Convex Regression with Interpretable Sharp Partitions
نویسندگان
چکیده
We consider the problem of predicting an outcome variable on the basis of a small number of covariates, using an interpretable yet non-additive model. We propose convex regression with interpretable sharp partitions (CRISP) for this task. CRISP partitions the covariate space into blocks in a data-adaptive way, and fits a mean model within each block. Unlike other partitioning methods, CRISP is fit using a non-greedy approach by solving a convex optimization problem, resulting in low-variance fits. We explore the properties of CRISP, and evaluate its performance in a simulation study and on a housing price data set.
منابع مشابه
Maximum-Variance Total Variation Denoising for Interpretable Spatial Smoothing
We consider the problem of spatial regression where interpretability of the model is a high priority. Such problems appear frequently in a diverse set of fields from climatology to epidemiology to predictive policing. For cognitive, logistical, and organizational reasons, humans tend to infer regions or neighborhoods of constant value, often with sharp discontinuities between regions, and then ...
متن کاملHinging Hyperplane Models for Multiple Predicted Variables
Model-based learning for predicting continuous values involves building an explicit generalization of the training data. Simple linear regression and piecewise linear regression techniques are well suited for this task, because, unlike neural networks, they yield an interpretable model. The hinging hyperplane approach is a nonlinear learning technique which computes a continuous model. It consi...
متن کاملGraphs, Ags and Partitions
This paper deenes, for each graph G, a ag vector fG. The ag vectors of the graphs on n vertices span a space whose dimension is p(n), the number of partitions on n. The analogy with convex polytopes indicates that the linear inequalities satissed by fG may be both interesting and accessible. Such would provide inequalities both sharp and subtle on the combinatorial structure of G. These may be ...
متن کاملGraphs, flags and partitions
This paper defines, for each graph G, a flag vector fG. The flag vectors of the graphs on n vertices span a space whose dimension is p(n), the number of partitions on n. The analogy with convex polytopes indicates that the linear inequalities satisfied by fG may be both interesting and accessible. Such would provide inequalities both sharp and subtle on the combinatorial structure of G. These m...
متن کاملInterpretable Low-Dimensional Regression via Data-Adaptive Smoothing
We consider the problem of estimating a regression function in the common situation where the number of features is small, where interpretability of the model is a high priority, and where simple linear or additive models fail to provide adequate performance. To address this problem, we present GapTV, an approach that is conceptually related both to CART and to the more recent CRISP algorithm (...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Journal of machine learning research : JMLR
دوره 17 شماره
صفحات -
تاریخ انتشار 2016