• Publications
  • Influence
Adversarial Multi Class Learning under Weak Supervision with Performance Guarantees
TLDR
The learning algorithm provably converges to a model that has minimum empirical risk with respect to an adversarial choice over feasible labelings for a set of unlabeled data, where the feasibility of a labeling is computed through constraints defined by rigorously estimated statistics of the weak supervision sources.
Semi-Supervised Aggregation of Dependent Weak Supervision Sources With Performance Guarantees
We develop a novel method that provides theoretical guarantees for learning from weak labelers without the (mostly unrealistic) assumption that the errors of the weak labelers are independent or come
Automated Data Accountability for Missions in Mars Rover Data
This paper proposes an automated solution system to assist with Real-Time Operations and automatically identify and report on issues with data transfer, archive, and manipulation throughout the