author
Co-Founder & Head of Research
,
Snorkel AI
Paroma Varma is the co-founder and head of solutions at Snorkel AI, and earned her doctorate in electrical engineering from Stanford University. Her research focused on democratizing machine learning for domain experts who lack access to large datasets necessary for training intricate models, thus making complex AI technologies more accessible and impactful for a broader audience. She applied these methods in diverse fields such as medical imaging and autonomous driving.
The latest from Paroma
Multi-Resolution Weak Supervision for Sequential Data
Proposing Dugong, the first framework to model multi-resolution weak supervision sources with complex correlations to assign probabilistic labels to training data.
Research Paper
Multi-Resolution Weak Supervision for Sequential Data
Proposing Dugong, the first framework to model multi-resolution weak supervision sources with complex correlations to assign probabilistic labels to training data.
Learning Dependency Structures for Weak Supervision Models
This work focuses on a robust PCA-based algorithm for learning these dependency structures, establish improved theoretical recovery rates, and outperform existing methods on various real world tasks.
Research Paper
Learning Dependency Structures for Weak Supervision Models
This work focuses on a robust PCA-based algorithm for learning these dependency structures, establish improved theoretical recovery rates, and outperform existing methods on various real world tasks.
Training Classifiers with Natural Language Explanations
Introducing BabbleLabble, a framework for training classifiers in which an annotator provides a natural language explanation for each labeling decision.
Research Paper
Training Classifiers with Natural Language Explanations
Introducing BabbleLabble, a framework for training classifiers in which an annotator provides a natural language explanation for each labeling decision.
Inferring Generative Model Structure With Static Analysis
Presenting Coral, a paradigm that infers generative model structure, significantly reducing the amount of data required to learn structure.
Research Paper
Inferring Generative Model Structure With Static Analysis
Presenting Coral, a paradigm that infers generative model structure, significantly reducing the amount of data required to learn structure.
Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data
Introducing Socratic learning, a paradigm that uses feedback from a discriminative model to automatically identify latent data subsets in training data.
Research Paper
Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data
Introducing Socratic learning, a paradigm that uses feedback from a discriminative model to automatically identify latent data subsets in training data.
