Dimension-free PAC-Bayesian bounds for the estimation of the mean of a random vector
arXiv:1802.04308
Abstract
In this paper, we present a new estimator of the mean of a random vector, computed by applying some threshold function to the norm. Non asymptotic dimension-free almost sub-Gaussian bounds are proved under weak moment assumptions, using PAC-Bayesian inequalities.
arXiv comment31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. Selected for oral presentation in the NIPS 2017 workshop "(Almost) 50 Shades of Bayesian Learning: PAC-Bayesian trends and insights", December 9, 2017. Workshop URL : https://bguedj.github.io/nips2017/50shadesbayesian.html
References in corpus (2)
Cited by in corpus (8)
- User-friendly introduction to PAC-Bayes bounds
- Dimension-free PAC-Bayesian bounds for matrices, vectors, and linear least squares regression
- Fast Mean Estimation with Sub-Gaussian Rates
- Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence
- A Generalization Bound for Online Variational Inference
- Exponential Concentration for Geometric-Median-of-Means in Non-Positive Curvature Spaces
- New bounds for -means and information -means
- Non-asymptotic analysis and inference for an outlyingness induced winsorized mean