Waseem Gharbieh — accepted AI-conference papers

2021

On the Role of Data in PAC-Bayes Bounds

Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Gabriel Arpino, Daniel Roy

AISTATS 2021poster

The dominant term in PAC-Bayes bounds is often the Kullback-Leibler divergence between the posterior and prior. For so-called linear PAC-Bayes risk bounds based on the empirical risk of a fixed posterior kernel, it is possible to minimize the expected value of the bound by choosing the prior to be t…

Cited by 123 Source ↗PDF ↗code ↗Scholar ↗

2021

Query-By-Example Keyword Spotting System Using Multi-Head Attention and Soft-triple Loss

Jinmiao Huang, Waseem Gharbieh, Han Suk Shim, Eugene Kim

ICASSP 2021accepted

This paper proposes a neural network architecture for tackling the query-by-example user-defined keyword spotting task. A multi-head attention module is added on top of a multi-layered GRU for effective feature extraction, and a normalized multi-head attention module is proposed for feature aggregat…

Cited by 0 Source ↗Scholar ↗