David Krueger

Uncertainty in Multitask Transfer Learning

2018 · arXiv (Cornell University)

Using variational Bayes neural networks, we develop an algorithm capable of accumulating knowledge into a prior from multiple different tasks. The result is a rich and meaningful prior capable of few-shot learning on new tasks. …

On The Fragility of Learned Reward Functions

2023 · arXiv (Cornell University)

Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and preferences. Prior works on reward learning have mainly focused on …

Black-Box Access is Insufficient for Rigorous AI Audits

2024

External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of access granted to auditors. Recent audits of state-of-the-art AI …

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

2016 · PolyPublie (École Polytechnique de Montréal)

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ensemble, improving generalization. …