Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates

by   Nicholas J. Irons, et al.

Triangular flows, also known as Knöthe-Rosenblatt measure couplings, comprise an important building block of normalizing flow models for generative modeling and density estimation, including popular autoregressive flow models such as real-valued non-volume preserving transformation models (Real NVP). We present statistical guarantees and sample complexity bounds for triangular flow statistical models. In particular, we establish the statistical consistency and the finite sample convergence rates of the Kullback-Leibler estimator of the Knöthe-Rosenblatt measure coupling using tools from empirical process theory. Our results highlight the anisotropic geometry of function classes at play in triangular flows, shed light on optimal coordinate ordering, and lead to statistical guarantees for Jacobian flows. We conduct numerical experiments on synthetic data to illustrate the practical implications of our theoretical findings.



page 4

page 16

page 18


Cubic-Spline Flows

A normalizing flow models a complex probability density as an invertible...

Neural Spline Flows

A normalizing flow models a complex probability density as an invertible...

Doubly Stochastic Generative Arrivals Modeling

We propose a new framework named DS-WGAN that integrates the doubly stoc...

Causal Autoregressive Flows

Two apparently unrelated fields – normalizing flows and causality – have...

Jacobian Determinant of Normalizing Flows

Normalizing flows learn a diffeomorphic mapping between the target and b...

Divergence Frontiers for Generative Models: Sample Complexity, Quantization Level, and Frontier Integral

The spectacular success of deep generative models calls for quantitative...

Lattice Recurrent Unit: Improving Convergence and Statistical Efficiency for Sequence Modeling

Recurrent neural networks have shown remarkable success in modeling sequ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.