296 citations · 365 across the 5 of their papers we have counts for
5 papers
Formal Limitations on the Measurement of Mutual Information
David McAllester, Karl Stratos
Measuring mutual information from finite data is difficult. Recent work has considered variational methods maximizing a lower bound. In this paper, we prove that serious statistica…
Information Theoretic Co-Training
David McAllester
This paper introduces an information theoretic co-training objective for unsupervised learning. We consider the problem of predicting the future. Rather than predict future sensati…
Exploring Generalization in Deep Learning
Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester +1
With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustnes…
Blending Learning and Inference in Structured Prediction
Tamir Hazan, Alexander Schwing, David McAllester +1
In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models. This algorithm blends the learning and inference tasks,…
Differential Contrastive Divergence
David McAllester
This paper has been retracted.