Timezone: »

 
Poster
A Spline Theory of Deep Learning
Randall Balestriero · Richard Baraniuk

Thu Jul 12 09:15 AM -- 12:00 PM (PDT) @ Hall B #192
in Posters Thu »

We build a rigorous bridge between deep networks (DNs) and approximation theory via spline functions and operators. Our key result is that a large class of DNs can be written as a composition of {\em max-affine spline operators} (MASOs), which provide a powerful portal through which to view and analyze their inner workings. For instance, conditioned on the input signal, the output of a MASO DN can be written as a simple affine transformation of the input. This implies that a DN constructs a set of signal-dependent, class-specific templates against which the signal is compared via a simple inner product; we explore the links to the classical theory of optimal classification via matched filters and the effects of data memorization. Going further, we propose a simple penalty term that can be added to the cost function of any DN learning algorithm to force the templates to be orthogonal with each other; this leads to significantly improved classification performance and reduced overfitting with no change to the DN architecture. The spline partition of the input signal space opens up a new geometric avenue to study how DNs organize signals in a hierarchical fashion. As an application, we develop and validate a new distance metric for signals that quantifies the difference between their partition encodings.

[ PDF] 

Author Information

Randall Balestriero (Rice University)
Richard Baraniuk (OpenStax / Rice University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors