no code implementations • 25 Jan 2023 • David Mcallester
This paper gives direct derivations of the differential equations and likelihood formulas of diffusion models assuming only knowledge of Gaussian distributions.
1 code implementation • CVPR 2021 • Pedro Savarese, Sunnie S. Y. Kim, Michael Maire, Greg Shakhnarovich, David Mcallester
We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets.
Ranked #1 on Unsupervised Image Segmentation on Flowers
no code implementations • WS 2020 • Hai Wang, David Mcallester
Here we experiment with the use of information retrieval as an augmentation for pre-trained language models.
no code implementations • 12 May 2020 • David McAllester
We propose the foundation of set-theoretic dependent type theory and an objective defined in terms of the classification problem -- the problem of classifying concept instances up to isomorphism.
1 code implementation • CVPR 2021 • Pedro Savarese, David Mcallester, Sudarshan Babu, Michael Maire
From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned.
1 code implementation • CONLL 2019 • Hai Wang, Dian Yu, Kai Sun, Jianshu Chen, Dong Yu, David Mcallester, Dan Roth
Remarkable success has been achieved in the last few years on some limited machine reading comprehension (MRC) tasks.
2 code implementations • ICLR 2019 • David McAllester, Karl Stratos
Measuring mutual information from finite data is difficult.
no code implementations • 21 Feb 2018 • David McAllester
The information theoretic training objective for $P_\Phi(z|x)$ and $P_\Psi(z|y)$ can be viewed as a form of co-training where we want the prediction from $x$ to match the confirmation from $y$.
2 code implementations • NeurIPS 2017 • Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro
With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness.
no code implementations • WS 2017 • Hai Wang, Takeshi Onishi, Kevin Gimpel, David Mcallester
A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets.
no code implementations • EACL 2017 • Zewei Chu, Hai Wang, Kevin Gimpel, David Mcallester
Progress in text understanding has been driven by large datasets that test particular capabilities, like recent datasets for reading comprehension (Hermann et al., 2015).
Ranked #32 on Language Modelling on LAMBADA
no code implementations • EMNLP 2016 • Takeshi Onishi, Hai Wang, Mohit Bansal, Kevin Gimpel, David Mcallester
We have constructed a new "Who-did-What" dataset of over 200, 000 fill-in-the-gap (cloze) multiple choice reading comprehension problems constructed from the LDC English Gigaword newswire corpus.
no code implementations • NeurIPS 2014 • Shubhendu Trivedi, David Mcallester, Greg Shakhnarovich
We formulate the problem of metric learning for k nearest neighbor classification as a large margin structured prediction problem, with a latent variable representing the choice of neighbors and the task loss directly corresponding to classification error.
no code implementations • 8 Jul 2013 • David McAllester
The first is an Occam bound which handles rules with finite precision parameters and which states that generalization loss is near training loss when the number of bits needed to write the rule is small compared to the sample size.
no code implementations • CVPR 2013 • Koichiro Yamaguchi, David Mcallester, Raquel Urtasun
We consider the problem of computing optical flow in monocular video taken from a moving vehicle.
no code implementations • 8 Oct 2012 • Tamir Hazan, Alexander Schwing, David Mcallester, Raquel Urtasun
In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models.
no code implementations • 25 Aug 2012 • David McAllester, Petri Myllymaki
This is the Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence, which was held in Helsinki, Finland, July 9 - 12 2008.
no code implementations • 13 Mar 2009 • David McAllester
This paper has been retracted.