42 citations · 247 across the 29 of their papers we have counts for
Showing 2017Show all
3 papers · 1 filter
cs.LG2017★ 15 cited
Subsampling for Ridge Regression via Regularized Volume Sampling
Michał Dereziński, Manfred K. Warmuth
Given vectors , we want to fit a linear regression model for noisy labels . The ridge estimator is a classical solution to this…
cs.LG2017★ 23 cited
Unbiased estimates for linear regression via volume sampling
Michał Dereziński, Manfred K. Warmuth
Given a full rank matrix with more columns than rows, consider the task of estimating the pseudo inverse based on the pseudo inverse of a sampled subset of columns (of si…
cs.LG2017★ 1 cited
Batch-Expansion Training: An Efficient Optimization Framework
Michał Dereziński, Dhruv Mahajan, S. Sathiya Keerthi +2
We propose Batch-Expansion Training (BET), a framework for running a batch optimizer on a gradually expanding dataset. As opposed to stochastic approaches, batches do not need to b…