Our next session is on Tuesday, June 16th. Stay tuned for more info.

Date: Tuesday, May 19 

Time: 2pm PT / 5pm ET

Join us for our monthly quantitative-focused series

SigOpt works with algorithmic trading firms who represent over $600B in assets under management. These partnerships have given us unique insights on how model optimization and experimentation can be made most useful for teams who are modeling at scale with the purpose of generating revenue or differentiating their products in a competitive marketplace. To share these lessons, tune in on the third Tuesday of each month where we will focus more specifically on best practices for experiment management, model optimization and parameter tuning. 

Training, Tuning and Metric Strategy

Last month, we focused on efficiently scaling tuning jobs with parallelism and multitask optimization. This month, we focus on getting the most out of every run with a focus on deep learning model development. 

In deep learning, it can be particularly tough to select the right metric and know when a model has converged during training. In this talk, we discuss ways to monitor convergence, automate early stopping and set the right metric strategy for deep learning training and tuning jobs. The result is a more efficient approach to iterating on these models in the development process.

In particular we will focus on:

  • Setting the right strategy for each metric, whether it is tracked, used to set constraints on a training or tuning run or optimized in a tuning process
  • Monitoring convergence with checkpoints to gain intra-run intelligence on each run
  • Automating early stopping to more efficiently utilize resources