no code implementations • 12 Nov 2022 • Erica Cai, Andrew Mcgregor, David Jensen
We propose such a pre-processing step for the PC algorithm which relies on performing CI tests on a few randomly selected large conditioning sets.
1 code implementation • 19 Sep 2022 • Katherine Avery, Jack Kenney, Pracheta Amaranath, Erica Cai, David Jensen
Recent work in reinforcement learning has focused on several characteristics of learned policies that go beyond maximizing reward.
no code implementations • 10 Jun 2021 • Jeff Druce, James Niehaus, Vanessa Moody, David Jensen, Michael L. Littman
The advances in artificial intelligence enabled by deep learning architectures are undeniable.
no code implementations • 23 Feb 2021 • Sam Witty, David Jensen, Vikash Mansinghka
This paper introduces simulation-based identifiability (SBI), a procedure for testing the identifiability of queries in Bayesian causal inference approaches that are implemented as probabilistic programs.
no code implementations • 14 Jan 2021 • Akanksha Atrey, Prashant Shenoy, David Jensen
We present Pelican, a privacy-preserving personalization system for context-aware mobile services that leverages both device and cloud resources to personalize ML models while minimizing the risk of privacy leakage for users.
no code implementations • 6 Oct 2020 • Amanda Gentzel, Purva Pruthi, David Jensen
Methods that infer causal dependence from observational data are central to many areas of science, including medicine, economics, and the social sciences.
no code implementations • ICML 2020 • Sam Witty, Kenta Takatsu, David Jensen, Vikash Mansinghka
Latent confounders---unobserved variables that influence both treatment and outcome---can bias estimates of causal effects.
no code implementations • ACL 2020 • Katherine A. Keith, David Jensen, Brendan O'Connor
For example, an individual's entire history of social media posts or the content of a news article could provide a rich measurement of multiple confounders.
1 code implementation • ICLR 2020 • Akanksha Atrey, Kaleigh Clary, David Jensen
Saliency maps are frequently used to support explanations of the behavior of deep reinforcement learning (RL) agents.
no code implementations • 30 Oct 2019 • Sam Witty, Alexander Lew, David Jensen, Vikash Mansinghka
This approach makes it straightforward to incorporate data from atomic interventions, as well as shift interventions, variance-scaling interventions, and other interventions that modify causal structure.
no code implementations • NeurIPS 2019 • Amanda Gentzel, Dan Garant, David Jensen
However, evaluation techniques for causal modeling algorithms have remained somewhat primitive, limiting what we can learn from experimental studies of algorithm performance, constraining the types of algorithms and model representations that researchers consider, and creating a gap between theory and practice.
2 code implementations • 7 May 2019 • Emma Tosch, Kaleigh Clary, John Foley, David Jensen
We show that TOYBOX enables a wide range of experiments and analyses that are impossible in other environments.
1 code implementation • 12 Apr 2019 • Kaleigh Clary, Emma Tosch, John Foley, David Jensen
Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a single environment.
no code implementations • 7 Dec 2018 • Sam Witty, Jun Ki Lee, Emma Tosch, Akanksha Atrey, Michael Littman, David Jensen
We re-examine what is meant by generalization in RL, and propose several definitions based on an agent's performance in on-policy, off-policy, and unreachable states.
3 code implementations • 6 Dec 2018 • John Foley, Emma Tosch, Kaleigh Clary, David Jensen
It is a widely accepted principle that software without tests has bugs.
no code implementations • 16 Aug 2016 • Dan Garant, David Jensen
The predominant method for evaluating the quality of causal models is to measure the graphical accuracy of the learned model structure.
no code implementations • 13 May 2016 • Katerina Marazopoulou, Rumi Ghosh, Prasanth Lade, David Jensen
Specifically, the goal of this work is to learn interpretable causal models from observational data produced by manufacturing lines.
no code implementations • 22 May 2014 • James Atwood, Don Towsley, Krista Gile, David Jensen
We investigate the problem of learning to generate complex networks from data.
no code implementations • 26 Sep 2013 • Marc Maier, Katerina Marazopoulou, David Arbour, David Jensen
However, there is no equivalent complete algorithm for learning the structure of relational models, a more expressive generalization of Bayesian networks.
no code implementations • 18 Feb 2013 • Marc Maier, Katerina Marazopoulou, David Jensen
We extend the theory of d-separation to cases in which data instances are not independent and identically distributed.
no code implementations • 15 Jun 2012 • Marc Maier, David Jensen
The rules of d-separation provide a framework for deriving conditional independence facts from model structure.