13 citations · 27 across the 7 of their papers we have counts for
7 papers
Perceptual adjustment queries and an inverted measurement paradigm for low-rank metric learning
Austin Xu, Andrew D. McRae, Jingyan Wang +2
We introduce a new type of query mechanism for collecting human feedback, called the perceptual adjustment query ( PAQ). Being both informative and cognitively lightweight, the PAQ…
Benign landscapes of low-dimensional relaxations for orthogonal synchronization on general graphs
Andrew D. McRae, Nicolas Boumal
Orthogonal group synchronization is the problem of estimating elements from the orthogonal group given some relative measurements $R_{ij} \appro…
New Equivalences Between Interpolation and SVMs: Kernels and Structured Features
Chiraag Kaushik, Andrew D. McRae, Mark A. Davenport +1
The support vector machine (SVM) is a supervised learning algorithm that finds a maximum-margin linear classifier, often after mapping the data to a high-dimensional feature space…
Harmless interpolation in regression and classification with structured features
Andrew D. McRae, Santhosh Karnik, Mark A. Davenport +1
Overparametrized neural networks tend to perfectly fit noisy training data yet generalize well on test data. Inspired by this empirical observation, recent work has sought to under…
Optimal convex lifted sparse phase retrieval and PCA with an atomic matrix norm regularizer
Andrew D. McRae, Justin Romberg, Mark A. Davenport
We present novel analysis and algorithms for solving sparse phase retrieval and sparse principal component analysis (PCA) with convex lifted matrix formulations. The key innovation…
Sample complexity and effective dimension for regression on manifolds
Andrew McRae, Justin Romberg, Mark Davenport
We consider the theory of regression on a manifold using reproducing kernel Hilbert space methods. Manifold models arise in a wide variety of modern machine learning problems, and…
Low-rank matrix completion and denoising under Poisson noise
Andrew D. McRae, Mark A. Davenport
This paper considers the problem of estimating a low-rank matrix from the observation of all or a subset of its entries in the presence of Poisson noise. When we observe all entrie…