CS 5777 - Principles of Large-Scale Machine Learning Systems

Fall. 4 credits. Student option grading.

Prerequisite: CS 4780 or CS 5780, CS 2110 or equivalents. Co-meets with CS 4787.

C. De Sa.

An introduction to the mathematical and algorithms design principles and tradeoffs that underlie large-scale machine learning on big training sets. Topics include: stochastic gradient descent and other scalable optimization methods, mini-batch training, accelerated methods, adaptive learning rates, parallel and distributed training, and quantization and model compression.