@inproceedings{lu-etal-2017-adagrad,
    title = "Why {ADAGRAD} Fails for Online Topic Modeling",
    author = "Lu, You  and
      Lund, Jeffrey  and
      Boyd-Graber, Jordan",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D17-1046/",
    doi = "10.18653/v1/D17-1046",
    pages = "446--451",
    abstract = "Online 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 during online gradient optimization. However, these two techniques do not work well together. We show that this is because ADAGRAD uses accumulation of previous gradients as the learning rates' denominators. For online topic modeling, the magnitude of gradients is very large. It causes learning rates to shrink very quickly, so the parameters cannot fully converge until the training ends"
}