Search Results for author:
Found 20 papers, 5 papers with code
On the Mathematics of Diffusion Models
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
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
On-The-Fly Information Retrieval Augmentation for Language Models
Here we experiment with the use of information retrieval as an augmentation for pre-trained language models.
MathZero, The Classification Problem, and Set-Theoretic Type Theory
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.
Domain-independent Dominance of Adaptive Methods
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.
Evidence Sentence Extraction for Machine Reading Comprehension
Remarkable success has been achieved in the last few years on some limited machine reading comprehension (MRC) tasks.
Formal Limitations on the Measurement of Mutual Information
Measuring mutual information from finite data is difficult.
Information Theoretic Co-Training
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
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
A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets.
Broad Context Language Modeling as Reading Comprehension
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
Who did What: A Large-Scale Person-Centered Cloze Dataset
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.
Discriminative Metric Learning by Neighborhood Gerrymandering
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.
A PAC-Bayesian Tutorial with A Dropout Bound
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.
Robust Monocular Epipolar Flow Estimation
We consider the problem of computing optical flow in monocular video taken from a moving vehicle.
Blending Learning and Inference in Structured Prediction
In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models.
Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (2008)
This is the Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence, which was held in Helsinki, Finland, July 9 - 12 2008.
