18 citations · 24 across the 8 of their papers we have counts for
8 papers
Online Learning Using Only Peer Prediction
Yang Liu, David P. Helmbold
This paper considers a variant of the classical online learning problem with expert predictions. Our model's differences and challenges are due to lacking any direct feedback on th…
A New Family of Neural Networks Provably Resistant to Adversarial Attacks
Rakshit Agrawal, Luca de Alfaro, David Helmbold
Adversarial attacks add perturbations to the input features with the intent of changing the classification produced by a machine learning system. Small perturbations can yield adve…
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks
Peter L. Bartlett, David P. Helmbold, Philip M. Long
We analyze algorithms for approximating a function mapping to using deep linear neural networks, i.e. that learn a function parameterized by matrice…
Online Learning of Combinatorial Objects via Extended Formulation
Holakou Rahmanian, David P. Helmbold, S. V. N. Vishwanathan
The standard techniques for online learning of combinatorial objects perform multiplicative updates followed by projections into the convex hull of all the objects. However, this m…
Surprising properties of dropout in deep networks
David P. Helmbold, Philip M. Long
We analyze dropout in deep networks with rectified linear units and the quadratic loss. Our results expose surprising differences between the behavior of dropout and more tradition…
On the Inductive Bias of Dropout
David P. Helmbold, Philip M. Long
Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout sho…
On the Necessity of Irrelevant Variables
David P. Helmbold, Philip M. Long
This work explores the effects of relevant and irrelevant boolean variables on the accuracy of classifiers. The analysis uses the assumption that the variables are conditionally in…
Learning Object Location Predictors with Boosting and Grammar-Guided Feature Extraction
Damian Eads, Edward Rosten, David Helmbold
We present BEAMER: a new spatially exploitative approach to learning object detectors which shows excellent results when applied to the task of detecting objects in greyscale aeria…