We consider training a deep neural network to generate samples from an unknown distribution given i.i.d. data. We frame learning as an optimization minimizing a two-sample test statisticâ€”informallyâ€¦ (More)

Neural network image classifiers are known to be vulnerable to adversarial images, i.e., natural images which have been modified by an adversarial perturbation specifically designed to beâ€¦ (More)

One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. In light of this capacity for overfitting, it is remarkable thatâ€¦ (More)

Data often comes in the form of an array or matrix. Matrix factorization techniques attempt to recover missing or corrupted entries by assuming that the matrix can be written as the product of twoâ€¦ (More)

The Probably Approximately Correct (PAC) Bayes framework (McAllester, 1999) can incorporate knowledge about the learning algorithm and data distribution through the use of distributiondependentâ€¦ (More)

We show that Entropy-SGD (Chaudhari et al., 2017), when viewed as a learning algorithm, optimizes a PAC-Bayes bound on the risk of a Gibbs (posterior) classifier, i.e., a randomized classifierâ€¦ (More)

In tasks such as visual search and change detection, a key question is how observers integrate noisy measurements from multiple locations to make a decision. Decision rules proposed to model thisâ€¦ (More)

In recent work, we have shown that Entropy-SGD (Chaudhari et al., 2017), when viewed as a learning algorithm for classifiers, optimizes a PAC-Bayes bound on the risk of the classifier, or moreâ€¦ (More)