COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Statistics > Minimum L1-norm interpolators: Precise asymptotics and multiple descent
Minimum L1-norm interpolators: Precise asymptotics and multiple descentAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Qingyuan Zhao. An evolving line of machine learning works observe empirical evidence that suggests interpolating estimators— We observe, and provide rigorous theoretical justification for, a curious multi-descent phenomenon; that is, the generalization risk of the minimum L1-norm interpolator undergoes multiple (and possibly more than two) phases of descent and ascent as one increases the model capacity. This phenomenon stems from the special structure of the minimum L1-norm interpolator as well as the delicate interplay between the over-parameterized ratio and the sparsity, thus unveiling a fundamental distinction in geometry from the minimum L2-norm interpolator. Our finding is built upon an exact characterization of the risk behavior, which is governed by a system of two non-linear equations with two unknowns. This talk is part of the Statistics series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsGraduate Union talks PDN Talks Quastel Midgen LLP PresentationOther talksHost Age-dependent Evolution of a Plant RNA Virus Understanding Myc Transcription ‘The decolonisation of African states. Taxation and expenditure in former French Africa, 1900-2020’ Designing the BEARS (Both Ears) Virtual Reality Training Package to Improve Spatial Hearing in Young People with Bilateral Cochlear Implant Multivalency and Selective Binding Uniqueness of shock waves under small perturbations for the Isentropic Euler Equations |