16 citations · 47 across the 11 of their papers we have counts for
11 papers
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
Jialin Mao, Itay Griniasty, Han Kheng Teoh +5
We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training. By examining the underlying high-dimensional probabilis…
A picture of the space of typical learnable tasks
Rahul Ramesh, Jialin Mao, Itay Griniasty +5
We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-superv…
The Value of Out-of-Distribution Data
Ashwin De Silva, Rahul Ramesh, Carey E. Priebe +2
We expect the generalization error to improve with more samples from a similar task, and to deteriorate with more samples from an out-of-distribution (OOD) task. In this work, we s…
Deep Reference Priors: What is the best way to pretrain a model?
Yansong Gao, Rahul Ramesh, Pratik Chaudhari
What is the best way to exploit extra data -- be it unlabeled data from the same task, or labeled data from a related task -- to learn a given task? This paper formalizes the quest…
Prospective Learning: Principled Extrapolation to the Future
Ashwin De Silva, Rahul Ramesh, Lyle Ungar +40
Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the…
Model Zoo: A Growing "Brain" That Learns Continually
Rahul Ramesh, Pratik Chaudhari
This paper argues that continual learning methods can benefit by splitting the capacity of the learner across multiple models. We use statistical learning theory and experimental a…