Despite recent advancements in neural data compression, classical codecs such as JPEG and BPG have remained industry standards to date. The talk will provide an introduction to the field of neural compression that provides novel perspectives to probabilistic machine learning while focusing on why these new compression technologies have not seen the 10X performance boosts that deep learning has already achieved in other fields, such as NLP or vision. The talk will also present new avenues for neural compression research that provide novel directions for deep probabilistic modeling and show promise to make neural compression more practical and widely applicable across industries.
Stephan Mandt is an Associate Professor of Computer Science and Statistics at the University of California, Irvine. From 2016 until 2018, he was a Senior Researcher and Head of the statistical machine learning group at Disney Research in Pittsburgh and Los Angeles. He held previous postdoctoral positions at Columbia University and Princeton University. Stephan holds a Ph.D. in Theoretical Physics from the University of Cologne, where he received the German National Merit Scholarship. He is furthermore a recipient of the NSF CAREER Award, the UCI ICS Mid-Career Excellence in Research Award, the German Research Foundation's Mercator Fellowship, a Kavli Fellow of the U.S. National Academy of Sciences, a member of the ELLIS Society, and a former visiting researcher at Google Brain. Stephan is an Action Editor of the Journal of Machine Learning Research and Transaction on Machine Learning Research and regularly serves as an Area Chair for NeurIPS, ICML, AAAI, and ICLR. His research is currently supported by NSF, DARPA, IARPA, DOE, Disney, Intel, and Qualcomm.