Plenary Talk

“When the Model selects the Samples

Time: 5-6:30 PM, Feburary 14

Abstract: This talk presents (the theory and practice of) a few different incarnations of a somewhat surprising phenomenon in deep-learnt models: the output inferences of these models can be used to select, re-weigh and re-shape the same datasets on which the model was originally trained, to subsequently train the same model better.

Biography: Sujay Sanghavi is the Fluor Centennial Fellow and Professor at UT Austin, where his research focuses on machine learning and optimization with applications to search, recommendations, and large model training. At UT Austin Sujay heads the EnCore and IFDS Tripods Institutes, and is the Associate Director of the Amazon Science Hub. Sujay has been a Principal Research Scientist and is currently an Amazon Scholar at Amazon. Sujay has three degrees from U. Illinois at Urbana Champaign: an MS in ECE, an MS in Math, and a PhD in ECE.