Dove e quando

Date: Thursday, 28st March 2019 Location: Dibris, Valletta Puggia, Conference Hall (322) Speaker: Luigi Carratino Time: 2:30PM Title: Algorithmic Regularization for Large-scale Machine Learning Abstract: Classically, regularization is achieved imposing explicit constraints on a data fit term, and optimization aspects are considered separately. We discuss how regularization can be controlled implicitly by an optimization method of choice. This latter approach has the advantage that training time controls at the same time statistical accuracy and time complexity of the obtained estimator. Moreover, we discuss how computations can be further reduced considering random projections. Our study bridges optimization and statistical studies. Short Bio: Luigi is a third-year PhD student in Computer Science in the Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS) of the Università degli Studi di Genova (UNIGE). He is working with Prof. Lorenzo Rosasco in the Laboratory for Computational and Statistical Learning (LCSL). His research focuses on Machine Learning. He aims to blend statistical and optimization principles to design sound and efficient learning procedures for high-dimensional large-scale data.

Contatti