Statistical Seminar: Every Monday at 2:00 pm. Time: 4:00 pm - 5:35 pm Date: 22th of March 2023 Place: Room 3001 Simon MAURAS (Université Tel Aviv) - "Truthful Matching with Online Items and Offline Agents" Abstract: Preprint available here: https://arxiv.org/abs/2211.02004 We study truthful mechanisms for welfare maximization in online bipartite matching. In our setting, […]
Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 27th of March 2023 Place: Room 3001 + ZOOM Radu-Alexandru DRAGOMIR (EPFL) - "Optimization method for quartic problems" Abstract: Many tasks in signal processing and learning require minimizing quartic polynomials, such as matrix factorization, phase retrieval and sensor network localization. […]
Statistical Seminar : Time: 5:00 pm - 6:00 pm Date: 30th of March 2023 Place: Room 3001 + ZOOM Dmitrii OVSTROSKI - "Fast and optimal algorithm for online portfolio, and beyond " https://ecolepolytechnique.zoom.us/j/84450260075 Abstract: In his seminal 1991 paper, Thomas M. Cover introduced a simple and elegant mathematical model for stock trading, […]
Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 3th of April 2023 Place: Room 3001 Anru ZHANG (Duke University) - TO BE ANNOUNCED (via Zoom) Abstract: Organizers: Cristina BUTUCEA (CREST), Alexandre TSYBAKOV (CREST), Karim LOUNICI (CMAP) , Jaouad MOURTADA (CREST) Sponsors: CREST-CMAP
Statistical Seminar: Time: 09:45 am - 11:00 am Date: 5th of April 2023 Place: Room 3001 + ZOOM Claire BOYER (Sorbonne Université) - "Is interpolation benign for random forest regression ?" https://zoom.us/j/94418482642?pwd=WGxBcnh2bE5MMEhENTVYQm9sR1NyZz09 Abstract: Statistical wisdom suggests that very complex models, interpolating training data, will be poor at predicting unseen examples.Yet, this aphorism […]
Statistical Seminar: Time: 2:15 pm - 3:15 pm Date: 13th of April 2023 Place: Room 3001 + ZOOM Matus TELGARSKY (Université Illinois, Urbana Champaign) - "Searching for the implicit bias of deep learning" Abstract: What makes deep learning special --- why is it effective in so many settings where other models fail? This […]
Statistical Seminar: Time: 10:30 pm - 11:30 pm Date: 9th of May 2023 Place: Room 3001 + ZOOM Steffen GRÜNEWALDER - Compressed Empirical Measures Abstract: I will discuss some of my recent results on compressing the empirical measure in the context of finite dimensional reproducing kernel Hilbert spaces (RKHSs). The aim is to significantly […]
Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 22th of May 2023 Place: Room 3001 Jordan SERRES (CREST) - "Stein's method for stability estimates of the Poincaré constant" Abstract: The Poincaré inequality governs the exponential convergence rate of algorithms such as Langevin dynamics. Interesting questions are then to understand […]
Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 5th of June 2023 Place: ZOOM Zijian Guo (Rutgers University) - " Doubly Debiased Lasso: High-Dimensional Inference under Hidden Confounding " https://zoom.us/j/95325264336?pwd=QnppNld1c3Y2d01pbmhZR0VMTEkydz09 Abstract: Inferring causal relationships or related associations from observational data can be invalidated by the existence of hidden […]
Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 12th of June 2023 Place: Room 3001 Nikita Zhivotovskiy (UC Berkeley) - “Optimal PAC Bounds without Uniform Convergence” Abstract: In statistical learning theory, the problem of determining sample complexity of realizable binary classification for VC classes was a longstanding challenge. […]
Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:00 pm Date: 18th September 2023 Place: 3001 Andrea CELLI (Bocconi University) - No-Regret Learning in Bilateral Trade via Global Budget Balance Abstract: Bilateral trade revolves around the challenge of facilitating transactions between two strategic agents — a seller and a buyer — […]
Statistical Seminar: Every Monday at 2:00 pm. Time: 3:00 pm - 4:15 pm Date: 18th September 2023 Place: ZOOM Matey NEYKOV (Northwestern University) - Some insights in Nonparametric Conditional Independence Testing Abstract: In this talk we discuss some recent developments in nonparametric conditional independence testing. Specifically if X, Y, Z are three real valued […]