ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1903.01093
36
22

Differentiable Causal Computations via Delayed Trace

4 March 2019
David Sprunger
Shin-ya Katsumata
ArXiv (abs)PDFHTML
Abstract

We investigate causal computations taking sequences of inputs to sequences of outputs where the nnnth output depends on the first nnn inputs only. We model these in category theory via a construction taking a Cartesian category CCC to another category St(C)St(C)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)St(C)St(C) with an implicit guardedness guarantee. When CCC is equipped with a Cartesian differential operator, we construct a differential operator for St(C)St(C)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.

View on arXiv
Comments on this paper