IFML Seminar
On the Computational Complexity of Private High-dimensional Model Selection
Abstract: We consider the problem of model selection in a high-dimensional sparse linear regression model under privacy constraints. We propose a differentially private best subset selection method with strong utility properties by adopting the...
Upcoming Events
-
September1312:15 - 1 pm
IFML Seminar
Event DetailsAbstract: We consider the problem of model selection in a high-dimensional sparse linear regression model under privacy constraints. We propose...
-
September2712:15 - 1 pm
IFML Seminar
Event DetailsAbstract: One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates…
-
October412:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Sequential decision-making (SDM) is crucial for adapting machine learning to dynamic real-world scenarios such as fluctuating markets or…
Past Events
-
February113 - 4 pm
ML+ X Seminar
Event DetailsML+X seminar with Joshua Chang, M.D., Ph.D., assistant professor in the Department of Neurology at The University of Texas at...
-
December132 - 3 pm
Ethics/Fairness in AI Seminar
Event DetailsChild maltreatment has become a prevalent problem and draws increasing concerns around the world. According to a recent study, approximately...
-
November22throughNovember26
Workshop
Event DetailsThe resurgence of deep neural networks has led to revolutionary success across almost all the areas in engineering and science...
-
November1912 - 1 pmEvent Details
Abstract: fastMRI is a collaboration project between Facebook AI Research and the NYU School of Medicine with the goal of...
-
November123 - 4 pm
ML+ X Seminar
Event DetailsThe recent artificial intelligence (AI) boom has been primarily driven by three confluence forces: algorithms, big-data, and computing power enabled…
-
November2throughNovember5
Workshop
Event DetailsMembers of the new NSF AI Institute for Foundations of Machine Learning (IFML) will spend a week in residence at...
