Automated AI classifiers should be able to defer the prediction to a hum...
We study the application of large language models to zero-shot and few-s...
Existing weak supervision approaches use all the data covered by weak si...
We show that large language models, such as GPT-3, perform well at zero-...
We demonstrate that co-training (Blum Mitchell, 1998) can improve th...
Label-scarce, high-dimensional domains such as healthcare present a chal...
Deep learning has proven effective for various application tasks, but it...
Several works have shown that perturbation stable instances of the MAP
i...
Labeling training examples at scale is a perennial challenge in machine
...
We prove that the alpha-expansion algorithm for MAP inference always ret...
We propose a statistical adaptive procedure called SALSA for automatical...
The use of momentum in stochastic gradient methods has become a widespre...
Despite the development of numerous adaptive optimizers, tuning the lear...
To understand the empirical success of approximate MAP inference, recent...
Approximate algorithms for structured prediction problems---such as the
...