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:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;VALUE=DATE:20260316
DTEND;VALUE=DATE:20260331
DTSTAMP:20260709T203938
CREATED:20251210T123817Z
LAST-MODIFIED:20260324T072239Z
UID:18644-1773619200-1774915199@crest.science
SUMMARY:Taiji Suzuki (Univ. Tokyo) - Feature learning perspective of deep foundation models: statistical and optimization theories
DESCRIPTION:FEATURE LEARNING PERSPECTIVE OF DEEP FOUNDATION MODELS: STATISTICAL AND OPTIMIZATION THEORIES\nTAIJI SUZUKI\nUniversity of Tokyo\nDepartment of Mathematical Informatics \nSchedule: \nMarch 16\, 2026 | 2PM – 5PM – Room 2005\nMarch 19\, 2026 | 2PM – 5PM – Room 2005\nMarch 26\, 2026 | 2PM – 5PM – Room 2005\nMarch 30\, 2026 | 2PM – 5PM – Room 2005 \nContent:\nThe main focus of this lecture will be on the feature learning aspects of deep foundation models\, especially about the benefit of feature learning to achieve better predictive accuracy and more efficient optimization. As the deep foundation models are developed following the scaling law\, a theoretical understanding of the learning principles behind practice is getting more important. For superior generalization of deep models\, it is essentially important to acquire compressed representations avoiding mere memorization\, making representation/feature learning fundamental. It has been theoretically shown that deep learning gains various advantages in generalization via its feature learning ability which naturally arises from its deep structure. It will be discussed how the feature learning ability affects the rate of convergence by comparing it with the sub-optimal rate of non-feature learning methods. This issue will be discussed not only from statistical  perspective but also from optimization perspective. Interesting examples include estimating a Gaussian single index model in which the computational complexity can be characterized by quantities socalled information exponent and generative exponent. If time permits\, optimization guarantees by mean field Langevin dynamics and its statistical property will also be discussed. Furthermore\, feature learning is significant not only during pre-training but also during test-time inference. This will be demonstrated concisely using in-context learning as an example. It will be discussed how the test time feature learning as well as pre-training feature learning affects the performance of test time inference. In summary\, the following topics will be covered in the lecture (but some of them could be omitted depending on time constraint):\n• Nonparametric function estimation by deep learning on high dimension data and its minimax optimality.\n• Stochastic gradient descent for neural network training; Gaussian single index model\, k-parity problem\, information exponent\, CSQ/SQ lower bound.\n• Mean field Langevin dynamics and its statistical property.\n• Test time inference and test time scaling: Transformer\, in-context learning\, chain-ofthought. \nEvaluation: \nTake home project. \nReferences:\nE. Giné and R. Nickl. Mathematical foundations of infinite-dimensional statistical models. Cambridge Series in Statistical and Probabilistic Mathematics. Cambridge University Press\, 2015.\nS. Hayakawa and T. Suzuki. On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces. Neural Networks\, 123:343–361\, 2020.\nJ. Kim\, T. Nakamaki\, and T. Suzuki. Transformers are minimax optimal nonparametric incontext learners. In Advances in Neural Information Processing Systems\, volume 37\, pages 106667–106713\, 2024.\nJ. D. Lee\, K. Oko\, T. Suzuki\, and D. Wu. Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit. In Advances in Neural Information Processing Systems\, volume 37\, pages 58716–58756\, 2024.\nN. Nishikawa\, Y. Song\, K. Oko\, D. Wu\, and T. Suzuki. Nonlinear transformers can perform inference-time feature learning. In Proceedings of the 42nd International Conference on Machine Learning\, volume 267 of Proceedings of Machine Learning Research\, pages 46554– 46585. PMLR\, 2025.\nA. Nitanda\, D. Wu\, and T. Suzuki. Convex analysis of the mean field Langevin dynamics. In Proceedings of The 25th International Conference on Artificial Intelligence and Statistics\, volume 151 of Proceedings of Machine Learning Research\, pages 9741–9757. PMLR\, 28–30 Mar 2022.\nNitanda\, A. Lee\, D. T. X. Kai\, M. Sakaguchi\, and T. Suzuki. Propagation of chaos for mean-field Langevin dynamics and its application to model ensemble. In Forty-second International Conference on Machine Learning\, 2025.\nK. Oko\, Y. Song\, T. Suzuki\, and D. Wu. Pretrained transformer efficiently learns lowdimensional target functions in-context. In Advances in Neural Information Processing Systems\, volume 37\, pages 77316–77365\, 2024.\nT. Suzuki. Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality. In International Conference on Learning Representations\, 2019.\nT. Suzuki and A. Nitanda. Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space. In Advances in Neural Information Processing Systems\, volume 34\, pages 3609–3621\, 2021. A. B. Tsybakov. \n  \n
URL:https://crest.science/event/taiji-suzuki-univ-tokyo-feature-learning-perspective-of-deep-foundation-models-statistical-and-optimization-theories/
CATEGORIES:Doctoral Courses,Statistics
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20260326T100000
DTEND;TZID=Europe/Helsinki:20260326T110000
DTSTAMP:20260709T203938
CREATED:20260310T092455Z
LAST-MODIFIED:20260310T092611Z
UID:18857-1774519200-1774522800@crest.science
SUMMARY:Juliette SAETRE (Toulouse School of Economics) - "From Frontlines to Home: The Impact of Returning Soldiers’ Testimonies on Public Opinion"
DESCRIPTION:Sociology Seminar \nTime: 10:00 am – 11:00 am\nDate: 26th of March\nRoom : 3049 \nJuliette SAETRE (Toulouse School of Economics) – “From Frontlines to Home: The Impact of Returning Soldiers’ Testimonies on Public Opinion” \nAbstract :  \nA large body of social science research treats political attitudes as settled dispositions\, formed early in life and reinforced through repeated interaction within homogeneous networks. On this account\, meaningful attitudinal change is expected to be rare and gradual. This paper examines a striking breach of this expectation: a rapid shift in Norwegian public opinion toward Israel in the late 1970s\, following decades of stable support. We argue that shifts in mass attitudes can emerge within communities when trusted in-group members return with firsthand information acquired through short-term mobility. Specifically\, we focus on Norwegian UNIFIL peacekeepers returning from Lebanon after 1978 who\, through their direct exposure to the conflict and continued embeddedness in local communities\, transmitted accounts that challenged dominant narratives about Israel’s actions in the region. Combining cross-sectional data on public opinion with original survey data on former veterans\, we leverage geographic variation in returnee intensity to show that counties with greater exposure to returnees experienced sharper declines in pro-Israel sentiment. The effect is strongest in areas where returnees remained socially embedded upon return and were politically aligned with their peers prior to deployment. The findings demonstrate how short-term mobility can drive changes in public opinion by enabling trusted in-group members to introduce new information into otherwise homogeneous environments. \n  \nOrganizers: \nEtienne OLLION (Pôle sociologie CREST)\n \nPaola TUBARO (Pôle sociologie CREST) \nNicolas JULIA (Pôle sociologie CREST) \nPatrick PRÄG (Pôle sociologie CREST) \nSponsors:\nCREST \n
URL:https://crest.science/event/https-www-tse-fr-eu-fr-people-juliette-saetre/
CATEGORIES:Seminars,Sociology
ATTACH;FMTTYPE=:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20260326T110000
DTEND;TZID=Europe/Helsinki:20260326T120000
DTSTAMP:20260709T203938
CREATED:20260323T152314Z
LAST-MODIFIED:20260323T152314Z
UID:18874-1774522800-1774526400@crest.science
SUMMARY:Christoph REISINGER  "Oxford University" t.b.a
DESCRIPTION:Mathematical Finance\nTime: 11.00 am\nDate: 26th of March 2026\nRoom 3001 \nChristoph REISINGER “Oxford University” t.b.a \nAbstract: \nOrganizers:  Roxanna DUMITRESCU – Jean-François CHASSAGNEUX \n  \n
URL:https://crest.science/event/christoph-reisinger-oxford-university-t-b-a/
CATEGORIES:Finance-Insurance,Mathematical Finance,Seminars
ATTACH;FMTTYPE=:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20260326T140000
DTEND;TZID=Europe/Helsinki:20260326T150000
DTSTAMP:20260709T203938
CREATED:20260310T093620Z
LAST-MODIFIED:20260310T093645Z
UID:18858-1774533600-1774537200@crest.science
SUMMARY:Luca CARBONE (KU Leuven) - "A Computational Sociology of Everyday Media Consumption for Youth Identities and Well-Being: Evidence from a Cross-National Daily Diary Study"
DESCRIPTION:Sociology Seminar \nTime: 2:00 pm – 3:00 pm\nDate: 26th of March\nRoom : 3049 \n  \nLuca CARBONE (KU Leuven) – “A Computational Sociology of Everyday Media Consumption for Youth Identities and Well-Being: Evidence from a Cross-National Daily Diary Study” \nAbstract :  \nHow do digitally distributed cultural narratives relate to young people’s everyday cognitions and well-being? In this talk\, I present evidence from a 14-day diary study on music consumption among 695 adolescents across three European countries\, namely Belgium\, France\, and Slovenia. Combining computational annotation of song lyrics with intensive longitudinal survey data\, I measure the exposure to individualistic success narratives in adolescents’ daily favorite songs and examine their associations with daily fluctuations in success-related cognitions and performance pressure. Using fixed-effects multilevel models\, I distinguish stable individual differences from day-to-day variation and assess whether observed relationships reflect exposure-based or selection-based processes. The findings indicate robust between- and within-person associations\, highlighting the self-regulatory and selective dimensions of cultural consumption in algorithmic media environments. Building on this study\, I conclude by outlining a broader computational sociology agenda integrating scalable and multimodal analysis of media content\, intensive longitudinal designs\, and algorithmic auditing to investigate how today’s digital media ecosystems contribute to the reproduction of intersectional inequalities in youth identities and well-being. \n  \nOrganizers: \nEtienne OLLION (Pôle sociologie CREST)\n \nPaola TUBARO (Pôle sociologie CREST) \nNicolas JULIA (Pôle sociologie CREST) \nPatrick PRÄG (Pôle sociologie CREST) \nSponsors:\nCREST \n
URL:https://crest.science/event/luca-carbone-ku-leuven-a-computational-sociology-of-everyday-media-consumption-for-youth-identities-and-well-being-evidence-from-a-cross-national-daily-diary-study/
CATEGORIES:Seminars,Sociology
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR