Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
Hyunwoo Kim, Junha Lee, Mincheol Choi +2
Deep learning models have become increasingly large and complex, resulting in higher memory consumption and computational demands. Consequently, model loading times and initial inf…
math.PR2025
Scaling Limit of Dependent Random Walk
Jeonghwa Lee
Recently, a generalized Bernoulli process (GBP) was developed as a stationary binary sequence that can have long-range dependence. In this paper, we find the scaling limit of a ran…