4 papers
Quantile Randomized Kaczmarz for Streaming Linear Systems with Massart Noise
Emeric Battaglia, Jian-Feng Cai, Junren Chen +3
Quantile randomized Kaczmarz (QRK) has proven to be an efficient solver for corrupted linear systems and has received much attention. It was recently shown by Cai et al. (SIAM J. M…
Complex Stochastic Gradient Descent and Directional Bias in Reproducing Kernel Hilbert Spaces
Natanael Alpay, Emeric Battaglia
Stochastic Gradient Descent (SGD) is a known stochastic iterative method popular for large-scale convex optimization problems due to its simple implementation and scalability. Some…
Quantile-RK and Double Quantile-RK Error Horizon Analysis
Emeric Battaglia, Anna Ma
In solving linear systems of equations of the form , corruptions present in affect stochastic iterative algorithms' ability to reach the true solution to the unc…
Reverse Quantile-RK and its Application to Quantile-RK
Emeric Battaglia, Anna Ma
When solving linear systems , and are given, but the measurements often contain corruptions. Inspired by recent work on the quantile-randomized Kaczmarz method, w…