
-
Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training
Self-training is a standard approach to semi-supervised learning where t...
read it
-
Task-agnostic Indexes for Deep Learning-based Queries over Unstructured Data
Unstructured data is now commonly queried by using target deep neural ne...
read it
-
Approximate Partition Selection for Big-Data Workloads using Summary Statistics
Many big-data clusters store data in large partitions that support acces...
read it
-
Leveraging Organizational Resources to Adapt Models to New Data Modalities
As applications in large organizations evolve, the machine learning (ML)...
read it
-
Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics
While deep neural networks (DNNs) are an increasingly popular way to que...
read it
-
Similarity Search for Efficient Active Learning and Search of Rare Concepts
Many active learning and search approaches are intractable for industria...
read it
-
Chromatic Learning for Sparse Datasets
Learning over sparse, high-dimensional data frequently necessitates the ...
read it
-
Approximate Selection with Guarantees using Proxies
Due to the falling costs of data acquisition and storage, researchers an...
read it
-
Model Assertions for Monitoring and Improving ML Model
ML models are increasingly deployed in settings with real world interact...
read it
-
Model Assertions for Monitoring and Improving ML Models
ML models are increasingly deployed in settings with real world interact...
read it
-
Storyboard: Optimizing Precomputed Summaries for Aggregation
An emerging class of data systems partition their data and precompute ap...
read it
-
MLPerf Training Benchmark
Machine learning is experiencing an explosion of software and hardware s...
read it
-
Selection Via Proxy: Efficient Data Selection For Deep Learning
Data selection methods such as active learning and core-set selection ar...
read it
-
Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
Machine learning (ML) has become increasingly important and performance-...
read it
-
CrossTrainer: Practical Domain Adaptation with Loss Reweighting
Domain adaptation provides a powerful set of model training techniques g...
read it
-
SysML: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
read it
-
Equivariant Transformer Networks
How can prior knowledge on the transformation invariances of a domain be...
read it
-
LIT: Block-wise Intermediate Representation Training for Model Compression
Knowledge distillation (KD) is a popular method for reducing the computa...
read it
-
Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark
The deep learning community has proposed optimizations spanning hardware...
read it
-
BlazeIt: Fast Exploratory Video Queries using Neural Networks
As video volumes grow, analysts have increasingly turned to deep learnin...
read it
-
Locality-Sensitive Hashing for Earthquake Detection: A Case Study of Scaling Data-Driven Science
In this work, we report on a novel application of Locality Sensitive Has...
read it
-
Locality-Sensitive Hashing for Earthquake Detection: A Case Study Scaling Data-Driven Science
In this work, we report on a novel application of Locality Sensitive Has...
read it
-
Moment-Based Quantile Sketches for Efficient High Cardinality Aggregation Queries
Interactive analytics increasingly involves querying for quantiles over ...
read it
-
Finding Heavily-Weighted Features in Data Streams
We introduce a new sub-linear space data structure---the Weight-Median S...
read it
-
DROP: Dimensionality Reduction Optimization for Time Series
Dimensionality reduction is critical in analyzing increasingly high-volu...
read it
-
There and Back Again: A General Approach to Learning Sparse Models
We propose a simple and efficient approach to learning sparse models. Ou...
read it
-
To Index or Not to Index: Optimizing Maximum Inner Product Search
Making top-K predictions for state-of-the-art Matrix Factorization model...
read it
-
SimDex: Exploiting Model Similarity in Exact Matrix Factorization Recommendations
We present SimDex, a new technique for serving exact top-K recommendatio...
read it
-
Infrastructure for Usable Machine Learning: The Stanford DAWN Project
Despite incredible recent advances in machine learning, building machine...
read it
-
NoScope: Optimizing Neural Network Queries over Video at Scale
Recent advances in computer vision-in the form of deep neural networks-h...
read it