81 citations · 91 across the 15 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 1 cited
Transformers can optimally learn regression mixture models
Reese Pathak, Rajat Sen, Weihao Kong +1
Mixture models arise in many regression problems, but most methods have seen limited adoption partly due to these algorithms' highly-tailored and model-specific nature. On the othe…
math.ST2023
Noisy recovery from random linear observations: Sharp minimax rates under elliptical constraints
Reese Pathak, Martin J. Wainwright, Lin Xiao
Estimation problems with constrained parameter spaces arise in various settings. In many of these problems, the observations available to the statistician can be modelled as arisin…