Compressed Least-Squares Regression

117 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Sharp analysis of low-rank kernel matrix approximations (2012, neutral): “…increases, the decay of the relative prediction error is much faster than the error in matrix approximation, suggesting that relying on good kernel matrix approximation may be suboptimal if the goal is simply to predict well. for linear prediction problems (Mahoney, 2011; Maillard and Munos, 2009).”
TRAK: Attributing Model Behavior at Scale (2023, unknown): “…we can view our approach of first projecting features to a lower dimension and then performing linear regression in the compressed feature space, as an instance of compressed linear regression (Maillard & Munos, 2009) and also related to principal components regression (Thanei et al., 2017).”
Statistical linear estimation with penalized estimators: an application to reinforcement learning (2012, background): “For a discussion of when to expect a milder dependence of the norm of φ on d, the interested reader may consult the paper by Maillard and Munos (2009).”
Sketch-Based Linear Value Function Approximation (2012, methodology): “Lemma 2 (Based on Maillard and Munos [16], Proposition 1) .”