19 citations · 19 across the 5 of their papers we have counts for
4 papers · 1 filter
Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale
Sihwan Park, Jihun Yun, SungYub Kim +2
Zeroth-order (ZO) optimization has emerged as a promising alternative to gradient-based backpropagation methods, particularly for black-box optimization and large language model (L…
Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
SungYub Kim, Sihwan Park, Kyungsu Kim +1
Explaining generalizations and preventing over-confident predictions are central goals of studies on the loss landscape of neural networks. Flatness, defined as loss invariability…
Reliable Estimation of Individual Treatment Effect with Causal Information Bottleneck
Sungyub Kim, Yongsu Baek, Sung Ju Hwang +1
Estimating individual level treatment effects (ITE) from observational data is a challenging and important area in causal machine learning and is commonly considered in diverse mis…
Tsallis Reinforcement Learning: A Unified Framework for Maximum Entropy Reinforcement Learning
Kyungjae Lee, Sungyub Kim, Sungbin Lim +2
In this paper, we present a new class of Markov decision processes (MDPs), called Tsallis MDPs, with Tsallis entropy maximization, which generalizes existing maximum entropy reinfo…