353 citations · 416 across the 12 of their papers we have counts for
5 papers · 1 filter
On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions
Kai Brügge, Asja Fischer, Christian Igel
The Metropolis algorithm is arguably the most fundamental Markov chain Monte Carlo (MCMC) method. But the algorithm is not guaranteed to converge to the desired distribution in the…
Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery
Mike Laszkiewicz, Asja Fischer, Johannes Lederer
Many Machine Learning algorithms are formulated as regularized optimization problems, but their performance hinges on a regularization parameter that needs to be calibrated to each…
Predictive Uncertainty Quantification with Compound Density Networks
Agustinus Kristiadi, Sina Däubener, Asja Fischer
Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. Bayesian neural networks are…
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
Stanisław Jastrzębski, Zachary Kenton, Nicolas Ballas +3
Stochastic Gradient Descent (SGD) based training of neural networks with a large learning rate or a small batch-size typically ends in well-generalizing, flat regions of the weight…
A Closer Look at Memorization in Deep Networks
Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas +8
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noi…