ML Prof @Caltech (group: @YueLabCaltech); Principal Scientist at Latitude AI (https://t.co/riZHAmvKpZ). Senior Program Chair @iclr_conf; Communication Co-Chair @icmlconf. He/Him
Mar 8, 2021 • 8 tweets • 3 min read
When I was a PhD student, a professor told me:
"There are only three papers worth writing on a given topic: the first paper, the best paper, and the last paper."
It's obv a bit tongue-in-cheek, but I've often used the underlying heuristic to aid in choosing research directions.
Of course, no one can exactly predict the outcome of a research project a priori, but in my experience this heuristic can manifest in a few ways.
(Note that the following examples are from my biased viewpoint as an academic ML researcher.)
Nov 24, 2020 • 7 tweets • 5 min read
I've found GPs to be very useful in real-world applications where data is scarce and uncertainty quantification is useful for (sequential) decision making.
We studied how to personalize the (implanted) neuromodulation of paralyzed subjects to help them stand. Led to novel bandit & Bayesian opt algs that learn via subjective preferences while exploring safely. Work by @YananSui
