22/04/2026
The empirical risk minimization (ERM) approach for supervised learning chooses prediction rules that fit training samples and are “simple” (generalize). This approach has been the workhorse of machine learning methods and has enabled a myriad of applications. However, ERM methods strongly rely on the specific training samples available and cannot easily address scenarios affected by distribution shifts or corrupted samples. Robust risk minimization (RRM) is an alternative approach that does not aim to fit training examples and instead chooses prediction rules minimizing the maximum expected loss (risk). This talk presents a learning framework based on the generalized maximum entropy principle that leads to minimax risk classifiers (MRCs). In particular, MRCs can minimize worst-case expected 0-1 loss while providing performance guarantees, and are strongly universally consistent using feature mappings given by characteristic kernels. In addition, the methods presented can provide techniques that are effective in practical situations that defy conventional assumptions, such as scenarios affected by distribution shifts and corrupted samples.
Bio: Santiago Mazuelas received the Ph.D. in Mathematics and Ph.D. in Telecommunications Engineering from the University of Valladolid, Spain, in 2009 and 2011, respectively. He is currently an Ikerbasque Research Professor at the Basque Center for Applied Mathematics (BCAM). Prior to joining BCAM, he was a Staff Engineer at Qualcomm Corporate Research and Development from 2014 to 2017. He previously worked from 2009 to 2014 as Postdoctoral Fellow and Associate in the Laboratory for Information and Decision Systems (LIDS) at the Massachusetts Institute of Technology (MIT). Dr. Mazuelas is currently Associate Editor-in-Chief for the IEEE Transactions on Mobile Computing, Associate Editor for the IEEE Transactions on Wireless Communications, Action Editor for the Transactions on Machine Learning Research, and Area Chair at the International Conference in Machine Learning (ICML). He has received multiple awards including the IEEE Communications Society Fred W. Ellersick Prize in 2012, the Early Achievement Award from the IEEE ComSoc in 2018, and the SEIO-BBVA Foundation Best Contribution in 2022 and 2025.