Christopher Ré

Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings

Our goal is to enable machine learning systems to be trained interactive...
06/26/2020 ∙ by Mayee F. Chen, et al. ∙ 1 ∙ share

read it
Contextual Embeddings: When Are They Worth It?

We study the settings for which deep contextual embeddings (e.g., BERT) ...
05/18/2020 ∙ by Simran Arora, et al. ∙ 0 ∙ share

read it
Machine Learning on Graphs: A Model and Comprehensive Taxonomy

There has been a surge of recent interest in learning representations fo...
05/07/2020 ∙ by Ines Chami, et al. ∙ 44 ∙ share

read it
Understanding and Improving Information Transfer in Multi-Task Learning

We investigate multi-task learning approaches that use a shared feature ...
05/02/2020 ∙ by Sen Wu, et al. ∙ 0 ∙ share

read it
On the Generalization Effects of Linear Transformations in Data Augmentation

Data augmentation is a powerful technique to improve performance in appl...
05/02/2020 ∙ by Sen Wu, et al. ∙ 5 ∙ share

read it
Low-Dimensional Hyperbolic Knowledge Graph Embeddings

Knowledge graph (KG) embeddings learn low-dimensional representations of...
05/01/2020 ∙ by Ines Chami, et al. ∙ 10 ∙ share

read it
Ivy: Instrumental Variable Synthesis for Causal Inference

A popular way to estimate the causal effect of a variable x on y from ob...
04/11/2020 ∙ by Zhaobin Kuang, et al. ∙ 2 ∙ share

read it
Assessing Robustness to Noise: Low-Cost Head CT Triage

Automated medical image classification with convolutional neural network...
03/17/2020 ∙ by Sarah M. Hooper, et al. ∙ 3 ∙ share

read it
Understanding the Downstream Instability of Word Embeddings

Many industrial machine learning (ML) systems require frequent retrainin...
02/29/2020 ∙ by Megan Leszczynski, et al. ∙ 0 ∙ share

read it
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods

Weak supervision is a popular method for building machine learning model...
02/27/2020 ∙ by Daniel Y. Fu, et al. ∙ 6 ∙ share

read it
Hyperbolic Graph Convolutional Neural Networks

Graph convolutional neural networks (GCNs) embed nodes in a graph into E...
10/28/2019 ∙ by Ines Chami, et al. ∙ 23 ∙ share

read it
Multi-Resolution Weak Supervision for Sequential Data

Since manually labeling training data is slow and expensive, recent indu...
10/21/2019 ∙ by Frederic Sala, et al. ∙ 16 ∙ share

read it
PipeMare: Asynchronous Pipeline Parallel DNN Training

Recently there has been a flurry of interest around using pipeline paral...
10/09/2019 ∙ by Bowen Yang, et al. ∙ 42 ∙ share

read it
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels

Many real-world video analysis applications require the ability to ident...
10/07/2019 ∙ by Daniel Y. Fu, et al. ∙ 37 ∙ share

read it
Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging

Machine learning models for medical image analysis often suffer from poo...
09/27/2019 ∙ by Luke Oakden-Rayner, et al. ∙ 24 ∙ share

read it
Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

In real-world machine learning applications, data subsets correspond to ...
09/13/2019 ∙ by Vincent S. Chen, et al. ∙ 34 ∙ share

read it
Overton: A Data System for Monitoring and Improving Machine-Learned Products

We describe a system called Overton, whose main design goal is to suppor...
09/07/2019 ∙ by Christopher Ré, et al. ∙ 0 ∙ share

read it
On the Downstream Performance of Compressed Word Embeddings

Compressing word embeddings is important for deploying NLP models in mem...
09/03/2019 ∙ by Avner May, et al. ∙ 5 ∙ share

read it
Sparse Recovery for Orthogonal Polynomial Transforms

In this paper we consider the following sparse recovery problem. We have...
07/19/2019 ∙ by Anna Gilbert, et al. ∙ 0 ∙ share

read it
Scene Graph Prediction with Limited Labels

Visual knowledge bases such as Visual Genome power numerous applications...
04/25/2019 ∙ by Vincent S. Chen, et al. ∙ 6 ∙ share

read it
Low-Memory Neural Network Training: A Technical Report

Memory is increasingly often the bottleneck when training neural network...
04/24/2019 ∙ by Nimit Sharad Sohoni, et al. ∙ 0 ∙ share

read it
Medical device surveillance with electronic health records

Post-market medical device surveillance is a challenge facing manufactur...
04/03/2019 ∙ by Alison Callahan, et al. ∙ 0 ∙ share

read it
SysML: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
03/29/2019 ∙ by Alexander Ratner, et al. ∙ 0 ∙ share

read it
Cross-Modal Data Programming Enables Rapid Medical Machine Learning

Labeling training datasets has become a key barrier to building medical ...
03/26/2019 ∙ by Jared Dunnmon, et al. ∙ 12 ∙ share

read it
Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations

Fast linear transforms are ubiquitous in machine learning, including the...
03/14/2019 ∙ by Tri Dao, et al. ∙ 28 ∙ share

read it
Learning Dependency Structures for Weak Supervision Models

Labeling training data is a key bottleneck in the modern machine learnin...
03/14/2019 ∙ by Paroma Varma, et al. ∙ 8 ∙ share

read it
Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale

Labeling training data is one of the most costly bottlenecks in developi...
12/02/2018 ∙ by Stephen H. Bach, et al. ∙ 0 ∙ share

read it
Low-Precision Random Fourier Features for Memory-Constrained Kernel Approximation

We investigate how to train kernel approximation methods that generalize...
10/31/2018 ∙ by Jian Zhang, et al. ∙ 4 ∙ share

read it
Training Complex Models with Multi-Task Weak Supervision

As machine learning models continue to increase in complexity, collectin...
10/05/2018 ∙ by Alexander Ratner, et al. ∙ 14 ∙ share

read it
Learning Compressed Transforms with Low Displacement Rank

The low displacement rank (LDR) framework for structured matrices repres...
10/04/2018 ∙ by Anna T. Thomas, et al. ∙ 2 ∙ share

read it
Training Classifiers with Natural Language Explanations

Training accurate classifiers requires many labels, but each label provi...
05/10/2018 ∙ by Braden Hancock, et al. ∙ 0 ∙ share

read it
Representation Tradeoffs for Hyperbolic Embeddings

Hyperbolic embeddings offer excellent quality with few dimensions when e...
04/10/2018 ∙ by Christopher De Sa, et al. ∙ 0 ∙ share

read it
Hypertree Decompositions Revisited for PGMs

We revisit the classical problem of exact inference on probabilistic gra...
04/05/2018 ∙ by Aarthy Shivram Arun, et al. ∙ 0 ∙ share

read it
A Kernel Theory of Modern Data Augmentation

Data augmentation, a technique in which a training set is expanded with ...
03/16/2018 ∙ by Tri Dao, et al. ∙ 0 ∙ share

read it
High-Accuracy Low-Precision Training

Low-precision computation is often used to lower the time and energy cos...
03/09/2018 ∙ by Christopher De Sa, et al. ∙ 0 ∙ share

read it
A Formal Framework For Probabilistic Unclean Databases

Traditional modeling of inconsistency in database theory casts all possi...
01/21/2018 ∙ by Christopher De Sa, et al. ∙ 0 ∙ share

read it
Snorkel: Rapid Training Data Creation with Weak Supervision

Labeling training data is increasingly the largest bottleneck in deployi...
11/28/2017 ∙ by Alexander Ratner, et al. ∙ 0 ∙ share

read it
Inferring Generative Model Structure with Static Analysis

Obtaining enough labeled data to robustly train complex discriminative m...
09/07/2017 ∙ by Paroma Varma, et al. ∙ 0 ∙ share

read it
Learning to Compose Domain-Specific Transformations for Data Augmentation

Data augmentation is a ubiquitous technique for increasing the size of l...
09/06/2017 ∙ by Alexander J. Ratner, et al. ∙ 0 ∙ share

read it
LevelHeaded: Making Worst-Case Optimal Joins Work in the Common Case

Pipelines combining SQL-style business intelligence (BI) queries and lin...
08/25/2017 ∙ by Christopher R. Aberger, et al. ∙ 0 ∙ share

read it
Accelerated Stochastic Power Iteration

Principal component analysis (PCA) is one of the most powerful tools in ...
07/10/2017 ∙ by Christopher De Sa, et al. ∙ 0 ∙ share

read it
YellowFin and the Art of Momentum Tuning

Hyperparameter tuning is one of the big costs of deep learning. State-of...
06/12/2017 ∙ by Jian Zhang, et al. ∙ 0 ∙ share

read it
Infrastructure for Usable Machine Learning: The Stanford DAWN Project

Despite incredible recent advances in machine learning, building machine...
05/22/2017 ∙ by Peter Bailis, et al. ∙ 0 ∙ share

read it
ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information

In healthcare applications, temporal variables that encode movement, hea...
05/13/2017 ∙ by Madalina Fiterau, et al. ∙ 0 ∙ share

read it
SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data

We present SwellShark, a framework for building biomedical named entity ...
04/20/2017 ∙ by Jason Fries, et al. ∙ 0 ∙ share

read it
Learning the Structure of Generative Models without Labeled Data

Curating labeled training data has become the primary bottleneck in mach...
03/02/2017 ∙ by Stephen H. Bach, et al. ∙ 0 ∙ share

read it
Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data

A challenge in training discriminative models like neural networks is ob...
10/25/2016 ∙ by Paroma Varma, et al. ∙ 0 ∙ share

read it
Sub-sampled Newton Methods with Non-uniform Sampling

We consider the problem of finding the minimizer of a convex function F:...
07/02/2016 ∙ by Peng Xu, et al. ∙ 0 ∙ share

read it
Parallel SGD: When does averaging help?

Consider a number of workers running SGD independently on the same pool ...
06/23/2016 ∙ by Jian Zhang, et al. ∙ 0 ∙ share

read it
Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much

Gibbs sampling is a Markov Chain Monte Carlo sampling technique that ite...
06/10/2016 ∙ by Bryan He, et al. ∙ 0 ∙ share

read it

Christopher Ré

Featured Co-authors