Errors from each rank-1 step in sequential low-rank learning compound through factors that grow when singular values are close, so early steps deserve more compute.
IHT dies hard: Provable accelerated Iterative Hard Thresholding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We study --both in theory and practice-- the use of momentum motions in classic iterative hard thresholding (IHT) methods. By simply modifying plain IHT, we investigate its convergence behavior on convex optimization criteria with non-convex constraints, under standard assumptions. In diverse scenaria, we observe that acceleration in IHT leads to significant improvements, compared to state of the art projected gradient descent and Frank-Wolfe variants. As a byproduct of our inspection, we study the impact of selecting the momentum parameter: similar to convex settings, two modes of behavior are observed --"rippling" and linear-- depending on the level of momentum.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
One Rank at a Time: Cascading Error Dynamics in Sequential Learning
Errors from each rank-1 step in sequential low-rank learning compound through factors that grow when singular values are close, so early steps deserve more compute.