Search Results for author:
Found 12 papers, 3 papers with code
Something for (almost) nothing: Improving deep ensemble calibration using unlabeled data
We present a method to improve the calibration of deep ensembles in the small training data regime in the presence of unlabeled data.
A Primer on Bayesian Neural Networks: Review and Debates
Neural networks have achieved remarkable performance across various problem domains, but their widespread applicability is hindered by inherent limitations such as overconfidence in predictions, lack of interpretability, and vulnerability to adversarial attacks.
The fine print on tempered posteriors
Contrary to previous results, we first show that for realistic models and datasets and the tightly controlled case of the Laplace approximation to the posterior, stochasticity does not in general improve test accuracy.
Europepolls: A Dataset of Country-Level Opinion Polling Data for the European Union and the UK
Both the raw and the preprocessed data are in the . csv format.
Cold Posteriors through PAC-Bayes
We investigate the cold posterior effect through the lens of PAC-Bayes generalization bounds.
On PAC-Bayes Bounds for Deep Neural Networks using the Loss Curvature
We investigate whether it's possible to tighten PAC-Bayes bounds for deep neural networks by utilizing the Hessian of the training loss at the minimum.
Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
Explaining how overparametrized neural networks simultaneously achieve low risk and zero empirical risk on benchmark datasets is an open problem.
The role of invariance in spectral complexity-based generalization bounds
Deep convolutional neural networks (CNNs) have been shown to be able to fit a random labeling over data while still being able to generalize well for normal labels.
Revisiting hard thresholding for DNN pruning
Recently developed smart pruning algorithms use the DNN response over the training set for a variety of cost functions to determine redundant network weights, leading to less accuracy degradation and possibly less retraining time.
FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy.
Cheap DNN Pruning with Performance Guarantees
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers often with little or no drop in classification accuracy.
PAC-Bayesian Margin Bounds for Convolutional Neural Networks
Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers.
