BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//IFDS - ECPv6.0.1.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ifds.info
X-WR-CALDESC:Events for IFDS
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20210314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20211107T090000
END:STANDARD
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20210314T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20211107T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20210409T133000
DTEND;TZID=America/Los_Angeles:20210409T143000
DTSTAMP:20260525T072119
CREATED:20210412T183054Z
LAST-MODIFIED:20210412T183353Z
UID:1140-1617975000-1617978600@ifds.info
SUMMARY:ML-Opt: Krishna Pillutla
DESCRIPTION:Title: Distributionally Robust Machine Learning with the Superquantile 1) For Supervised Learning\, 2) For Federated Learning\n\n\nAbstract: I will talk about distributionally robust machine learning\, a principled approach for robust performance across subpopulations\, and shifting distributions. We will focus on the superquantile\, a.k.a. the Conditional Value at Risk (CVaR)\, which was popularized by the seminal work of UW’s own R. T. Rockafellar and co-authors in the field of computational finance and economics in the early 2000s.\nWe will first review the use of the superquantile for distributionally robust supervised learning. We will prove a generalization bound from first principles.\nSecond\, we will discuss an application of the superquantile in the field of federated learning\, i.e.\, the distributed training of machine learning models on mobile phones. We will quantify the extent to which a user conforms to the population distribution and show how the superquantile can be leveraged to improve performance on users who do not conform to the population. We will round of the discussion with a communication-efficient training algorithm and experimental results and heterogeneous datasets.\n\nBio: Krishna Pillutla is a 5th year Ph.D. student at the Paul G. Allen School of Computer Science and Engineering at the University of Washington\, where he is advised by Zaid Harchaoui and Sham Kakade. Krishna is broadly interested in machine learning and optimization and works in the particular areas of structured prediction and federated learning. Krishna was a 2019-20 JP Morgan Ph.D. Fellow.
URL:https://ifds.info/event/ml-opt-krishna-pillutla/
CATEGORIES:MLOpt@UWash
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20210312T133000
DTEND;TZID=America/Chicago:20210312T143000
DTSTAMP:20260525T072119
CREATED:20210115T203442Z
LAST-MODIFIED:20210115T203442Z
UID:896-1615555800-1615559400@ifds.info
SUMMARY:ML-Opt @ UWash: Vincent Roulet
DESCRIPTION:Title: Global convergence of first-order methods for nonlinear control problems \nAbstract:
URL:https://ifds.info/event/ml-opt-uwash-vincent-roulet/
CATEGORIES:MLOpt@UWash
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20210226T133000
DTEND;TZID=America/Los_Angeles:20210226T143000
DTSTAMP:20260525T072119
CREATED:20210115T203300Z
LAST-MODIFIED:20220325T193610Z
UID:894-1614346200-1614349800@ifds.info
SUMMARY:ML-Opt @ UWash: Andrew Wagenmaker
DESCRIPTION:Title:\n\nAbstract:
URL:https://ifds.info/event/ml-opt-uwash-andrew-wagenmaker/
CATEGORIES:MLOpt@UWash
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20210219T133000
DTEND;TZID=America/Chicago:20210219T143000
DTSTAMP:20260525T072119
CREATED:20210115T203136Z
LAST-MODIFIED:20210115T203136Z
UID:892-1613741400-1613745000@ifds.info
SUMMARY:ML-Opt @ UWash: Omid Sadeghi
DESCRIPTION:Title: \nAbstract:
URL:https://ifds.info/event/ml-opt-uwash-omid-sadeghi/
CATEGORIES:MLOpt@UWash
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20210212T133000
DTEND;TZID=America/Chicago:20210212T143000
DTSTAMP:20260525T072119
CREATED:20210115T202956Z
LAST-MODIFIED:20210212T002315Z
UID:890-1613136600-1613140200@ifds.info
SUMMARY:ML-Opt @ UWash: Postponed-TBD
DESCRIPTION:This talk will be rescheduled for a later date.\nTitle: Convergence of the empirical superquantile for risk-sensitive machine learning \nAbstract:  I’ll present some background in risk-sensitive learning + Theorem 2.1 of  this paper (using ML nomenclature) \n 
URL:https://ifds.info/event/ml-opt-uwash-krishna-pillutla/
CATEGORIES:MLOpt@UWash
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20210129T133000
DTEND;TZID=America/Chicago:20210129T143000
DTSTAMP:20260525T072119
CREATED:20210115T202824Z
LAST-MODIFIED:20210115T202824Z
UID:888-1611927000-1611930600@ifds.info
SUMMARY:ML-Opt @ UWash: Ronak Mehta
DESCRIPTION:Title: \nAbstract: \n 
URL:https://ifds.info/event/ml-opt-uwash-ronak-mehta/
CATEGORIES:MLOpt@UWash
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20210122T133000
DTEND;TZID=America/Los_Angeles:20210122T143000
DTSTAMP:20260525T072119
CREATED:20210115T202625Z
LAST-MODIFIED:20210115T202625Z
UID:886-1611322200-1611325800@ifds.info
SUMMARY:ML-Opt @ UWash: Lang Liu
DESCRIPTION:Title: \nAbstract:
URL:https://ifds.info/event/ml-opt-uwash-lang-liu/
CATEGORIES:MLOpt@UWash
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20210115T133000
DTEND;TZID=America/Los_Angeles:20210115T143000
DTSTAMP:20260525T072119
CREATED:20210115T201953Z
LAST-MODIFIED:20210115T205423Z
UID:882-1610717400-1610721000@ifds.info
SUMMARY:ML-Opt @ U Washington: Yue Yu
DESCRIPTION:Title: Proportional-integral projected gradient method for model predictive control \nAbstract: \n 
URL:https://ifds.info/event/ml-opt-u-washington-yue-yu/
CATEGORIES:MLOpt@UWash
END:VEVENT
END:VCALENDAR