F Bach - Journal of Machine Learning Research, 2017 - jmlr.org
We consider neural networks with a single hidden layer and non-decreasing positively homogeneous activation functions like the rectified linear units. By letting the number of …
X Yin, H Hilafu - Journal of the Royal Statistical Society Series B …, 2015 - academic.oup.com
We propose a new and simple framework for dimension reduction in the large p, small n setting. The framework decomposes the data into pieces, thereby enabling existing …
Single-Index Models are high-dimensional regression problems with planted structure, whereby labels depend on an unknown one-dimensional projection of the input via a …
P Alquier, G Biau - Journal of Machine Learning Research, 2013 - jmlr.org
Let (X, Y) be a random pair taking values in Rp× R. In the so-called single-index model, one has Y= f⋆(θ⋆ TX)+ W, where f⋆ is an unknown univariate measurable function, θ⋆ is an …
We study active learning methods for single index models of the form $ F ({\bm x})= f (⟨{\bm w},{\bm x}⟩) $, where $ f:\mathbb {R}\to\mathbb {R} $ and ${\bx,\bm w}\in\mathbb {R}^ d $. In …
S Chen, R Meka - Conference on Learning Theory, 2020 - proceedings.mlr.press
Polynomial regression is a basic primitive in learning and statistics. In its most basic form the goal is to fit a degree $ d $ polynomial to a response variable $ y $ in terms of an $ n …
R Dudeja, D Hsu - Conference On Learning Theory, 2018 - proceedings.mlr.press
We consider regression problems where the response is a smooth but non-linear function of a $ k $-dimensional projection of $ p $ normally-distributed covariates, contaminated with …
R Parhi, M Unser - SIAM Journal on Mathematical Analysis, 2024 - SIAM
We investigate the distributional extension of the-plane transform in and of related operators. We parameterize the-plane domain as the Cartesian product of the Stiefel manifold of …
We study the power of query access for the task of agnostic learning under the Gaussian distribution. In the agnostic model, no assumptions are made on the labels and the goal is to …