DeepAI AI Chat
Log In Sign Up

Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem

by   Vaggos Chatziafratis, et al.

Understanding the representational power of Deep Neural Networks (DNNs) and how their structural properties (e.g., depth, width, type of activation unit) affect the functions they can compute, has been an important yet challenging question in deep learning and approximation theory. In a seminal paper, Telgarsky highlighted the benefits of depth by presenting a family of functions (based on simple triangular waves) for which DNNs achieve zero classification error, whereas shallow networks with fewer than exponentially many nodes incur constant error. Even though Telgarsky's work reveals the limitations of shallow neural networks, it does not inform us on why these functions are difficult to represent and in fact he states it as a tantalizing open question to characterize those functions that cannot be well-approximated by smaller depths. In this work, we point to a new connection between DNNs expressivity and Sharkovsky's Theorem from dynamical systems, that enables us to characterize the depth-width trade-offs of ReLU networks for representing functions based on the presence of generalized notion of fixed points, called periodic points (a fixed point is a point of period 1). Motivated by our observation that the triangle waves used in Telgarsky's work contain points of period 3 - a period that is special in that it implies chaotic behavior based on the celebrated result by Li-Yorke - we proceed to give general lower bounds for the width needed to represent periodic functions as a function of the depth. Technically, the crux of our approach is based on an eigenvalue analysis of the dynamical system associated with such functions.


page 1

page 2

page 3

page 4


Better Depth-Width Trade-offs for Neural Networks through the lens of Dynamical Systems

The expressivity of neural networks as a function of their depth, width ...

Depth-Width Trade-offs for Neural Networks via Topological Entropy

One of the central problems in the study of deep learning theory is to u...

Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem

Given a target function f, how large must a neural network be in order t...

An Analysis of the Expressiveness of Deep Neural Network Architectures Based on Their Lipschitz Constants

Deep neural networks (DNNs) have emerged as a popular mathematical tool ...

On the Spectral Bias of Deep Neural Networks

It is well known that over-parametrized deep neural networks (DNNs) are ...

Interplay between depth of neural networks and locality of target functions

It has been recognized that heavily overparameterized deep neural networ...

Information contraction in noisy binary neural networks and its implications

Neural networks have gained importance as the machine learning models th...