Events Search and Views Navigation

Event Views Navigation

Today

  • 1/27/2021 New Tech in Math Seminar

    Knowledge graph representation: From recent models towards a theoretical understanding

    Speaker: Carl Allen and Ivana Balažević - University of Edinburgh School of Informatics Title: Knowledge graph representation: From recent models towards a theoretical understanding Abstract: Knowledge graphs (KGs), or knowledge bases, are large repositories of facts in the form of triples (subject, relation, object), e.g. (Edinburgh, capital_of, Scotland). Many models have been developed to succinctly represent KGs […]

  • 2/10/2021 New Tech in Math

    A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks

    https://youtu.be/OoimTbnSe7I Speaker: Nikunj Saunshi, Dept. of Computer Science, Princeton University Title: A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks Abstract: Autoregressive language models pretrained on large corpora have been successful at solving downstream tasks, even with zero-shot usage. However, there is little theoretical justification for their success. This paper considers the following […]

  • 2/16/2021 Computer Science for Mathematicians

    Virtual

    Speaker: Michael P. Kim (UC Berkeley) Title: Outcome Indistinguishability Abstract: Prediction algorithms assign numbers to individuals that are popularly understood as individual “probabilities” — e.g., what is the probability of 5-year survival after cancer diagnosis? — and which increasingly form the basis for life-altering decisions. The understanding of individual probabilities in the context of such unrepeatable events […]