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:20251124T121500
DTEND;TZID=Europe/Helsinki:20251124T133000
DTSTAMP:20260710T163439
CREATED:20251117T063312Z
LAST-MODIFIED:20251117T063312Z
UID:18565-1763986500-1763991000@crest.science
SUMMARY:Ivan SHCHAPOV (CREST) "Monetary Tightening\, Quantitative Easing\, and Financial Stability"
DESCRIPTION:[vc_row][vc_column][vc_column_text]Macro seminar\nTime : 12h15 – 13h30 \nDate : 24 th  November 2025 \nRoom 3001 \nIvan SHCHAPOV (CREST) “Monetary Tightening\, Quantitative Easing\, and Financial Stability” \nAbstract: This paper analyses the effects of central bank balance sheet policies on financial and price stability in a framework with endogenous disruptions in financial intermediation. Central bank balance sheet expansions increase the frequency of financial stress episodes and their duration by inducing financial intermediaries to take on more risk in normal times and slowing their recapitalisation during a stress episode. Rapid monetary policy tightening induces financial stress that can be mitigated by central bank balance sheet expansions at significant cost to price stability. The optimal monetary policy mix balances the welfare costs of inflation and financial stress with the efficiency costs of balance sheet expansions. Optimal policy leans towards prevention of financial stress via accommodative conventional policy and limited balance sheet interventions. \nOrganizer : Suzanne BELLUE \n
URL:https://crest.science/event/ivan-shchapov-crest-monetary-tightening-quantitative-easing-and-financial-stability/
CATEGORIES:Macroeconomics,Seminars
ATTACH;FMTTYPE=:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20251124T140000
DTEND;TZID=Europe/Helsinki:20251124T153000
DTSTAMP:20260710T163439
CREATED:20251118T084834Z
LAST-MODIFIED:20251118T084834Z
UID:18574-1763992800-1763998200@crest.science
SUMMARY:Arthur STEPHANOVITCH (CREST) -  Regularity of the score and convergence rates of generative diffusion models
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:00 pm\nDate: 24th November\nPlace: 3001 \n  \nArthur STEPHANOVITCH (CREST) – Regularity of the score and convergence rates of generative diffusion models \n  \n  \n  \n  \n Abstract:  \nWe show that in generative modeling with diffusion processes\, the score function naturally inherits the regularity of the target distribution. This adaptive behavior provides a concise proof that these models attain minimax optimal rates for density estimation. \n  \n  \n  \n  \n  \nOrganizers: \nAnna KORBA (CREST)\, Vincent DIVOL (CREST)\, Jaouad MOURTADA (CREST) \nSponsors:\nCREST \n
URL:https://crest.science/event/arthur-stephanovitch-crest-regularity-of-the-score-and-convergence-rates-of-generative-diffusion-models/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20251124T140000
DTEND;TZID=Europe/Helsinki:20251124T150000
DTSTAMP:20260710T163439
CREATED:20251126T073831Z
LAST-MODIFIED:20251126T073843Z
UID:18575-1763992800-1763996400@crest.science
SUMMARY:Antonio OCELLO (CREST)  "Convergence Analysis of Diffusion Models: Towards Reliable Sampling"
DESCRIPTION:Statistics\nTime: 2.00 p.m.\nDate: 24th November 2025\nRoom 3001 \nAntonio OCELLO (Ecole Polytechnique) “Convergence Analysis of Diffusion Models: Towards Reliable Sampling” \nAbstract : \nGenerative models are attracting growing attention across various applied domains\, including insurance and finance. Their potential lies in their capacity to capture and reproduce complex data patterns\, crucial for realistic modeling and decision-making under uncertainty. Among the available methods\, Score-Based Generative Models (SGMs)\, also known as diffusion models\, offer a flexible framework to sample from complex\, high-dimensional distributions. However\, a key challenge lies in rigorously understanding their convergence. \nIn this talk\, I will present recent advances in the theoretical analysis of SGMs. First\, I will provide explicit bounds on Wasserstein-2 distance under the log-concave assumption of the target data distribution. Second\, I will generalize this bound beyond the log-concave settings—such as for mixtures of Gaussians. \nThis talk is based on joint work with Stanislas Strasman\, Claire Boyer\, Sylvain Le Corff\, and Vincent Lemaire (TMLR 2024 – https://openreview.net/forum?id=BlYIPa0Fx1)\, as well as a recent collaboration with Marta Gentiloni-Silveri (ICML 2025 – https://arxiv.org/pdf/2501.02298). \n  \nOrganizers:  Jaouad MOURTADA\, Anna KORBA\, Vincent DIVOL \n  \n
URL:https://crest.science/event/antonio-ocello-ecole-polytechnique-convergence-analysis-of-diffusion-models-towards-reliable-sampling-2/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR