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:20190331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20191027T010000
END:STANDARD
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20190331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20191027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20191202T110000
DTEND;TZID=Europe/Helsinki:20191202T120000
DTSTAMP:20260816T022150
CREATED:20191116T142254Z
LAST-MODIFIED:20210330T063331Z
UID:12358-1575284400-1575288000@crest.science
SUMMARY:Norio Takeoka (Hitotsubashi University) - "Information Acquisition with Subjective Waiting Costs"
DESCRIPTION:CREST Internal Seminar in Microeconomics :  \n\nTime: 11:00 am – 12:00pm\nDate: 02nd Dec. 2019\nPlace: Room 3105.\nNorio Takeoka (Hitotsubashi University) – “Information Acquisition with Subjective Waiting Costs”\n\nAbstract: Information acquisition is an important aspect of decision making. Acquiring information is costly\, as in the literature of rational inattention\, but the cost of information acquisition is not typically observable and hence it is not obvious how it can be measured. Using preference over menus\, de Oliveira\, Denti\, Mihm\, and Ozbek (2017) provide an axiomatic foundation for the additive costs model of information  acquisition. On the other hand\, if obtaining signals from experiments is time-consuming\, such as in the case of a long-run investment decision\, costs may be measured as a discount factor or waiting time for acquiring information. We provide an axiomatic foundation for such an alternative model and identify unique discounting costs. To prove the main theorem\, we borrow techniques from the literature of choice under ambiguity. Our representation has a parallel relationship with the confidence representation of Chateauneuf and Faro (2009). We first show\, as an intermediate lemma\, that our axioms ensure a counterpart of the uncertain averse representation of Cerreia-Vioglio\, Maccheroni\, Marinacci\, and Montrucchio (2011) and then specialize it into the confidence-class representation. \n\nOrganizer: \n\n\nMorgane Guignard (CREST)\nSponsors:\nCREST\n\n
URL:https://crest.science/event/norio-takeoka-hitotsubashi-university-information-acquisition-with-subjective-waiting-costs/
LOCATION:3105
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20191202T140000
DTEND;TZID=Europe/Paris:20191202T151500
DTSTAMP:20260816T022150
CREATED:20191003T073034Z
LAST-MODIFIED:20191003T073034Z
UID:12340-1575295200-1575299700@crest.science
SUMMARY:Henry REEVE (Université de Birmingham) - "Classification with unknown class conditional label noise on non-compact feature spaces "
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 2nd of December 2019\nPlace: Room 3001.\nHenry REEVE (Université de Birmingham) – “Classification with unknown class conditional label noise on non-compact feature spaces“ \nAbstract: We consider the problem of classification in the presence of label noise.　 In the analysis of classification problems it is typically assumed that the train and test distributions are one and the same. In practice\, however\, it is often the case that the labels in the training data have been corrupted with some unknown probability. We shall focus on classification with class conditional label noise in which the labels observed by the learner have been corrupted with some unknown probability which is determined by the true class label.　 \nIn order to obtain finite sample rates\, previous approaches to classification with unknown class conditional label noise have required that the regression function attains its extrema uniformly on sets of positive measure. We consider this problem in the setting of non-compact metric spaces\, where the regression function need not attain its extrema.　 \nIn this setting we determine the minimax optimal learning rates (up to logarithmic factors). The rate displays interesting threshold behaviour: When the regression function approaches its extrema at a sufficient rate\, the optimal learning rates are of the same order as those obtained in the label-noise free setting. If the regression function approaches its extrema more gradually then classification performance necessarily degrades. In addition\, we present an algorithm which attains these rates without prior knowledge of either the distributional parameters or the local density. \nOrganizers:\nCristina BUTUCEA\, Alexandre TSYBAKOV\, Julie JOSSE\, Eric MOULINES\, Mathieu ROSENBAUM\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/henry-reeve/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20191202T160000
DTEND;TZID=Europe/Paris:20191202T173000
DTSTAMP:20260816T022150
CREATED:20191120T092627Z
LAST-MODIFIED:20191120T092627Z
UID:12360-1575302400-1575307800@crest.science
SUMMARY:Pierre LAFORGUE (Télécom Paris)  - "On the Dualization of Operator-Valued Kernel Machines " - Sylvain ARLOT (LMO\, Université Paris-Sud) - "Analysis of some Purely Random Forests"
DESCRIPTION:\nSéminaire Palaisien\nTime: 4:00 pm – 17:30 pm\nDate: 2nd of December 2019\nPlace: Amphi 200.\nPierre LAFORGUE (Télécom Paris) – “On the Dualization of Operator-Valued Kernel Machines ” \nSylvain ARLOT (LMO\, Université Paris-Sud) – “Analysis of some Purely Random Forests”\n \nSponsors:\nUniversité Paris-Saclay/ Institut DATAIA/ Institut Polytechnique de Paris/ CREST\n \n\n
URL:https://crest.science/event/pierre-laforgue-telecom-paris-on-the-dualization-of-operator-valued-kernel-machines-sylvain-arlot-lmo-universite-paris-sud-analysis-of-some-purely-random-forests/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR