We introduce contextual stochastic bilevel optimization (CSBO) – a stochastic bilevel optimization template with the lower-level problem minimizing an expectation conditioned on some contextual information and the upper-level decision variable. This framework captures important applications such as meta-learning, Wasserstein distributionally robust optimization with side information (WDRO-SI), and instrumental variable regression (IV). Due to the presence of contextual information, existing sing…