MMDS大阪大学 数理・データ科学教育研究センター
Center for Mathematical Modeling and Data Science,Osaka University

Sparse Additive Modeling and Misspecified Smoothness

Noah Simon (University of Washington)

大阪大学 数理・データ科学セミナー データ科学セミナーシリーズ 第42回

Sparse Additive Modeling and Misspecified Smoothness

Noah Simon (University of Washington)

Predictive methods must balance 3 objectives: predictive performance, computational tractability, and, in many applications, interpretability. In this talk we will discuss a broad class of models which effectively balance these objectives in high dimensional problems: Sparse additive models induced by combining a structural semi-norm and sparsity penalty. These are more flexible than the standard linear penalized model, but maintain its interpretability and computational tractability. We will show when these penalties can and cannot be combined to induce the desired structure and sparsity. We will give an efficient algorithm for fitting a wide class of these models. And we will give a rate of convergence for this model, which, under some conditions, matches the minimax lower bound.

Asymptotic behavior of these estimators has been primarily studied when the smoothness induced by the penalty matches the smoothness of the true underlying regression function. In this talk we will also give upper bounds on convergence rates when our penalties induce too much smoothness (eg. If we estimate a non-differentiable piecewise constant function with a smoothing spline-based penalty)

講師: Noah Simon (University of Washington)
テーマ: 大阪大学 数理・データ科学セミナー データ科学セミナーシリーズ 第42回
日時: 2019年05月14日(火) 14:40-16:10
場所: 大阪大学豊中キャンパス基礎工学研究科 J棟 J617号室
参加費: 無料
アクセス: 会場までのアクセスは下記URLをご参照ください。
http://www.es.osaka-u.ac.jp/ja/access.html
お問い合せ: 本ウェブサイトの「お問い合せ」のページをご参照ください。