Reproduce “Causal Invariance Learning via Efficient Nonconvex Optimization” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhenyu Wang, Yifan Hu, Peter Bühlmann, Zijian Guo
NegDRO identifies causal outcome models by optimizing a continuous objective over predictors and environment weights, allowing negative weights to encourage equal prediction risks across environments instead of enumerating variable subsets. Under additive interventions and identification conditions, its stationary points can approximate the causal model. In synthetic simulations, it scales to 100 covariates, while EILLS and ICP hit runtime limits.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.