UMN Machine Learning Seminar: Benefits of Convolutional Models

The UMN Machine Learning Seminar Series brings together faculty, students, and local industrial partners who are interested in the theoretical, computational, and applied aspects of machine learning, to pose problems, exchange ideas, and foster collaborations. The talks are every Wednesday from 12 p.m. - 1 p.m. during the Spring 2022 semester.

This week's speaker,  Dr. Alberto Bietti (NYU Center for Data Science), will be giving a talk titled "Benefits of Convolutional Models".

Abstract

Many supervised learning problems involve high-dimensional data such as images, text, or graphs. In order to make efficient use of data, it is often useful to leverage priors in the problem at hand, such as invariance to certain transformations or stability to small deformations. Empirically, deep convolutional architectures have been very successful on such problems, raising the question of how they are able to capture the structure of these problems for efficient learning.
I study this question from a theoretical perspective using kernel methods, in particular convolutional kernels, which are constructed following similar architectural principles, and provide good empirical performance on standard vision benchmarks such as Cifar10. I will present three contributions that highlight the benefits of (deep) convolutional architectures in terms of stability to deformations and sample complexity.

Biography

Alberto Bietti received his PhD in 2019 from Inria Grenoble, where he worked under the supervision of Julien Mairal. He was a postdoc at Inria Paris in 2020 and is currently a Faculty Fellow at the NYU Center for Data Science. His main research focus is on the theoretical foundations of deep learning, particularly through the lens of kernel methods.