TensorFlow: Large-scale machine learning on heterogeneous systems, Josh Levenberg, Dandelion Mané, 2015. ,
Weight uncertainty in neural network, Proceedings of the 32nd International Conference on Machine Learning, vol.37, pp.1613-1622, 2015. ,
Pac-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning, IMS Lecture Notes Monogr. Ser, vol.56, pp.1-163, 2007. ,
URL : https://hal.archives-ouvertes.fr/hal-00206119
Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data, Conference on Uncertainty in Artificial Intelligence 33, 2017. ,
PAC-Bayesian learning of linear classifiers, Proceedings of the 26th Annual International Conference on Machine Learning -ICML '09, pp.1-8, 2009. ,
PAC-Bayesian theory meets bayesian inference, Advances in Neural Information Processing Systems, vol.29, pp.1884-1892, 2016. ,
URL : https://hal.archives-ouvertes.fr/hal-01324072
Adam: A method for stochastic optimization, 2014. ,
Auto-encoding variational bayes, 2013. ,
Variational dropout and the local reparameterization trick, Advances in Neural Information Processing Systems, vol.28, pp.2575-2583, 2015. ,
Generalized Variational Inference: Three arguments for deriving new Posteriors, 2019. ,
Not) Bounding the True Error, Advances in Neural Information Processing Systems 14, pp.809-816, 2002. ,
Bounds for averaging classifiers, 2001. ,
Dichotomize and generalize: PAC-Bayesian binary activated deep neural networks, Advances in Neural Information Processing Systems, vol.32, pp.6872-6882, 2019. ,
URL : https://hal.archives-ouvertes.fr/hal-02482352
Monte carlo gradient estimation in machine learning, 2019. ,
An improved predictive accuracy bound for averaging classifiers, Proceedings of the 18th International Conference on Machine Learning, number CONF, pp.290-297, 2001. ,
Simple statistical gradient-following algorithms for connectionist reinforcement learning, Machine learning, vol.8, issue.3-4, pp.229-256, 1992. ,
Non-vacuous generalization bounds at the ImageNet scale: A PAC-Bayesian compression approach, International Conference on Learning Representations, 2019. ,