Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Multiplicative learning from observation-prediction ratios
Han Kim, Hyungjoon Soh, Vipul Periwal +1
Additive parameter updates, as used in gradient descent and its adaptive extensions, underpin most modern machine-learning optimization. Yet, such additive schemes often demand num…
cs.LG2025
Variational Garrote for Statistical Physics-based Sparse and Robust Variable Selection
Hyungjoon Soh, Dongha Lee, Vipul Periwal +1
Selecting key variables from high-dimensional data is increasingly important in the era of big data. Sparse regression serves as a powerful tool for this purpose by promoting model…