On Coresets for Regularized Regression
12. července 2020
Řečníci
Rachit Chhaya
Řečník · 0 sledujících
Supratim Shit
Řečník · 0 sledujících
Anirban Dasgupta
Řečník · 0 sledujících
O prezentaci
We study the effect of norm based regularization on the size of coresets for the regularized regression problems. Specifically, given a matrix 𝐀∈𝐑^n xd with n≫ d and a vector 𝐛∈𝐑 ^ n and λ > 0, we analyze the size of coresets for regularized versions of regression of the form ||Ax-b||_p^r + λ||x||_q^s . It has been shown for the case of ridge regression (p,q,r,s=2) that we can obtain a coreset smaller than the coreset for its unregularized counterpart i.e. least squares regression<cit.>. However we show that when r ≠ s, no coreset for some regularized regression can have size smaller than the optimal coreset of the unregularized version. The well known LASSO problem falls under this category and hence does not allow a coreset smaller than the one for least squares regression. We propose a modified version of the LASSO problem and obtain for it a coreset of size smaller than the least square regression. We empirically show that the modified version of LASSO also induces sparsity in solution like the LASSO. We also obtain smaller coresets for ℓ_p-regression with ℓ_p-regularization. We extend our methods to multi response regularized regression. Finally, we empirically demonstrate the coreset performance for the modified LASSO and the ℓ_1-regression with ℓ_1- regularization.We study the effect of norm based regularization on the size of coresets for the regularized regression problems. Specifically, given a matrix 𝐀∈𝐑^n xd with n≫ d and a vector 𝐛∈𝐑 ^ n and λ > 0, we analyze the size of coresets for regularized versions of regression of the form ||Ax-b||_p^r + λ||x||_q^s . It has been shown for the case of ridge regression (p,q,r,s=2) that we can obtain a coreset smaller than the coreset for its unregularized counterpart i.e. least squares regression<cit…
Kategorie
Leadership a management
Kategorie · 805 prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
On Variational Learning of Controllable Representations for Text without Supervision
Zhlédnout později
Peng Xu, …
A Free-Energy Principle for Representation Learning
Zhlédnout později
Yansong Gao, …
Poster session 4
Zhlédnout později
Cost-effectively Identifying Causal Effect When Only Response Variable Observable
Zhlédnout později
Research mentoring hour + MC
Zhlédnout později
Pedro Braga, …