← Search

Alexander I. Rudnicky

2 accepted papers

2022

Training Discrete Deep Generative Models via Gapped Straight-Through Estimator

ICML 2022spotlight

While deep generative models have succeeded in image processing, natural language processing, and reinforcement learning, training that involves discrete random variables remains challenging due to the high variance of its gradient estimation process. Monte Carlo is a common solution used in most va…

2016

Unsupervised user intent modeling by feature-enriched matrix factorization

ICASSP 2016accepted

Spoken language interfaces are being incorporated into various devices such as smart phones and TVs. However, dialogue systems may fail to respond correctly when users' request functionality is not supported by currently installed apps. This paper proposes a feature-enriched matrix factorization (MF…

Cited by 0SourceScholar