104 citations · 374 across the 40 of their papers we have counts for
8 papers · 1 filter
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…
Time-Varying Propensity Score to Bridge the Gap between the Past and Present
Rasool Fakoor, Jonas Mueller, Zachary C. Lipton +2
Real-world deployment of machine learning models is challenging because data evolves over time. While no model can work when data evolves in an arbitrary fashion, if there is some…
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…
A Model for Multi-Agent Heterogeneous Interaction Problems
Christopher D. Hsu, Mulugeta A. Haile, Pratik Chaudhari
We introduce a model for multi-agent interaction problems to understand how a heterogeneous team of agents should organize its resources to tackle a heterogeneous team of attackers…
Beyond mAP: Towards better evaluation of instance segmentation
Rohit Jena, Lukas Zhornyak, Nehal Doiphode +4
Correctness of instance segmentation constitutes counting the number of objects, correctly localizing all predictions and classifying each localized prediction. Average Precision i…
Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity
Shiyun Xu, Zhiqi Bu, Pratik Chaudhari +1
Interpretable machine learning has demonstrated impressive performance while preserving explainability. In particular, neural additive models (NAM) offer the interpretability to th…
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…