pith. sign in

arxiv: 1903.01093 · v1 · pith:4E4VCGUWnew · submitted 2019-03-04 · 💻 cs.LO · cs.NE· math.CT

Differentiable Causal Computations via Delayed Trace

classification 💻 cs.LO cs.NEmath.CT
keywords tracecategorydelayeddifferentialoperatorbackpropagationcartesiancausal
0
0 comments X
read the original abstract

We investigate causal computations taking sequences of inputs to sequences of outputs where the $n$th output depends on the first $n$ inputs only. We model these in category theory via a construction taking a Cartesian category $C$ to another category $St(C)$ with a novel trace-like operation called "delayed trace", which misses yanking and dinaturality axioms of the usual trace. The delayed trace operation provides a feedback mechanism in $St(C)$ with an implicit guardedness guarantee. When $C$ is equipped with a Cartesian differential operator, we construct a differential operator for $St(C)$ using an abstract version of backpropagation through time, a technique from machine learning based on unrolling of functions. This obtains a swath of properties for backpropagation through time, including a chain rule and Schwartz theorem. Our differential operator is also able to compute the derivative of a stateful network without requiring the network to be unrolled.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.