Mar

16:20

HDI&TFAIM Lab seminar 'Dimension-free Bounds in High-dimensional Linear Regression via Error-in-operator Approach'

12+

*recommended age

Event ended

On March 27 Fyodor Noskov, Junior Research Fellow at HSE Laboratory for Theoretical Modelling in AI, will speak on 'Dimension-free Bounds in High-dimensional Linear Regression via Error-in-operator Approach'.

Abstract:

We consider a problem of high-dimensional linear regression with random design. We suggest a novel approach referred to as error-in-operator which does not estimate the design covariance $\Sigma$ directly but incorporates it into empirical risk minimization. We provide an expansion of the excess prediction risk and derive non-asymptotic dimension-free bounds on the leading term and the remainder. This helps us to show that auxiliary variables do not increase the effective dimension of the problem, provided that parameters of the procedure are tuned properly. We also discuss computational aspects of our method and illustrate its performance with numerical experiments.

Start time: 16:20

Venue: 11 Pokrovsky Bulvar, room D725

If you need a pass to HSE, please contact ealyamovskaya@hse.ru or kzelenova@hse.ru.

Date

27 March 16:20