Poster
in
Workshop: Information-Theoretic Principles in Cognitive Systems (InfoCog)
Lossy Compression and the Granularity of Causal Representation
David Kinney · Tania Lombrozo
[
Abstract
]
[ Project Page ]
presentation:
Information-Theoretic Principles in Cognitive Systems (InfoCog)
Fri 15 Dec 6:15 a.m. PST — 3:30 p.m. PST
[
OpenReview]
Fri 15 Dec 12:40 p.m. PST
— 1:30 p.m. PST
Fri 15 Dec 6:15 a.m. PST — 3:30 p.m. PST
Abstract:
A given causal system can be represented in a variety of ways. How do agents determine which variables to include in their causal representations, and at what level of granularity? Using techniques from information theory, we develop a formal theory according to which causal representations reflect a trade-off between compression and informativeness. We then show, across three studies (N=1,391), that participants’ choices over causal models demonstrate a preference for more compressed causal models when all other factors are held fixed, with some further tolerance for lossy compressions.
Chat is not available.