Search Results for author:
Found 13 papers, 1 papers with code
A note on generalization bounds for losses with finite moments
Moreover, the paper derives a high-probability PAC-Bayes bound for losses with a bounded variance.
A Note on the Convergence of Denoising Diffusion Probabilistic Models
Diffusion models are one of the most important families of deep generative models.
Semi-supervised Batch Learning From Logged Data
We propose learning methods for problems where feedback is missing for some samples, so there are samples with feedback and samples missing-feedback in the logged data.
Progress in Self-Certified Neural Networks
We then show that in data starvation regimes, holding out data for the test set bounds adversely affects generalisation performance, while self-certified strategies based on PAC-Bayes bounds do not suffer from this drawback, proving that they might be a suitable choice for the small data regime.
Learning PAC-Bayes Priors for Probabilistic Neural Networks
We experiment on 6 datasets with different strategies and amounts of data to learn data-dependent PAC-Bayes priors, and we compare them in terms of their effect on test performance of the learnt predictors and tightness of their risk certificate.
On the Role of Optimization in Double Descent: A Least Squares Study
Empirically it has been observed that the performance of deep neural networks steadily improves as we increase model size, contradicting the classical view on overfitting and generalization.
A note on a confidence bound of Kuzborskij and Szepesvári
In an interesting recent work, Kuzborskij and Szepesv\'ari derived a confidence bound for functions of independent random variables, which is based on an inequality that relates concentration to squared perturbations of the chosen function.
Tighter risk certificates for neural networks
In the context of probabilistic neural networks, the output of training is a probability distribution over network weights.
PAC-Bayes Analysis Beyond the Usual Bounds
Specifically, we present a basic PAC-Bayes inequality for stochastic kernels, from which one may derive extensions of various known PAC-Bayes bounds as well as novel bounds.
Logarithmic Pruning is All You Need
The Lottery Ticket Hypothesis is a conjecture that every large neural network contains a subnetwork that, when trained in isolation, achieves comparable performance to the large network.
PAC-Bayes unleashed: generalisation bounds with unbounded losses
We present new PAC-Bayesian generalisation bounds for learning problems with unbounded loss functions.
PAC-Bayes with Backprop
We explore the family of methods "PAC-Bayes with Backprop" (PBB) to train probabilistic neural networks by minimizing PAC-Bayes bounds.
PAC-Bayes bounds for stable algorithms with instance-dependent priors
Our main result estimates the risk of the randomized algorithm in terms of the hypothesis stability coefficients.
