2 citations · 5 across the 6 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2021
Solving hybrid machine learning tasks by traversing weight space geodesics
Guruprasad Raghavan, Matt Thomson
Machine learning problems have an intrinsic geometric structure as central objects including a neural network's weight space and the loss function associated with a particular task…
cs.LG2020★ 1 cited
Sparsifying networks by traversing Geodesics
Guruprasad Raghavan, Matt Thomson
The geometry of weight spaces and functional manifolds of neural networks play an important role towards 'understanding' the intricacies of ML. In this paper, we attempt to solve c…
cs.LG2020
Architecture Agnostic Neural Networks
Sabera Talukder, Guruprasad Raghavan, Yisong Yue
In this paper, we explore an alternate method for synthesizing neural network architectures, inspired by the brain's stochastic synaptic pruning. During a person's lifetime, numero…