Quantile-based Loss Filtering for Outlier-Robust Stochastic Gradient Descent
Quantile-k-Loss SGD filters corrupted component losses by quantile sampling, proving linear convergence while outperforming standard and min-k-loss SGD.
1 stories, newest first · one card per story
Quantile-k-Loss SGD filters corrupted component losses by quantile sampling, proving linear convergence while outperforming standard and min-k-loss SGD.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views