Machine Learning

Machine Learning is core to our products. Our researchers and engineers develop and deploy large scale ML and deep learning algorithms on one of the largest grid computing platforms in the world. We process over 100 billion daily user activities and over 200 billion daily ad requests over our global media and advertising networks.

Publications

Paper
|
January 27, 2020
IEEE Transactions on Neural Networks and Learning Systems

MBA: Mini-Batch AUC Optimization

Paper
|
November 10, 2019
AAAI 2020

Learning to Crawl

Paper
|
November 10, 2019
AAAI 2020

A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound

Paper
|
January 1, 2019
CIKM

Task-Guided Pair Embedding in Heterogeneous Network

Paper
|
January 1, 2019
COLT

Optimal Learning for Mallows Block Model

Paper
|
January 1, 2019
ICML

The Information-Theoretic Value of Unlabeled Data in Semi-Supervised Learning

Paper
|
January 1, 2019
ICML

Contextual Memory Trees

Paper
|
January 1, 2019
ICML

Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case

Paper
|
January 1, 2019
EC 2019

Computing a Data Dividend

Paper
|
January 1, 2019
IJCNN 2019

Ensemble Validation: Selectivity has a Price, but Variety is Free

Paper
|
January 1, 2019
IEEE CDC

Constrained Online Learning in Networks with Sublinear Regret and Fit

Paper
|
January 1, 2019
Machine Learning (Journal)

Speculate-Correct Error Bounds for K-Nearest Neighbor Classifiers

Paper
|
January 1, 2019
IEEE Transactions on Pattern Analysis and Machine Intelligence

Tensor Graphical Model: Non-Convex Optimization and Statistical Inference

Paper
|
January 1, 2019
Tractable Probabilistic Modeling

Decomposition Based Reparametrization for Efficient Estimation of Sparse Gaussian Conditional Random Fields

Paper
|
January 1, 2019
Parallel Architectures and Compilation Techniques (PACT)

Achieving Scalability in a K-NN Multi-GPU Network Service with Centaur

Paper
|
January 1, 2019
APPROX-RANDOM 2019

Submodular Optimization with Contention Resolution Extensions