Events

  1. Events
  2. Statistics

Views Navigation

Event Views Navigation

Today
Notice: Utilizing the form controls will dynamically update the content

Lorenzo ROSASCO (Università di Genova & MIT) – “Interpolation and learning with scale dependent kernels “

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 8th of November 2021 Place: visio Lorenzo ROSASCO (Università di Genova & MIT) - "Interpolation and learning with scale dependent kernels" Abstract: We study the learning properties of nonparametric ridge-less least squares. In particular, we consider the common case of estimators defined […]

Daniel HSU (Columbia University) – “Computational Lower Bounds for Tensor PCA”

Statistical Seminar: Every Monday at 2:00 pm. Time: 3:00 pm - 4:15 pm exceptionally Date: 15th of November 2021 Place: visio Daniel HSU (Columbia University) - "Computational Lower Bounds for Tensor PCA " Abstract: Tensor PCA is a model statistical inference problem introduced by Montanari and Richard in 2014 for studying method-of-moments approaches to parameter estimation […]

Julie JOSSE (INRIA) – “Causal effect on a target population: a sensitivity analysis to handle missing covariates “

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 29th of November 2021 Place: visio Julie JOSSE (INRIA) - "Causal effect on a target population: a sensitivity analysis to handle missing covariates" Abstract: Randomized controlled trials (RCTs) are considered the gold standard approach for assessing the causal effect of an intervention […]

Yihong Wu (Yale University) – “Self-regularizing Property of Nonparametric Maximum Likelihood Estimator in Mixture Models”

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 31th of January 2022 Place: en visio Yihong Wu (Yale University) - "Self-regularizing Property of Nonparametric Maximum Likelihood Estimator in Mixture Models" Abstract: Introduced by Kiefer and Wolfowitz 1956, the nonparametric maximum likelihood estimator (NPMLE) is a widely used methodology for learning […]

Francis BACH (INRIA & ENS) – “Statistics, Machine Learning, and Optimization with Kernel Sums-of-Squares”

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 14th of February 2022 Place: salle 3001 Francis BACH (INRIA & ENS) - "Statistics, Machine Learning, and Optimization with Kernel Sums-of-Squares" Abstract: In this talk, I will present recent work on representing non-negative functions with infinite-dimensional sums of squares, with applications to […]

Tim Cannings (University of Edinburgh) – “Adaptive transfer learning”

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 14th of March 2022 Place: salle 3001 Tim Cannings (University of Edinburgh) - "Adaptive transfer learning" Abstract: In transfer learning, we wish to make inference about a target population when we have access to data both from the distribution itself, and from […]

Julien CHHOR et Flore SENTENAC (ENSAE-CREST) – “Robust estimation of discrete distributions under local differential privacy “

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 28th of March 2022 Place: Amphi 200 Julien CHHOR et Flore SENTENAC (ENSAE-CREST) - "Robust estimation of discrete distributions under local differential privacy" Abstract: Although robust learning and local differential privacy are both widely studied fields of research, combining the two settings […]

Mohamed (Simo) NDAOUD (ESSEC-CREST) – “Variable selection, monotone likelihood ratio and group sparsity “

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 4th of April 2022 Place: Amphi 200 Mohamed (Simo) NDAOUD (ESSEC-CREST) - "Variable selection, monotone likelihood ratio and group sparsity " Abstract: In the pivotal variable selection problem, we derive the ex- act non-asymptotic minimax selector over the class of all s-sparse […]

Guillaume LECUÉ (CREST) – “A geometrical viewpoint on the benign overfitting property of the minimum l_2-norm interpolant estimator “

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 2nd of May 2022 Place: salle 3001 Guillaume LECUÉ (CREST) - "A geometrical viewpoint on the benign overfitting property of the minimum l_2-norm interpolant estimator" Abstract: Practitioners have observed that some deep learning models generalize well even with a perfect fit to […]

Philippe Rigollet (MIT) – “Variational inference via Wasserstein gradient flows”

Statistical Seminar: Every Monday at 2:00 pm. Time: 2:00 pm - 3:15 pm Date: 9th of May 2022 Place: Amphi 200 Philippe RIGOLLET (MIT) - "Variational inference via Wasserstein gradient flows" Abstract: Bayesian methodology typically generates a high-dimensional posterior distribution that is known only up to normalizing constants, making the computation even of simple summary statistics […]