Project
SALSA
A statistical adaptive procedure to automatically schedule the learning rate for deep learning with a broad family of stochastic gradient methods.
Algorithms
Publication
Bandits with adversarial scaling
Tool
Randomized Smoothing of All Shapes and Sizes
This library implements the algorithms in our paper for computing robust radii for different smoothing distributions against different adversaries.
Project
Quickr: Cost-Effective Data Analytics at Scale
Quickr explores cost-effective data analytics at scale, breaking new ground in research on offering approximate answers for complex ad-hoc queries.
Group
Deep Learning Group
The Deep Learning group advances the state-of-the-art in deep learning to achieve general intelligence. We develop algorithms, models, and systems in deep supervised and unsupervised learning, deep reinforcement learning, and neural-symbolic reasoning, and then pursue breakthroughs in computer vision,…
Video
Faculty Summit 2016: Hot Topics
Generating Natural Questions About an Image CryptoNets: Machine Learning Inference on Encrypted Data Everest: Deploying Verified-Secure Implementations in the HTTPS Ecosystem Molecular Programming
Podcast
Neural architecture search, imitation learning and the optimized pipeline with Dr. Debadeepta Dey
Dr. Debadeepta Dey is a Principal Researcher in the Adaptive Systems and Interaction group at MSR and he’s currently exploring several lines of research that may help bridge the gap between perception and planning for…
