IEEE IT Society, Santa Clara Valley Chapter presents "Deep knockoffs machines for replicable selections"

Topic: 
Deep knockoffs machines for replicable selections
Wednesday, March 20, 2019 - 6:30pm
Venue: 
Packard 202
Speaker: 
Yaniv Romano (Stanford)
Abstract / Description: 

The Santa Clara Valley Chapter of the IEEE Information Theory Society sponsors this event. Please register if you plan to attend. Registration is not necessary for attendance but it helps with planning a successful event.

This is a follow up talk to the 2019 Kailath lecture. The speaker, Yaniv Romano is one of Emmanuel Candes' postdoctoral researchers. He will go in more detail over model-X knockoffs.


 

Model-X knockoffs is a new statistical tool that reliably selects which of the many potentially explanatory variables of interest (e.g. the absence or not of a mutation) are indeed truly associated with the response under study (e.g. the risk of getting a specific form of cancer). This framework can deal with very complex statistical models; in fact, they may be so complex that they can be treated as black boxes. The idea is to construct fake variables — knockoffs — which obey some crucial exchangeability properties with the real variables we wish to assay so that they can be used as negative controls. To leverage the full power of this framework, however, we need flexible tools to construct knockoffs from sampled data. This talk presents a machine that can produce knockoffs for arbitrary and unspecified data distributions, using deep generative models. The main idea is to iteratively refine a knockoff sampling mechanism until a criterion measuring the validity of the knockoffs we produce is minimized. Extensive numerical experiments and quantitative tests confirm the generality, effectiveness, and power of our approach. This results in a model-free variable selection method, and we present an application to the study of mutations linked to changes in drug resistance in the human immunodeficiency virus.


 

Bio:

Yaniv Romano is a postdoctoral fellow in the department of statistics at Stanford University, advised by Prof. Emmanuel Candès. He received his BSc (2012), MSc (2015) and PhD (2017) from the department of Electrical Engineering, Technion – Israel Institute of Technology. His MSc and Ph.D advisor was Prof. Michael Elad. Together with Prof. Elad, he constructed a Massive Open Online Course (MOOC) on Sparse Representations on the edX platform. Yaniv received the 2015 Zeff fellowship, the 2017 Andrew and Erna Finci Viterbi fellowship, the 2017 Irwin and Joan Jacobs fellowship, the 2018-2019 Zuckerman postdoctoral scholarship, the 2018-2019 ISEF fellowship for postdoctoral studies, and the 2018-2019 Viterbi fellowship, Technion.

Yaniv has been working in the industry as an image processing algorithms developer. The super-resolution technology he invented together with Peyman Milanfar is being used in various Google's products, e.g. Pixel 2/XL Phones, Google Clips, Google+ and Motion Stills application.