13 citations · 23 across the 12 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023
Mini-batch -means terminates within iterations
Gregory Schwartzman
We answer the question: "Does local progress (on batches) imply global progress (on the entire dataset) for mini-batch -means?". Specifically, we consider mini-batch -means w…
cs.LG2021
SGD Through the Lens of Kolmogorov Complexity
Gregory Schwartzman
We prove that stochastic gradient descent (SGD) finds a solution that achieves classification accuracy on the entire dataset. We do so under two main assumptions: (1. Local…