안녕하세요, 데이터사이언스대학원에서 아래의 내용과 같이 BK21 x ERC 세미나를 개최하오니 여러분의 많은 관심과 참여를 부탁드립니다.
연사 박준형 박사님은 ETH Zürich에서 Postdoctoral Researcher로, 인과추론을 하기 위한 인과 모델이 표현하는 관찰데이터와 실험데이터 등의 관계를 Measure Theory를 통해서 수학적으로, 확률론적으로 이해하는 연구를 발표해주실 예정입니다.
일시: 2025년 4월 23일 오후 3:30 - 5:00
장소: 서울대학교 942동 302호
Speaker: Dr. Junhyung Park
Title: Causal Spaces: A Measure Theoretic Axiomatisation of Causality
Abstract:
While the theory of causality is widely viewed as an extension of probability theory, a view which we share, there was no universally accepted, axiomatic framework for causality, analogous to Kolmogorov's measure-theoretic axiomatisation for the theory of probabilities. Instead, many competing frameworks exist, such as the structural causal models or the potential outcomes framework, that mostly have the flavour of statistical models. To fill this gap, we propose the notion of causal spaces, consisting of a probability space along with a collection of transition probability kernels, called causal kernels, which satisfy two simple axioms and which encode causal information that probability spaces cannot encode. The proposed framework is not only rigorously grounded in measure theory, but it also sheds light on long-standing limitations of existing frameworks including, for example, cycles, latent variables and stochastic processes. Our hope is that causal spaces will play the same role for the theory of causality that probability spaces play for the theory of probabilities.
Bio:
Jun is a postdoctoral researcher in the Statistical Machine Learning Group at ETH Zürich, led by Fanny Yang. He received his PhD last year at the Max Planck Institute for Intelligent Systems, Tübingen, under the supervision of Krikamol Muandet and Bernhard Schölkopf. Previously, he obtained his MSc in Statistics at ETH Zürich under Sara van de Geer, and before that, he received his BA and MMath (Part III) degrees at the University of Cambridge. He is interested in the foundational questions of causality, as well as statistical learning theory.