Statistical Learning under Heterogenous Distribution Shift
Paper
•
2302.13934
•
Published
Max Simchowitz
msimchowitz
AI & ML interests
Robotics, Generative Models, Sequence Prediction, ML Theory
Organizations
None yet
authored
6
papers
about 1 year ago
Robot Fleet Learning via Policy Merging
Paper
•
2310.01362
•
Published
The Power of Learned Locally Linear Models for Nonlinear Policy Optimization
Paper
•
2305.09619
•
Published
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Paper
•
2310.11428
•
Published
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Paper
•
2407.01392
•
Published
•
45
Diffusion Policy Policy Optimization
Paper
•
2409.00588
•
Published
•
20