GTC Silicon Valley-2019: Tuning the Un-Tunable: Lessons for Tuning Expensive Deep Learning Functions

GTC Silicon Valley-2019 ID:S9313:Tuning the Un-Tunable: Lessons for Tuning Expensive Deep Learning Functions

Scott Clark(SigOpt)
Training and tuning models with lengthy training cycles like those in deep learning can be extremely expensive and may sometimes involve techniques that degrade performance. We'll explore recent research on optimization strategies to efficiently tune these types of deep learning models. We will provide benchmarks and comparisons to other popular methods for optimizing the models, and we'll recommend valuable areas for further applied research.

View the slides (pdf)