Fetching the paper…
Reading the bibliography…
PAC-Bayesian is an analysis framework where the training error can be expressed as the weighted average of the hypotheses in the posterior distribution whilst incorporating the prior knowledge.
On exact computation with an infinitely wide neural net
Arora, S., Du, S. S., Hu, W., Li, Z., Salakhutdinov, R., and Wang, R · 1904
Earlier work this paper cites.
Probabilistic neural networks
Specht, D. F · 1990
Earlier work this paper cites.
Bounds for averaging classifiers
Langford, J. and Seeger, M · 2001
Earlier work this paper cites.
Pac-bayesian generalisation error bounds for gaussian process classification
Seeger, M · 2002
Earlier work this paper cites.
A note on the pac bayesian theorem
Maurer, A · 2004
Earlier work this paper cites.
Tighter pac-bayes bounds
Ambroladze, A., Parrado-Hernández, E., and Shawe-Taylor, J · 2007
Earlier work this paper cites.
Tighter risk certificates for neural networks
Pérez-Ortiz, M., Rivasplata, O., Shawe-Taylor, J., and Szepesvári, C · 2007
Earlier work this paper cites.
Pac-bayesian theory for transductive learning
Bégin, L., Germain, P., Laviolette, F., and Roy, J.-F · 2014
Earlier work this paper cites.
Variational dropout and the local reparameterization trick
Kingma, D. P., Salimans, T., and Welling, M · 2015
Earlier work this paper cites.
Deep learning
LeCun, Y., Bengio, Y., and Hinton, G · 2015
Earlier work this paper cites.
Pac-bayesian bounds based on the rényi divergence
Bégin, L., Germain, P., Laviolette, F., and Roy, J.-F · 2016
Earlier work this paper cites.
Variational autoencoder for deep learning of images, labels and captions
Pu, Y., Gan, Z., Henao, R., Yuan, X., Li, C., Stevens, A., and Carin, L · 2016
Earlier work this paper cites.
Dziugaite, G. K. and Roy, D. M · 2017
Earlier work this paper cites.
Non-convex optimization for machine learning
Jain, P. and Kar, P · 2017
Earlier work this paper cites.
A pac-bayesian analysis of randomized learning with application to stochastic gradient descent
London, B · 2017
Earlier work this paper cites.
Non-convex learning via stochastic gradient langevin dynamics: a nonasymptotic analysis
Raginsky, M., Rakhlin, A., and Telgarsky, M · 2017
Cited alongside, same era.
A bayesian perspective on generalization and stochastic gradient descent
Smith, S. L. and Le, Q. V · 2017
Cited alongside, same era.
A strongly quasiconvex pac-bayesian bound
Thiemann, N., Igel, C., Wintenberger, O., and Seldin, Y · 2017
Cited alongside, same era.
Meta-learning by adjusting priors based on extended pac-bayes theory
Amit, R. and Meir, R · 2018
Cited alongside, same era.
Gradient descent provably optimizes over-parameterized neural networks
Du, S. S., Zhai, X., Poczos, B., and Singh, A · 2018
Cited alongside, same era.
Differentiable pac-bayes objectives with partially aggregated neural networks
Biggs, F. and Guedj, B · 2020
Later among the works it cites.
On the role of data in pac-bayes bounds
Dziugaite, G. K., Hsu, K., Gharbieh, W., and Roy, D. M · 2020
Later among the works it cites.
Fast rates for general unbounded loss functions: From erm to generalized bayes
Grünwald, P. D. and Mehta, N. A · 2020
Later among the works it cites.
Infinite attention: Nngp and ntk for deep attention networks
Hron, J., Bahri, Y., Sohl-Dickstein, J., and Novak, R · 2020
Later among the works it cites.
On the neural tangent kernel of deep networks with orthogonal initialization
Huang, W., Du, W., and Da Xu, R. Y · 2020
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Jacot, A., Gabriel, F., and Hongler, C · 2018
Cited alongside, same era.
The deep regression bayesian network and its applications: Probabilistic deep learning for computer vision
Nie, S., Zheng, M., and Ji, Q · 2018
Cited alongside, same era.
Non-vacuous generalization bounds at the imagenet scale: a pac-bayesian compression approach
Zhou, W., Veitch, V., Austern, M., Adams, R. P., and Orbanz, P · 2018
Cited alongside, same era.
A convergence theory for deep learning via over-parameterization
Allen-Zhu, Z., Li, Y., and Song, Z · 2019
Cited alongside, same era.
Generalization bounds of stochastic gradient descent for wide and deep neural networks
Cao, Y. and Gu, Q · 2019
Cited alongside, same era.
A primer on pac-bayesian learning
Guedj, B · 2019
Cited alongside, same era.
Hu, W., Li, Z., and Yu, D · 2019
Cited alongside, same era.
A pac-bayesian approach to generalization bounds for graph neural networks
Liao, R., Urtasun, R., and Zemel, R · 2020
Later among the works it cites.
Zero-cost proxies for lightweight nas
Abdelfattah, M. S., Mehrotra, A., Dudziak, Ł., and Lane, N. D · 2021
Later among the works it cites.
Bayesian neural architecture search using a training-free performance metric
Camero, A., Wang, H., Alba, E., and Bäck, T · 2021
Later among the works it cites.
Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective
Chen, W., Gong, X., and Wang, Z · 2021
Later among the works it cites.
A linearized framework and a new benchmark for model selection for fine-tuning
Deshpande, A., Achille, A., Ravichandran, A., Li, H., Zancato, L., Fowlkes, C., Bhotika, R., Soatto, S., and Perona, P · 2021
Later among the works it cites.
Pac-bayes unleashed: generalisation bounds with unbounded losses
Haddouche, M., Guedj, B., Rivasplata, O., and Shawe-Taylor, J · 2021
Later among the works it cites.
Wide graph neural networks: Aggregation provably leads to exponentially trainability loss
Huang, W., Li, Y., Du, W., Da Xu, R. Y., Yin, J., and Chen, L · 2021
Later among the works it cites.
Pac-bayes bounds for meta-learning with data-dependent prior
Liu, T., Lu, J., Yan, Z., and Zhang, G · 2021
Later among the works it cites.
Learning pac-bayes priors for probabilistic neural networks
Perez-Ortiz, M., Rivasplata, O., Guedj, B., Gleeson, M., Zhang, J., Shawe-Taylor, J., Bober, M., and Kittler, J · 2021
Later among the works it cites.
Understanding deep learning (still) requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., and Vinyals, O · 2021
Later among the works it cites.