Home > FFT 2022 > Zico Kolter

Zico Kolter (CMU)

Time: 2:30 pm on Friday, October 7th, 2022

How can we leverage FFT-based methods in convolutional networks?

Convolutional neural networks are one of the most widely used models in deep learning. However, the actual computation of these networks is typically done by simply "unrolling" a (relatively small) convolutional operator manually, rather than using Fourier-based approaches, and spectral approaches to convolutions have been more or less absent from practical deep learning. In this talk, I'll argue that, in fact, there are several interesting extensions to traditional convolutions networks that can be enabled through FFT-baed approaches: specifically, the ability to _invert_ convolutional operators, offered by the FFT-based approaches, enables us to create a number of interesting new layers types, such as orthogonal convolutions or better solvers for certain classes of fixed-point layers. I will conclude by discussing some of the larger implications and future outlook of such approaches.