4 papers
Stochastic Gradients under Nuisances
Facheng Yu, Ronak Mehta, Alex Luedtke +1
Stochastic gradient optimization is the dominant learning paradigm for a variety of scenarios, from classical supervised learning to modern self-supervised learning. We consider st…
Sinkhorn Treatment Effects: A Causal Optimal Transport Measure
Medha Agarwal, Alex Luedtke
We introduce the Sinkhorn treatment effect, an entropic optimal transport measure of divergence between counterfactual distributions. Unlike classical quantities such as the averag…
DoubleGen: Debiased Generative Modeling of Counterfactuals
Alex Luedtke, Kenji Fukumizu
Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who rec…
Coreset selection for the Sinkhorn divergence and generic smooth divergences
Alex Kokot, Alex Luedtke
We introduce CO2, an efficient algorithm to produce convexly-weighted coresets with respect to generic smooth divergences. By employing a functional Taylor expansion, we show a loc…