method ID: adagrad

Related Papers

A Comparison of Update Strategies for Large-Scale Maximum Expected BLEU Training

Authors: nan

Publication: TIPSTER (2015)

DOI: nan

This work presents a flexible and efficient discriminative training approach for statisti- cal machine translation. We propose to use the RPROP algorithm for optimizing a max- imum expected BLEU objective …...

23046

Why ADAGRAD Fails for Online Topic Modeling

Authors: nan

Publication: TIPSTER (2017)

DOI: nan

AbstractOnline topic modeling, i.e., topic modeling with stochastic variational inference, is a powerful and efficient technique for analyzing large datasets, and ADAGRAD is a widely-used technique for tuning learning rates …...

33073