4 papers
Flatness-Aware Stochastic Gradient Langevin Dynamics
Stefano Bruno, Youngsik Hwang, Jaehyeon An +2
Flatness of the loss landscape has been widely studied as an important perspective for understanding the behavior and generalization of deep learning algorithms. Motivated by this…
Controllable Machine Unlearning via Gradient Pivoting
Youngsik Hwang, Dong-Young Lim
Machine unlearning (MU) aims to remove the influence of specific data from a trained model. However, approximate unlearning methods, often formulated as a single-objective optimiza…
DGSAM: Domain Generalization via Individual Sharpness-Aware Minimization
Youngjun Song, Youngsik Hwang, Jonghun Lee +2
Domain generalization (DG) aims to learn models that perform well on unseen target domains by training on multiple source domains. Sharpness-Aware Minimization (SAM), known for fin…
Dual Cone Gradient Descent for Training Physics-Informed Neural Networks
Youngsik Hwang, Dong-Young Lim
Physics-informed neural networks (PINNs) have emerged as a prominent approach for solving partial differential equations (PDEs) by minimizing a combined loss function that incorpor…