Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
Matias D. Cattaneo, Boris Shigida
We analyze gradient descent with Polyak (1964) heavy-ball momentum (HB) whose fixed momentum hyperparameter provides exponential decay of memory. Building on Kovachki…
cs.LG2025
How Memory in Optimization Algorithms Implicitly Modifies the Loss
Matias D. Cattaneo, Boris Shigida
In modern optimization methods used in deep learning, each update depends on the history of previous iterations, often referred to as memory, and this dependence decays fast as the…