Events: Data- och informationsteknik events at Chalmers University of TechnologyWed, 22 Jan 2020 14:54:02 +0100 Machine Learning Seminar<p>Analysen, meeting room, Rännvägen 6B, EDIT trappa D, E och F</p><p>​Large-Scale Regularized Least Squares: A Universal and Statistical Analysis</p><p><br />​<b>Speaker: </b>Ashkan Panahi, Assistant professor, Data Science and AI division, Department of Computer Science and Engineering<br /></p> <p><strong>Abstract:</strong> A problem that has been of recent interest in statistical inference, machine learning and signal processing is that of understanding the asymptotic behavior of regularized least squares solutions under random measurement matrices (or dictionaries). The Least Absolute Shrinkage and Selection Operator (LASSO or least-squares with l1 regularization) is perhaps one of the most interesting examples. In this talk, we review precise expressions for the asymptotic performance of such problems for a number of different cases, in particular when the elements of the dictionary matrix are sampled independently from a Gaussian distribution.  We further mathematically confirm that these expressions remain valid under a milder assumption of sub-Gaussian matrices. In particular, we establish the universality of the asymptotic statistics (e.g., the average quadratic risk) of LASSO with non-Gaussian dictionaries.</p> Philosophy to Ethics to Law to Technology and Back – Thoughts on Current European State Of The Art<p>EC, lecture hall, Hörsalsvägen 11, EDIT trappa C, D och H</p><p>​Welcome to a seminar under the theme: AI ETHICS at Chalmers, with the speaker Gordana Dodig Crnkovic, Professor, Interaction Design division, Department of Computer Science and Engineering at Chalmers and the University of Gothenburg.</p> Augustín Mista, Computer Science and Engineering<p>EA, lecture hall, Hörsalsvägen 11, EDIT trappa C, D och H</p><p>​DRAGEN: Automated Derivation of Random Generators for Algebraic Data Types</p>