Timezone: »

 
Workshop
Discrete Optimization in Machine Learning (DISCML): Structure and Scalability
Stefanie Jegelka · Andreas Krause · Jeffrey A Bilmes · Pradeep Ravikumar

Fri Dec 07 07:30 AM -- 06:30 PM (PST) @ Emerald Bay B, Harveys Convention Center Floor (CC)
Event URL: http://discml.cc »

Optimization problems with discrete solutions (e.g., combinatorial optimization) are becoming increasingly important in machine learning. The core of statistical machine learning is to infer conclusions from data, and when the variables underlying the data are discrete, both the tasks of inferring the model from data, as well as performing predictions using the estimated model are discrete optimization problems. Two factors complicate matters: first, many discrete problems are in general computationally hard, and second, machine learning applications often demand solving such problems at very large scales.

The focus of this year's workshop lies on structures that enable scalability. Examples of important structures include sparse graphs, the marginal polytope, and submodularity. Which properties of the problem make it possible to still efficiently obtain exact or decent approximate solutions? What are the challenges posed by parallel and distributed processing? Which discrete problems in machine learning are in need of more scalable algorithms? How can we make discrete algorithms scalable while retaining quality? Some heuristics perform well but as of yet are devoid of a theoretical foundation; what explains such good behavior?

Author Information

Stefanie Jegelka (MIT)
Andreas Krause (ETHZ)
Jeffrey A Bilmes (University of Washington, Seattle)

Jeffrey A. Bilmes is a professor at the Department of Electrical and Computer Engineering at the University of Washington, Seattle Washington. He is also an adjunct professor in Computer Science & Engineering and the department of Linguistics. Prof. Bilmes is the founder of the MELODI (MachinE Learning for Optimization and Data Interpretation) lab here in the department. Bilmes received his Ph.D. from the Computer Science Division of the department of Electrical Engineering and Computer Science, University of California in Berkeley and a masters degree from MIT. He was also a researcher at the International Computer Science Institute, and a member of the Realization group there. Prof. Bilmes is a 2001 NSF Career award winner, a 2002 CRA Digital Government Fellow, a 2008 NAE Gilbreth Lectureship award recipient, and a 2012/2013 ISCA Distinguished Lecturer. Prof. Bilmes was, along with Andrew Ng, one of the two UAI (Conference on Uncertainty in Artificial Intelligence) program chairs (2009) and then the general chair (2010). He was also a workshop chair (2011) and the tutorials chair (2014) at NIPS/NeurIPS (Neural Information Processing Systems), and is a regular senior technical chair at NeurIPS/NIPS since then. He was an action editor for JMLR (Journal of Machine Learning Research). Prof. Bilmes's primary interests lie in statistical modeling (particularly graphical model approaches) and signal processing for pattern classification, speech recognition, language processing, bioinformatics, machine learning, submodularity in combinatorial optimization and machine learning, active and semi-supervised learning, and audio/music processing. He is particularly interested in temporal graphical models (or dynamic graphical models, which includes HMMs, DBNs, and CRFs) and ways in which to design efficient algorithms for them and design their structure so that they may perform as better structured classifiers. He also has strong interests in speech-based human-computer interfaces, the statistical properties of natural objects and natural scenes, information theory and its relation to natural computation by humans and pattern recognition by machines, and computational music processing (such as human timing subtleties). He is also quite interested in high performance computing systems, computer architecture, and software techniques to reduce power consumption. Prof. Bilmes has also pioneered (starting in 2003) the development of submodularity within machine learning, and he received a best paper award at ICML 2013, a best paper award at NIPS 2013, and a best paper award at ACMBCB in 2016, all in this area. In 2014, Prof. Bilmes also received a most influential paper in 25 years award from the International Conference on Supercomputing, given to a paper on high-performance matrix optimization. Prof. Bilmes has authored the graphical models toolkit (GMTK), a dynamic graphical-model based software system widely used in speech, language, bioinformatics, and human-activity recognition.

Pradeep Ravikumar (Carnegie Mellon University)

More from the Same Authors