BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20250929T121500
DTEND;TZID=Europe/Helsinki:20250929T133000
DTSTAMP:20260715T103730
CREATED:20250922T080658Z
LAST-MODIFIED:20250924T061502Z
UID:18366-1759148100-1759152600@crest.science
SUMMARY:Jordan ROULLEAU-PASDELOUP (National University of Singapore) "Clearing Up the Effective Lower Bound Morass"
DESCRIPTION:[vc_row][vc_column][vc_column_text]Macro seminar\nTime : 12h15 – 13h30 \nDate : 29 th  September 2025 \nSalle 3001 \nJordan ROULLEAU-PASDELOUP (National University of Singapore) “Clearing Up the Effective Lower Bound Morass” \nAbstract: Depending on the persistence of the underlying Markov chain shock\, the standard New Keynesian model predicts starkly different conclusions at the Effective Lower Bound (ELB). Using a mildly persistent structural shock to generate the ELB\, Eggertsson (2011) concludes that fiscal policy crowds consumption in. Using multiple equilibria and a highly persistent sunspot shock to generate the ELB Mertens & Ravn (2014) conclude that it crowds consumption out. We clear up this morass by using a truncated Markov chain. In our setup\, the equilibrium is guaranteed to be unique and the effects of fiscal (or any other) policy do not flip qualitatively regardless of the persistence level.” \nJoint work : Haochun Ma (NUS) \nOrganizer : Jean-Baptiste MICHAU \n
URL:https://crest.science/event/jordand-roulleau-pasdeloup-national-university-of-singapore-clearing-up-the-effective-lower-bound-morass/
CATEGORIES:Macroeconomics,Seminars
ATTACH;FMTTYPE=:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20250929T140000
DTEND;TZID=Europe/Helsinki:20250929T153000
DTSTAMP:20260715T103730
CREATED:20250922T072703Z
LAST-MODIFIED:20250922T080312Z
UID:18365-1759154400-1759159800@crest.science
SUMMARY:Pierre MARION (INRIA) - Large Stepsizes Accelerate Gradient Descent for (Regularized) Logistic Regression
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:00 pm\nDate: 29th September\nPlace: 3001 \n  \nPierre MARION (INRIA Paris) – Large Stepsizes Accelerate Gradient Descent for (Regularized) Logistic Regression \n  \n Abstract :  \n  \nDeep learning practitioners usually use large stepsizes when training neural networks. To understand the impact of large stepsizes on training dynamics\, we consider the simplified setting of gradient descent (GD) applied to logistic regression with linearly separable data\, where the stepsize is so large that the loss initially oscillates. We study the training dynamics\, and show convergence and acceleration compared to using stepsizes that satisfy the descent lemma. I will show some key ideas from the proof and\, if time allows\, discuss what happens when adding a regularization term. \n  \n  \n  \nOrganizers: \nAnna KORBA (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/pierre-marion-inria-large-stepsizes-accelerate-gradient-descent-for-regularized-logistic-regression/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR