22 citations · 91 across the 29 of their papers we have counts for
3 papers · 1 filter
Causal Matrix Completion
Anish Agarwal, Munther Dahleh, Devavrat Shah +1
Matrix completion is the study of recovering an underlying matrix from a sparse subset of noisy observations. Traditionally, it is assumed that the entries of the matrix are "missi…
Causal Inference with Corrupted Data: Measurement Error, Missing Values, Discretization, and Differential Privacy
Anish Agarwal, Rahul Singh
The US Census Bureau will deliberately corrupt data sets derived from the 2020 US Census, enhancing the privacy of respondents while potentially reducing the precision of economic…
PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators
Anish Agarwal, Abdullah Alomar, Varkey Alumootil +4
We consider offline reinforcement learning (RL) with heterogeneous agents under severe data scarcity, i.e., we only observe a single historical trajectory for every agent under an…