標(biāo)題：On the Core of Causal Reasoning Based on DAG Models
報(bào)告時(shí)間：2024年12月5日（星期四）14：00-15：00
報(bào)告地點(diǎn)：線上騰訊會(huì)議（會(huì)議ID：940-379-287）
主講人：張寄冀
主辦單位：數(shù)學(xué)與統(tǒng)計(jì)學(xué)院
報(bào)告內(nèi)容簡(jiǎn)介：
Directed acyclic graphical (DAG) models are one of the most widely used frameworks for causal modeling. In this talk, we present a category-theoretic treatment of DAG models by associating each DAG with a free Markov category in a canonical way. This framework enables us to study key concepts in causal reasoning from an abstract perspective, including causal independence/separation, causal conditionals, and decomposition of intervention effects. Our results abstract away from the specifics of common causal models such as causal Bayesian networks, making them both more widely applicable and conceptually clearer. Notably, we show that the 'causal core' of the celebrated do-calculus can be unified in a single principle of modularity.
主講人簡(jiǎn)介：
張寄冀本科就讀北京大學(xué)哲學(xué)系，后于卡耐基梅隆大學(xué)哲學(xué)系獲得博士學(xué)位。先后任教于加州理工學(xué)院，香港嶺南大學(xué)，香港浸會(huì)大學(xué)，也曾擔(dān)任華為諾亞方舟人工智能實(shí)驗(yàn)室因果研究組的學(xué)術(shù)顧問(wèn)。現(xiàn)任香港中文大學(xué)哲學(xué)系教授，文學(xué)院副院長(zhǎng)(研究)。 主要研究領(lǐng)域包括科學(xué)哲學(xué)和形式知識(shí)論，同時(shí)從事因果知識(shí)表征和學(xué)習(xí)的跨學(xué)科研究。其成果不僅發(fā)表在哲學(xué)領(lǐng)域的一流期刊, 也發(fā)表在人工智能領(lǐng)域的頂刊和頂會(huì)。多個(gè)研究課題獲香港研究資助局資助，包括人文學(xué)及社會(huì)科學(xué)杰出學(xué)者基金。
