
-
Rethinking Neural Operations for Diverse Tasks
An important goal of neural architecture search (NAS) is to automate-awa...
read it
-
Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation
Labeling data for modern machine learning is expensive and time-consumin...
read it
-
Robustness Gym: Unifying the NLP Evaluation Landscape
Despite impressive performance on standard benchmarks, deep neural netwo...
read it
-
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
Modern neural network architectures use structured linear transformation...
read it
-
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
In real-world classification tasks, each class often comprises multiple ...
read it
-
Sharp Bias-variance Tradeoffs of Hard Parameter Sharing in High-dimensional Linear Regression
Hard parameter sharing for multi-task learning is widely used in empiric...
read it
-
Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation
A challenge for named entity disambiguation (NED), the task of mapping t...
read it
-
From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering
Similarity-based Hierarchical Clustering (HC) is a classical unsupervise...
read it
-
Leveraging Organizational Resources to Adapt Models to New Data Modalities
As applications in large organizations evolve, the machine learning (ML)...
read it
-
HiPPO: Recurrent Memory with Optimal Polynomial Projections
A central problem in learning from sequential data is representing cumul...
read it
-
Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
Classifiers in machine learning are often brittle when deployed. Particu...
read it
-
GRIP: A Graph Neural Network Accelerator Architecture
We present GRIP, a graph neural network accelerator architecture designe...
read it
-
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...
read it
-
Contextual Embeddings: When Are They Worth It?
We study the settings for which deep contextual embeddings (e.g., BERT) ...
read it
-
Machine Learning on Graphs: A Model and Comprehensive Taxonomy
There has been a surge of recent interest in learning representations fo...
read it
-
Understanding and Improving Information Transfer in Multi-Task Learning
We investigate multi-task learning approaches that use a shared feature ...
read it
-
On the Generalization Effects of Linear Transformations in Data Augmentation
Data augmentation is a powerful technique to improve performance in appl...
read it
-
Low-Dimensional Hyperbolic Knowledge Graph Embeddings
Knowledge graph (KG) embeddings learn low-dimensional representations of...
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...
read it
-
Assessing Robustness to Noise: Low-Cost Head CT Triage
Automated medical image classification with convolutional neural network...
read it
-
Understanding the Downstream Instability of Word Embeddings
Many industrial machine learning (ML) systems require frequent retrainin...
read it
-
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Weak supervision is a popular method for building machine learning model...
read it
-
Hyperbolic Graph Convolutional Neural Networks
Graph convolutional neural networks (GCNs) embed nodes in a graph into E...
read it
-
Multi-Resolution Weak Supervision for Sequential Data
Since manually labeling training data is slow and expensive, recent indu...
read it
-
PipeMare: Asynchronous Pipeline Parallel DNN Training
Recently there has been a flurry of interest around using pipeline paral...
read it
-
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Many real-world video analysis applications require the ability to ident...
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...
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 ...
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...
read it
-
On the Downstream Performance of Compressed Word Embeddings
Compressing word embeddings is important for deploying NLP models in mem...
read it
-
Sparse Recovery for Orthogonal Polynomial Transforms
In this paper we consider the following sparse recovery problem. We have...
read it
-
Scene Graph Prediction with Limited Labels
Visual knowledge bases such as Visual Genome power numerous applications...
read it
-
Low-Memory Neural Network Training: A Technical Report
Memory is increasingly often the bottleneck when training neural network...
read it
-
Medical device surveillance with electronic health records
Post-market medical device surveillance is a challenge facing manufactur...
read it
-
SysML: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
read it
-
Cross-Modal Data Programming Enables Rapid Medical Machine Learning
Labeling training datasets has become a key barrier to building medical ...
read it
-
Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations
Fast linear transforms are ubiquitous in machine learning, including the...
read it
-
Learning Dependency Structures for Weak Supervision Models
Labeling training data is a key bottleneck in the modern machine learnin...
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...
read it
-
Low-Precision Random Fourier Features for Memory-Constrained Kernel Approximation
We investigate how to train kernel approximation methods that generalize...
read it
-
Training Complex Models with Multi-Task Weak Supervision
As machine learning models continue to increase in complexity, collectin...
read it
-
Learning Compressed Transforms with Low Displacement Rank
The low displacement rank (LDR) framework for structured matrices repres...
read it
-
Training Classifiers with Natural Language Explanations
Training accurate classifiers requires many labels, but each label provi...
read it
-
Representation Tradeoffs for Hyperbolic Embeddings
Hyperbolic embeddings offer excellent quality with few dimensions when e...
read it
-
Hypertree Decompositions Revisited for PGMs
We revisit the classical problem of exact inference on probabilistic gra...
read it
-
A Kernel Theory of Modern Data Augmentation
Data augmentation, a technique in which a training set is expanded with ...
read it
-
High-Accuracy Low-Precision Training
Low-precision computation is often used to lower the time and energy cos...
read it
-
A Formal Framework For Probabilistic Unclean Databases
Traditional modeling of inconsistency in database theory casts all possi...
read it
-
Snorkel: Rapid Training Data Creation with Weak Supervision
Labeling training data is increasingly the largest bottleneck in deployi...
read it
-
Inferring Generative Model Structure with Static Analysis
Obtaining enough labeled data to robustly train complex discriminative m...
read it