2 citations · 5 across the 11 of their papers we have counts for
12 papers
A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
J. Jon Ryu, Abhin Shah, Gregory W. Wornell
This paper studies a family of estimators based on noise-contrastive estimation (NCE) for learning unnormalized distributions. The main contribution of this work is to provide a un…
Doubly Robust Inference in Causal Latent Factor Models
Alberto Abadie, Anish Agarwal, Raaz Dwivedi +1
This article introduces a new estimator of average treatment effects under unobserved confounding in modern data-rich environments featuring large numbers of units and outcomes. Th…
On Computationally Efficient Learning of Exponential Family Distributions
Abhin Shah, Devavrat Shah, Gregory W. Wornell
We consider the classical problem of learning, with arbitrary accuracy, the natural parameters of a -parameter truncated \textit{minimal} exponential family from i.i.d. samples…
Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge
Abhin Shah, Karthikeyan Shanmugam, Murat Kocaoglu
Causal effect estimation from data typically requires assumptions about the cause-effect relations either explicitly in the form of a causal graph structure within the Pearlian fra…
Group Fairness with Uncertainty in Sensitive Attributes
Abhin Shah, Maohao Shen, Jongha Jon Ryu +4
Learning a fair predictive model is crucial to mitigate biased decisions against minority groups in high-stakes applications. A common approach to learn such a model involves solvi…
On counterfactual inference with unobserved confounding
Abhin Shah, Raaz Dwivedi, Devavrat Shah +1
Given an observational study with independent but heterogeneous units, our goal is to learn the counterfactual distribution for each unit using only one -dimensional sample…
Optimal Compression of Locally Differentially Private Mechanisms
Abhin Shah, Wei-Ning Chen, Johannes Balle +2
Compressing the output of ε-locally differentially private (LDP) randomizers naively leads to suboptimal utility. In this work, we demonstrate the benefits of using schemes that jo…
A Computationally Efficient Method for Learning Exponential Family Distributions
Abhin Shah, Devavrat Shah, Gregory W. Wornell
We consider the question of learning the natural parameters of a parameter minimal exponential family from i.i.d. samples in a computationally and statistically efficient manne…
Selective Regression Under Fairness Criteria
Abhin Shah, Yuheng Bu, Joshua Ka-Wing Lee +4
Selective regression allows abstention from prediction if the confidence to make an accurate prediction is not sufficient. In general, by allowing a reject option, one expects the…
Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge
Abhin Shah, Karthikeyan Shanmugam, Kartik Ahuja
Treatment effect estimation from observational data is a fundamental problem in causal inference. There are two very different schools of thought that have tackled this problem. On…
Treatment Effect Estimation using Invariant Risk Minimization
Abhin Shah, Kartik Ahuja, Karthikeyan Shanmugam +3
Inferring causal individual treatment effect (ITE) from observational data is a challenging problem whose difficulty is exacerbated by the presence of treatment assignment bias. In…
On Learning Continuous Pairwise Markov Random Fields
Abhin Shah, Devavrat Shah, Gregory W. Wornell
We consider learning a sparse pairwise Markov Random Field (MRF) with continuous-valued variables from i.i.d samples. We adapt the algorithm of Vuffray et al. (2019) to this settin…