Weiwei Pan

Failure Modes of Variational Autoencoders and Their Effects on\n Downstream Tasks

2020 · arXiv (Cornell University)

Variational Auto-encoders (VAEs) are deep generative latent variable models\nthat are widely used for a number of downstream tasks. While it has been\ndemonstrated that VAE training can suffer from a number of pathologies,\nexisting literature lacks characterizations …

Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

2018 · arXiv (Cornell University)

As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkable gains in terms of predictive accuracy, characterizing uncertainty over the parameters of …

Discovering User Types: Mapping User Traits by Task-Specific Behaviors in Reinforcement Learning

2023 · arXiv (Cornell University)

When assisting human users in reinforcement learning (RL), we can represent users as RL agents and study key parameters, called \emph{user traits}, to inform intervention design. We study the relationship between user behaviors (policy classes) …