BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CMSA
X-ORIGINAL-URL:https://cmsa.fas.harvard.edu
X-WR-CALDESC:Events for CMSA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220303T151100
DTEND;TZID=America/New_York:20220303T161100
DTSTAMP:20240301T104734Z
CREATED:20240215T091737Z
LAST-MODIFIED:20240301T104734Z
UID:10002711-1646320260-1646323860@cmsa.fas.harvard.edu
SUMMARY:Towards Understanding Training Dynamics for Mildly Overparametrized Models
DESCRIPTION:Abstract: While over-parameterization is widely believed to be crucial for the success of optimization for the neural networks\, most existing theories on over-parameterization do not fully explain the reason — they either work in the Neural Tangent Kernel regime where neurons don’t move much\, or require an enormous number of neurons. In this talk I will describe our recent works towards understanding training dynamics that go beyond kernel regimes with only polynomially many neurons (mildly overparametrized). In particular\, we first give a local convergence result for mildly overparametrized two-layer networks. We then analyze the global training dynamics for a related overparametrized tensor model. For both works\, we rely on a key intuition that neurons in overparametrized models work in groups and it’s important to understand the behavior of an average neuron in the group. Based on two works: https://arxiv.org/abs/2102.02410 and https://arxiv.org/abs/2106.06573. \nBio: Professor Rong Ge is Associate Professor of Computer Science at Duke University. He received his Ph.D. from the Computer Science Department of Princeton University\, supervised by Sanjeev Arora. He was a post-doc at Microsoft Research\, New England. In 2019\, he received both a Faculty Early Career Development Award from the National Science Foundation and the prestigious Sloan Research Fellowship. His research interest focus on theoretical computer science and machine learning. Modern machine learning algorithms such as deep learning try to automatically learn useful hidden representations of the data. He is interested in formalizing hidden structures in the data and designing efficient algorithms to find them. His research aims to answer these questions by studying problems that arise in analyzing text\, images\, and other forms of data\, using techniques such as non-convex optimization and tensor decompositions.
URL:https://cmsa.fas.harvard.edu/event/3-3-2022-interdisciplinary-science-seminar/
CATEGORIES:Interdisciplinary Science Seminar
ATTACH;FMTTYPE=image/jpeg:https://cmsa.fas.harvard.edu/media/CMSA-Interdisciplinary-Science-Seminar-03.03.2022-1583x2048-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220310T151300
DTEND;TZID=America/New_York:20220310T161300
DTSTAMP:20240301T104543Z
CREATED:20240215T091511Z
LAST-MODIFIED:20240301T104543Z
UID:10002710-1646925180-1646928780@cmsa.fas.harvard.edu
SUMMARY:Virtual Teams in Gig Economy — An End-to-End Data Science Approach
DESCRIPTION:Abstract: The gig economy provides workers with the benefits of autonomy and flexibility\, but it does so at the expense of work identity and co-worker bonds. Among the many reasons why gig workers leave their platforms\, an unexplored aspect is the organization identity. In a series of studies\, we develop a team formation and inter-team contest at a ride-sharing platform. We employ an end-to-end data science approach\, combining methodologies from randomized field experiments\, recommender systems\, and counterfactual machine learning. Together\, our results show that platform designers can leverage team identity and team contests to increase revenue and worker engagement in a gig economy. \nBio: Wei Ai is an Assistant Professor in the College of Information Studies (iSchool) and the Institute for Advanced Computer Studies (UMIACS) at the University of Maryland. His research interest lies in data science for social good\, where the advances of machine learning and data analysis algorithms translate into measurable impacts on society. He combines machine learning\, causal inference\, and field experiments in his research\, and has rich experience in collaborating with industrial partners. He earned his Ph.D. from the School of Information at the University of Michigan. His research has been published in top journals and conferences\, including PNAS\, ACM TOIS\, WWW\, and ICWSM.
URL:https://cmsa.fas.harvard.edu/event/3-10-2022-interdisciplinary-science-seminar/
CATEGORIES:Interdisciplinary Science Seminar
ATTACH;FMTTYPE=image/jpeg:https://cmsa.fas.harvard.edu/media/CMSA-Interdisciplinary-Science-Seminar-03.10.2022-1583x2048-1-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220317T151500
DTEND;TZID=America/New_York:20220317T161500
DTSTAMP:20240301T104445Z
CREATED:20240215T091301Z
LAST-MODIFIED:20240301T104445Z
UID:10002709-1647530100-1647533700@cmsa.fas.harvard.edu
SUMMARY:On optimization and generalization in deep learning
DESCRIPTION:Abstract: Deep neural networks have achieved significant empirical success in many fields\, including the fields of computer vision and natural language processing. Along with its empirical success\, deep learning has been theoretically shown to be attractive in terms of its expressive power. However\, the theory of expressive power does not ensure that we can efficiently find an optimal solution in terms of optimization and generalization\, during the optimization process. In this talk\, I will discuss some mathematical properties of optimization and generalization for deep neural networks.
URL:https://cmsa.fas.harvard.edu/event/3-17-2022-interdisciplinary-science-seminar/
CATEGORIES:Interdisciplinary Science Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Interdisciplinary-Science-Seminar-03.17.2022-1583x2048-1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220324T151700
DTEND;TZID=America/New_York:20220324T171700
DTSTAMP:20240301T104333Z
CREATED:20240215T091039Z
LAST-MODIFIED:20240301T104333Z
UID:10002708-1648135020-1648142220@cmsa.fas.harvard.edu
SUMMARY:An operadic structure on supermoduli spaces
DESCRIPTION:Abstract: The operadic structure on the moduli spaces of algebraic curves  encodes in a combinatorial way how nodal curves in the boundary can be obtained by glueing smooth curves along marked points. In this talk\, I will present a generalization of the operadic structure to moduli spaces of SUSY curves (or super Riemann surfaces). This requires colored graphs and generalized operads in the sense of Borisov-Manin. Based joint work with Yu. I. Manin and Y. Wu. https://arxiv.org/abs/2202.10321
URL:https://cmsa.fas.harvard.edu/event/3-24-2022-interdisciplinary-science-seminar/
CATEGORIES:Interdisciplinary Science Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Interdisciplinary-Science-Seminar-03.24.2022-1583x2048-1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220331T152000
DTEND;TZID=America/New_York:20220331T172000
DTSTAMP:20240301T103621Z
CREATED:20240214T113726Z
LAST-MODIFIED:20240301T103621Z
UID:10002704-1648740000-1648747200@cmsa.fas.harvard.edu
SUMMARY:Compactification of an embedded vector space and its combinatorics
DESCRIPTION:Abstract: Matroids are combinatorial abstractions of vector spaces embedded in a coordinate space.  Many fundamental questions have been open for these classical objects.  We highlight some recent progress that arise from the interaction between matroid theory and algebraic geometry.  Key objects involve compactifications of embedded vector spaces\, and an exceptional Hirzebruch-Riemann-Roch isomorphism between the K-ring of vector bundles and the cohomology ring of stellahedral varieties.
URL:https://cmsa.fas.harvard.edu/event/3-31-2022-interdisciplinary-science-seminar/
CATEGORIES:Interdisciplinary Science Seminar
ATTACH;FMTTYPE=image/jpeg:https://cmsa.fas.harvard.edu/media/CMSA-Interdisciplinary-Science-Seminar-03.231.2022-1583x2048-1.jpg
END:VEVENT
END:VCALENDAR