Haitian
Scientific Society Seminar
Series
Saturday February 24, 2024
12:45-2:30
Zoom-Link: https://umassboston.zoom.us/j/94777986513
Unveiling the power of metric learning: from diverse
domains to enhanced optimization
Maryam Bagherian
University of Massachusetts Boston
Abstract: Metric
learning serves as an approach for uncovering hidden structures within
high-dimensional spaces. Through the acquisition of a suitable distance metric,
algorithms reliant on distance measurements can more effectively capture the
inherent structure of data points, resulting in enhanced performance. In
contrast to single metric learning methods, the effectiveness of multi-metric
and geometric metric learning becomes evident in handling intricate data
distributions and diverse data characteristics. These alternative approaches
offer heightened flexibility and interpretability, making them especially
valuable for representation learning in intricate non-linear multi-modal
datasets. In this context, I provide a concise introduction to the concepts of
distance metric learning and introduce methods for extending its applicability
to high-dimensional spaces, graphs and
manifolds.
Bio: Maryam Bagherian
obtained her PhD in Mathematics from the University of South Florida, Tampa, in
2019. She held postdoctoral positions at the University of Michigan-Ann Arbor,
Michigan Institute for Data Science, and Yale University before joining UMass
Boston as an assistant professor in Fall 2023. Her research interests revolve
around optimization in high-dimensional spaces, with applications in physics
and biology.