. Rao (2012). In Proceedings of the 26th Annual Conference on Neural Information Processing Systems (NIPS). Lake Tahoe, Nevada. December, 2012.
(pdf) An ideal observer model for identifying the reference frame of objects. Joseph L. Austerweil, Abram L. Friesen, and Thomas L. Griffiths (2011). In Proceedings of the 25th Annual Conference on Neural Information Processing Systems (NIPS). Granada, Spain. December, 2011.
(pdf) Gaze Following as Goal Inference: A Bayesian Model. Abram L. Friesen and Rajesh P. N. Rao (2011). In Proceedings of the 33rd Annual Conference of the Cognitive Science Society. Boston, MA: Cognitive Science Society. July, 2011.
(pdf) Imitation Learning with Hierarchical Actions. Abram L. Friesen and Rajesh P. N. Rao (2010). In Proceedings of the International Conference on Learning and Development (ICDL), Ann Arbor, MI, USA. August, 2010.
(pdf) Estimating the Progress of MapReduce Pipelines. Kristi Morton, Abram Friesen, Magdalena Balazinska, and Dan Grossman (2010). In Proceedings of the 26th IEEE International Conference on Data Engineering (ICDE), Long Beach, CA, USA. March, 2010.
(pdf) |