no code implementations • 18 Mar 2024 • Yewon Byun, Dylan Sam, Michael Oberst, Zachary C. Lipton, Bryan Wilder
A fundamental problem in decision-making systems is the presence of inequity across demographic lines.
no code implementations • 20 Feb 2024 • Dylan Sam, Rattana Pukdee, Daniel P. Jeong, Yewon Byun, J. Zico Kolter
Bayesian neural networks (BNNs) have recently gained popularity due to their ability to quantify model uncertainty.
no code implementations • 6 Oct 2023 • Victor Akinwande, Yiding Jiang, Dylan Sam, J. Zico Kolter
Zero-shot learning in prompted vision-language models, the practice of crafting prompts to build classifiers without an explicit training process, has achieved impressive performance in many settings.
no code implementations • NeurIPS 2023 • Rattana Pukdee, Dylan Sam, J. Zico Kolter, Maria-Florina Balcan, Pradeep Ravikumar
In this paper, we formalize this notion as learning from explanation constraints and provide a learning theoretic framework to analyze how such explanations can improve the learning of our models.
no code implementations • 16 Dec 2022 • Dylan Sam, Min Bai, Tristan McKinney, Li Erran Li
Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision.
1 code implementation • 13 Dec 2022 • Dylan Sam, J. Zico Kolter
Owing to the prohibitive costs of generating large amounts of labeled data, programmatic weak supervision is a growing paradigm within machine learning.
1 code implementation • 7 Oct 2022 • Rattana Pukdee, Dylan Sam, Maria-Florina Balcan, Pradeep Ravikumar
Semi-supervised learning and weakly supervised learning are important paradigms that aim to reduce the growing demand for labeled data in current machine learning applications.