DeepAI
Log In Sign Up

Robust normalizing flows using Bernstein-type polynomials

02/06/2021
by   Sameera Ramasinghe, et al.
0

Normalizing flows (NFs) are a class of generative models that allows exact density evaluation and sampling. We propose a framework to construct NFs based on increasing triangular maps and Bernstein-type polynomials. Compared to the existing (universal) NF frameworks, our method provides compelling advantages like theoretical upper bounds for the approximation error, robustness, higher interpretability, suitability for compactly supported densities, and the ability to employ higher degree polynomials without training instability. Moreover, we provide a constructive universality proof, which gives analytic expressions of the approximations for known transformations. We conduct a thorough theoretical analysis and empirically demonstrate the efficacy of the proposed technique using experiments on both real-world and synthetic datasets.

READ FULL TEXT
03/20/2022

Approximation and Interpolation of Singular Measures by Trigonometric Polynomials

Complex signed measures of finite total variation are a powerful signal ...
03/10/2021

Universal Approximation of Residual Flows in Maximum Mean Discrepancy

Normalizing flows are a class of flexible deep generative models that of...
07/27/2022

An improved bound on Legendre approximation

In this paper, new relations between the derivatives of the Legendre pol...
09/04/2017

Continuous-Time Flows for Deep Generative Models

Normalizing flows have been developed recently as a method for drawing s...
05/07/2019

Sum-of-Squares Polynomial Flow

Triangular map is a recent construct in probability theory that allows o...
08/01/2021

Multidimensional Padé approximation of binomial functions: Equalities

Let ω_0,…,ω_M be complex numbers. If H_0,…,H_M are polynomials of degree...