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

Abstract

The expressivity of neural networks as a function of their depth, width and type of activation units has been an important question in deep learning theory. Recently, depth separation results for ReLU networks were obtained via a new connection with dynamical systems, using a generalized notion of fixed points of a continuous map $f$, called periodic points. In this work, we strengthen the connection with dynamical systems and we improve the existing width lower bounds along several aspects. Our first main result is period-specific width lower bounds that hold under the stronger notion of $L^1$-approximation error, instead of the weaker classification error. Our second contribution is that we provide sharper width lower bounds, still yielding meaningful exponential depth-width separations, in regimes where previous results wouldn't apply. A byproduct of our results is that there exists a universal constant characterizing the depth-width trade-offs, as long as $f$ has odd periods. Technically, our results follow by unveiling a tighter connection between the following three quantities of a given function: its period, its Lipschitz constant and the growth rate of the number of oscillations arising under compositions of the function $f$ with itself.

arXiv commentAppeared in ICML 2020

References in corpus (6)

• On the Number of Linear Regions of Deep Neural Networks
• Exponential expressivity in deep neural networks through transient chaos
• Representation Benefits of Deep Feedforward Networks
• Deep ReLU Networks Have Surprisingly Few Activation Patterns
• On the Expressive Power of Deep Polynomial Neural Networks
• Is Deeper Better only when Shallow is Good?

Cited by in corpus (2)

• Depth-Width Trade-offs for Neural Networks via Topological Entropy
• Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth