Showing 2024Show all
3 papers · 1 filter
eess.SY2024
Action-Attentive Deep Reinforcement Learning for Autonomous Alignment of Beamlines
Siyu Wang, Shengran Dai, Jianhui Jiang +3
Synchrotron radiation sources play a crucial role in fields such as materials science, biology, and chemistry. The beamline, a key subsystem of the synchrotron, modulates and direc…
cs.LG2024
MARS: Unleashing the Power of Variance Reduction for Training Large Models
Huizhuo Yuan, Yifeng Liu, Shuang Wu +2
Training deep neural networks--and more recently, large models demands efficient and scalable optimizers. Adaptive gradient algorithms like Adam, AdamW, and their variants have bee…
cs.LG2024
Graph Neural Thompson Sampling
Shuang Wu, Arash A. Amini
We consider an online decision-making problem with a reward function defined over graph-structured data. We formally formulate the problem as an instance of graph action bandit. We…