Alex Nowak-Vila, Research Scientist, Ecole Normale Supérieure and INRIA; Paris, France

Consistency of Max-Margin Methods for Structured Prediction

The foundational concept of Max-Margin in machine learning is ill-posed for output spaces with more than two labels such as in structured prediction.  In the first part of the talk, we show that the Max-Margin loss can only be consistent to the classification task under highly restrictive assumptions on the discrete loss measuring the error between outputs and we generalize partial consistency results existing for the classification error.  In the second part, we design two Max-Margin loss extensions: the Restricted-Max-Margin loss for which we prove consistency under mild assumptions and the Max-Min-Margin loss for which consistency always holds. Finally, we provide an efficient algorithm for the latter working in structured prediction settings based on projections to the marginal polytope and provide generalization guarantees with respect to the original task of interest. 

• Bio: Alex Nowak is a Research Scientist at Owkin, working at the intersection of machine learning and healthcare. He holds a PhD in Machine Learning advised by Francis Bach and Alessandro Rudi from INRIA and Ecole Normale Supérieure at the SIERRA project-team in Paris, France.

Join via Zoom at https://cuboulder.zoom.us/j/92089983548?pwd=QmNER2J1S0NLWTZ2N2NEUmRaVkgxQT09

Please note non-standard time for this talk!