À PROPOS DE CET ÉPISODE
Strachey Lecture: From probabilistic bisimulation to representation learning via metrics - Professor Prakash Panangaden Bisimulation is a fundamental equivalence relation in process theory invented by Robin Milner and with an elegant fixed-point definition due to David Park. In this talk I will review the concept of bisimulation and then discuss its probabilistic analogue. This was extended to systems with continuous state spaces. Despite its origin in theoretical work, it has proved to be useful in fields like machine learning, especially reinforcement learning. Surprisingly, it turned out that one could prove a striking theorem: a theorem that pins down exactly what differences one can "see" in process behaviours when two systems are not bisimilar.
However, it is questionable whether a concept like equivalence is the right one for quantitative systems. If two systems are almost, but not quite, the same, bisimulation would just say that they are not equivalent. One would like to say in some way that they are "almost" the same. Metric analogues of bisimulation were developed to capture a notion of behavioral similarity rather than outright equivalence. These ideas have been adopted by the machine learning community and a bisimulation-style metric was developed for Markov decision processes. Recent work has shown that variants of these bisimulation metrics can be useful in representation learning. I will tell the tale of this arc of ideas in as accessible a way as possible.
However, it is questionable whether a concept like equivalence is the right one for quantitative systems. If two systems are almost, but not quite, the same, bisimulation would just say that they are not equivalent. One would like to say in some way that they are "almost" the same. Metric analogues of bisimulation were developed to capture a notion of behavioral similarity rather than outright equivalence. These ideas have been adopted by the machine learning community and a bisimulation-style metric was developed for Markov decision processes. Recent work has shown that variants of these bisimulation metrics can be useful in representation learning. I will tell the tale of this arc of ideas in as accessible a way as possible.
Anglais
Royaume-Uni
TRANSCRIPTION 🔗
1
00:00:01,660 --> 00:00:16,820
[Auto-generated transcript. Edits may have been applied for clarity.]
So. Welcome, everybody.
2
00:00:17,090 --> 00:00:22,180
Welcome to this lecture. The series of lectures founding doctor Christopher Strangio,
3
00:00:22,460 --> 00:00:27,200
who was a leading figure in the history of our Department of History of Programming languages.
4
00:00:27,650 --> 00:00:32,390
Before introducing today the speaker, I want to thank our sponsors for Oxford Asset Management…
00:00:01,660 --> 00:00:16,820
[Auto-generated transcript. Edits may have been applied for clarity.]
So. Welcome, everybody.
2
00:00:17,090 --> 00:00:22,180
Welcome to this lecture. The series of lectures founding doctor Christopher Strangio,
3
00:00:22,460 --> 00:00:27,200
who was a leading figure in the history of our Department of History of Programming languages.
4
00:00:27,650 --> 00:00:32,390
Before introducing today the speaker, I want to thank our sponsors for Oxford Asset Management…
RECHERCHER LES ÉPISODES PASSÉS
Rechercher les épisodes précédents de Strachey Lectures.
Avertissement: Le podcast et les illustrations intégrés sur cette page proviennent de Oxford University, qui est la propriété de son propriétaire et n'est ni affilié ni approuvé par Listen Notes, Inc.
MODIFIER
Merci de nous avoir aidé à tenir la base de données de podcasts à jour.