9 papers
Optimal Inference with Black-box Predictions
Lucas Kania, Abhinav Chakraborty, Edward Kennedy +2
Powerful black-box predictive models have motivated many proposals for combining observed data with predictions to perform valid statistical inference. Despite this progress, the f…
On the Equivalence between Neyman Orthogonality and Pathwise Differentiability
Yuxi Chen, Edward H. Kennedy, Sivaraman Balakrishnan
It has been frequently observed that Neyman orthogonality, the central device underlying double/debiased machine learning (Chernozhukov et al., 2018), and pathwise differentiabilit…
The Fundamental Limits of Valid Transport Map Estimation
Sivaraman Balakrishnan
Many modern generative modeling methods, including diffusion models, normalizing flows, and flow matching, estimate transport maps or plans between distributions without explicitly…
On Robust Hypothesis Testing with respect to the Hellinger Distance
Eeshan Modak, Sivaraman Balakrishnan, Ananda Theertha Suresh
We study a variant of the simple hypothesis testing problem where observed samples do not necessarily come from either of the specified distributions, but rather from a close varia…
ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity
Lujing Zhang, Daniel Hsu, Sivaraman Balakrishnan
Multi-group learning is a learning task that focuses on controlling predictors' conditional losses over specified subgroups. We propose ShakyPrepend, a method that leverages tools…
Testing Imprecise Hypotheses
Lucas Kania, Tudor Manole, Larry Wasserman +1
Many scientific applications involve testing theories that are only partially specified. This task often amounts to testing the goodness-of-fit of a candidate distribution while al…