I hope you will also be willing to share your lecture notes later during the semester. I’m from systems biology and there’s a small group of people that I talked to interested in applying control theory to cellular systems, and since biology is so complicated generally we are finding success with ML approaches as well. Maybe there will be some cross pollination of ideas based on what you would like to teach!
Solid framing on the induction vs feedback split. The trap of getting stuck in stochastic optimization makes sense when everyones default is "whats the loss function" instead of asking how feedback stabilizes teh system. I've run into the Lucas Critique problem way more times than I'd like to admit, where models trained on past data break the moment deployment changes behavior. Deemphasizing optimal control to focus on stability and robustness feels overdue.
Brilliant reframing of the stuck-in-optimization problem. The insight that we've been treating feedback as just another dynamic programming tool rather than understanding what feedback fundamentaly does is sharp. I ran into this same trap when building control systems for industrial robots, kept trying to optimize every parameter until someone pointed out we were igoring basic stability guarantees. This new course approach focusing on why feedback systems work despite brittleness everywhere sounds way more grounding than another RL class.
Cybernetics strikes again! The principles of feedback control really seem to be fundamental in some way to complex systems, the way conservation laws underpin mechanics and thermodynamics.
I look forward to your syllabus and future discussions.
Is there any way I can access the notes or recording or tune in live?
Doing my PhD in AI and human control processes and your article captures a lot of the concepts I'm looking into!
It’s a seminar, so there won’t be a video, but I’ll liveblog and post all the readings.
Thanks a lot!!
I hope you will also be willing to share your lecture notes later during the semester. I’m from systems biology and there’s a small group of people that I talked to interested in applying control theory to cellular systems, and since biology is so complicated generally we are finding success with ML approaches as well. Maybe there will be some cross pollination of ideas based on what you would like to teach!
Absolutely. I’ll post all of the materials here, starting next week.
Sounds awesome!!!
Solid framing on the induction vs feedback split. The trap of getting stuck in stochastic optimization makes sense when everyones default is "whats the loss function" instead of asking how feedback stabilizes teh system. I've run into the Lucas Critique problem way more times than I'd like to admit, where models trained on past data break the moment deployment changes behavior. Deemphasizing optimal control to focus on stability and robustness feels overdue.
Brilliant reframing of the stuck-in-optimization problem. The insight that we've been treating feedback as just another dynamic programming tool rather than understanding what feedback fundamentaly does is sharp. I ran into this same trap when building control systems for industrial robots, kept trying to optimize every parameter until someone pointed out we were igoring basic stability guarantees. This new course approach focusing on why feedback systems work despite brittleness everywhere sounds way more grounding than another RL class.
Cybernetics strikes again! The principles of feedback control really seem to be fundamental in some way to complex systems, the way conservation laws underpin mechanics and thermodynamics.
I look forward to your syllabus and future discussions.