Harmonic Analysis and Approximation Theory techniques in Machine Learning, part 2

Abstract: In this talk, I will pick up my presentation from where I left off last time. The main challenge I will address in this talk is to find small size shallow neural networks that can be trained algorithmically and which achieve guaranteed approximation speed and precision. To maintain the small size we apply penalties on the weights of the network. We show that under minimal requirements, all local minima of the resulting problem are well behaved and possess a desirable small size without sacrificing precision.

Additionally, I will present an overview of the topics in the upcoming Focus Program on Data Science, Approximation Theory, and Harmonic Analysis at Fields Institute in Toronto, Canada where I am one of the coorganizers. This will be held in a hybrid format from May 9 to June 10, 2022. More details at www.fields.utoronto.ca/activities/21-22/data

ArmenianMathematics

Audience: general audience

( slides | video )

Comments: Talk host: Michael Poghosyan (YSU)

---

Yerevan Mathematical Colloquium

Series comments: "Yerevan Mathematical Colloquium" invites survey talks aimed at a general mathematical audience, that emphasize proof methods, relations between branches of mathematics, possible applications, and open problems.

---