Nicholas Carl Roberts — accepted AI-conference papers

2022

Universalizing Weak Supervision

Changho Shin, Winfred Li, Harit Vishwakarma, Nicholas Carl Roberts, Frederic Sala

ICLR 2022poster

Weak supervision (WS) frameworks are a popular way to bypass hand-labeling large datasets for training data-hungry models. These approaches synthesize multiple noisy but cheaply-acquired estimates of labels into a set of high-quality pseudo-labels for downstream training. However, the synthesis tech…

Cited by 43 Source ↗PDF ↗Scholar ↗

2021

Rethinking Neural Operations for Diverse Tasks

Nicholas Carl Roberts, Mikhail Khodak, Tri Dao, Liam Li, Christopher Re, Ameet Talwalkar

NeurIPS 2021poster

An important goal of AutoML is to automate-away the design of neural networks on new tasks in under-explored domains. Motivated by this goal, we study the problem of enabling users to discover the right neural operations given data from their specific domain. We introduce a search space of operation…

Cited by 32 Source ↗PDF ↗Scholar ↗