How much ML theory should I prepare? I have a solid understanding of the fundamentals but it would be hard for me to work through the mathematics of say Adagrad or Adam on the spot without working through it beforehand. Rooftop slushie link: https://www.rooftopslushie.com/request/Preparing%20for%20E6%20ML%20Engineer-1690
Can you share your background? Curious what it takes to get considered for e6 ml engineer
And TC
Interested to know background and yoe
Adaptive gradients methods like Adam should be easy to drive on the fly as most of them are based some sort of a moving average of gradients and learning rate decaying
Thanks! I am talking about formal mathematical proof of convergence and deriving it on the spot. At the high level I understand why and how it works .
That nobody knows at the moment, to the best of my knowledge. It’s an active research field.