Search Results for author: David Mcallester

Found 20 papers, 5 papers with code

On the Mathematics of Diffusion Models

no code implementations25 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.

Information-Theoretic Segmentation by Inpainting Error Maximization

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.

Image Segmentation Segmentation +2

On-The-Fly Information Retrieval Augmentation for Language Models

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.

Information Retrieval Retrieval

MathZero, The Classification Problem, and Set-Theoretic Type Theory

no code implementations12 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.

Classification General Classification +1

Domain-independent Dominance of Adaptive Methods

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.

Image Classification Language Modelling +1

Formal Limitations on the Measurement of Mutual Information

2 code implementations ICLR 2019 David McAllester, Karl Stratos

Measuring mutual information from finite data is difficult.

Information Theoretic Co-Training

no code implementations21 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 $y$.

Exploring Generalization in Deep Learning

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.

Emergent Predication Structure in Hidden State Vectors of Neural Readers

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.

Reading Comprehension

Broad Context Language Modeling as Reading Comprehension

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).

coreference-resolution LAMBADA +2

Who did What: A Large-Scale Person-Centered Cloze Dataset

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.

Multiple-choice Reading Comprehension

Discriminative Metric Learning by Neighborhood Gerrymandering

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.

Classification General Classification +2

A PAC-Bayesian Tutorial with A Dropout Bound

no code implementations8 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.

Generalization Bounds

Robust Monocular Epipolar Flow Estimation

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.

Optical Flow Estimation

Blending Learning and Inference in Structured Prediction

no code implementations8 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.

Scene Understanding Semantic Segmentation +1

Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (2008)

no code implementations25 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.

Differential Contrastive Divergence

no code implementations13 Mar 2009 David McAllester

This paper has been retracted.

Cannot find the paper you are looking for? You can Submit a new open access paper.