
From probabilistic bisimulation to representation learning via metrics
From Strachey Lectures by Oxford University
December 2, 2024 · 55 min
About this episode
Professor Prakash Panangaden discusses the evolution of bisimulation concepts and their applications in machine learning.
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…
People in this episode
Host: Oxford University
Guest: Professor Prakash Panangaden
Topics covered
- bisimulation
- probabilistic systems
- representation learning
- machine learning
- reinforcement learning
- behavioral similarity
Keywords
- bisimulation
- probabilistic bisimulation
- representation learning
- Markov decision processes
- machine learning
- theoretical work
More episodes of Strachey Lectures
- Hardening Digital Infrastructure: Two Examples · May 27, 2026 · 1h 2m
- An AI stack: from scaling AI workloads to evaluating LLMs · February 26, 2026 · 56 min
- Advances in Garbled Circuits · October 27, 2025 · 48 min
- Will Computers prove theorems? · May 15, 2025 · 46 min
- Formalizing the Future: Lean’s Impact on Mathematics, Programming, and AI · May 15, 2025 · 47 min
- Privacy, Verification, Robustness: A Cryptographer's perspective on ML · March 11, 2025 · 1h 4m
Explore listener stats, chart rankings, contacts and more on the Strachey Lectures podcast page.