Make Stochastic Gradient Descent Fast Again (Ep. 113)
Jul 22, 2020•21 min•Ep. 110
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
There is definitely room for improvement in the family of algorithms of stochastic gradient descent. In this episode I explain a relatively simple method that has shown to improve on the Adam optimizer. But, watch out! This approach does not generalize well.
Join our Discord channel and chat with us.
References
For the best experience, listen in Metacast app for iOS or Android