BibTeX records: Gabriel Pereyra

• > Home > Persons > Gabriel Pereyra

@article{DBLP:journals/corr/abs-2212-12017,
  author       = {Srinivasan Iyer and
                  Xi Victoria Lin and
                  Ramakanth Pasunuru and
                  Todor Mihaylov and
                  Daniel Simig and
                  Ping Yu and
                  Kurt Shuster and
                  Tianlu Wang and
                  Qing Liu and
                  Punit Singh Koura and
                  Xian Li and
                  Brian O'Horo and
                  Gabriel Pereyra and
                  Jeff Wang and
                  Christopher Dewan and
                  Asli Celikyilmaz and
                  Luke Zettlemoyer and
                  Ves Stoyanov},
  title        = {{OPT-IML:} Scaling Language Model Instruction Meta Learning through
                  the Lens of Generalization},
  journal      = {CoRR},
  volume       = {abs/2212.12017},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2212.12017},
  doi          = {10.48550/ARXIV.2212.12017},
  eprinttype    = {arXiv},
  eprint       = {2212.12017},
  timestamp    = {Tue, 09 May 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-12017.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/iclr/AnilPPODH18,
  author       = {Rohan Anil and
                  Gabriel Pereyra and
                  Alexandre Passos and
                  R{\'{o}}bert Orm{\'{a}}ndi and
                  George E. Dahl and
                  Geoffrey E. Hinton},
  title        = {Large scale distributed neural network training through online distillation},
  booktitle    = {6th International Conference on Learning Representations, {ICLR} 2018,
                  Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
  publisher    = {OpenReview.net},
  year         = {2018},
  url          = {https://openreview.net/forum?id=rkr1UDeC-},
  timestamp    = {Thu, 25 Jul 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/AnilPPODH18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-1804-03235,
  author       = {Rohan Anil and
                  Gabriel Pereyra and
                  Alexandre Passos and
                  R{\'{o}}bert Orm{\'{a}}ndi and
                  George E. Dahl and
                  Geoffrey E. Hinton},
  title        = {Large scale distributed neural network training through online distillation},
  journal      = {CoRR},
  volume       = {abs/1804.03235},
  year         = {2018},
  url          = {http://arxiv.org/abs/1804.03235},
  eprinttype    = {arXiv},
  eprint       = {1804.03235},
  timestamp    = {Fri, 22 Feb 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1804-03235.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/iclr/PereyraTCKH17,
  author       = {Gabriel Pereyra and
                  George Tucker and
                  Jan Chorowski and
                  Lukasz Kaiser and
                  Geoffrey E. Hinton},
  title        = {Regularizing Neural Networks by Penalizing Confident Output Distributions},
  booktitle    = {5th International Conference on Learning Representations, {ICLR} 2017,
                  Toulon, France, April 24-26, 2017, Workshop Track Proceedings},
  publisher    = {OpenReview.net},
  year         = {2017},
  url          = {https://openreview.net/forum?id=HyhbYrGYe},
  timestamp    = {Thu, 04 Apr 2019 13:20:08 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/PereyraTCKH17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/PereyraTCKH17,
  author       = {Gabriel Pereyra and
                  George Tucker and
                  Jan Chorowski and
                  Lukasz Kaiser and
                  Geoffrey E. Hinton},
  title        = {Regularizing Neural Networks by Penalizing Confident Output Distributions},
  journal      = {CoRR},
  volume       = {abs/1701.06548},
  year         = {2017},
  url          = {http://arxiv.org/abs/1701.06548},
  eprinttype    = {arXiv},
  eprint       = {1701.06548},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/PereyraTCKH17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/icassp/LaurentPBZB16,
  author       = {C{\'{e}}sar Laurent and
                  Gabriel Pereyra and
                  Philemon Brakel and
                  Ying Zhang and
                  Yoshua Bengio},
  title        = {Batch normalized recurrent neural networks},
  booktitle    = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  pages        = {2657--2661},
  publisher    = {{IEEE}},
  year         = {2016},
  url          = {https://doi.org/10.1109/ICASSP.2016.7472159},
  doi          = {10.1109/ICASSP.2016.7472159},
  timestamp    = {Fri, 03 Apr 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/LaurentPBZB16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/LaurentPBZB15,
  author       = {C{\'{e}}sar Laurent and
                  Gabriel Pereyra and
                  Philemon Brakel and
                  Ying Zhang and
                  Yoshua Bengio},
  title        = {Batch Normalized Recurrent Neural Networks},
  journal      = {CoRR},
  volume       = {abs/1510.01378},
  year         = {2015},
  url          = {http://arxiv.org/abs/1510.01378},
  eprinttype    = {arXiv},
  eprint       = {1510.01378},
  timestamp    = {Fri, 03 Apr 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/LaurentPBZB15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}