124 citations · 147 across the 12 of their papers we have counts for
3 papers · 1 filter
Adaptive Sketch-and-Project Methods for Solving Linear Systems
Robert Gower, Denali Molitor, Jacob Moorman +1
We present new adaptive sampling rules for the sketch-and-project method for solving linear systems. To deduce our new sampling rules, we first show how the progress of one step of…
Bias of Homotopic Gradient Descent for the Hinge Loss
Denali Molitor, Deanna Needell, Rachel Ward
Gradient descent is a simple and widely used optimization method for machine learning. For homogeneous linear classifiers applied to separable data, gradient descent has been shown…
On Inferences from Completed Data
Jamie Haddock, Denali Molitor, Deanna Needell +3
Matrix completion has become an extremely important technique as data scientists are routinely faced with large, incomplete datasets on which they wish to perform statistical infer…