38 citations · 73 across the 9 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
math.OC2023
Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking
Frederik Kunstner, Victor S. Portella, Mark Schmidt +1
The backtracking line-search is an effective technique to automatically tune the step-size in smooth optimization. It guarantees similar performance to using the theoretically opti…
cs.LG2023★ 5 cited
Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be
Frederik Kunstner, Jacques Chen, Jonathan Wilder Lavington +1
The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoret…