Search Results for author: David Jensen

Found 25 papers, 5 papers with code

Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability

no code implementations25 Nov 2024 Jatin Nainani, Sankaran Vaidyanathan, AJ Yeung, Kartik Gupta, David Jensen

For instance, it is unclear whether the models generalization results from reusing the same circuit components, the components behaving differently, or the use of entirely different components.

Compositional Models for Estimating Causal Effects

no code implementations25 Jun 2024 Purva Pruthi, David Jensen

We discover novel benefits of the compositional approach in causal inference - systematic generalization to estimate counterfactual outcomes of unseen combinations of components and improved overlap guarantees between treatment and control groups compared to the classical methods for causal effect estimation.

Causal Inference counterfactual +1

Automated Discovery of Functional Actual Causes in Complex Environments

no code implementations16 Apr 2024 Caleb Chuck, Sankaran Vaidyanathan, Stephen Giguere, Amy Zhang, David Jensen, Scott Niekum

This paper introduces functional actual cause (FAC), a framework that uses context-specific independencies in the environment to restrict the set of actual causes.

Attribute Reinforcement Learning (RL)

Algorithmic Robustness

no code implementations17 Oct 2023 David Jensen, Brian LaMacchia, Ufuk Topcu, Pamela Wisniewski

Algorithmic robustness refers to the sustained performance of a computational system in the face of change in the nature of the environment in which that system operates or in the task that the system is meant to perform.

Fairness

Improving the Efficiency of the PC Algorithm by Using Model-Based Conditional Independence Tests

no code implementations12 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.

Measuring Interventional Robustness in Reinforcement Learning

1 code implementation19 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.

Fairness reinforcement-learning +2

SBI: A Simulation-Based Test of Identifiability for Bayesian Causal Inference

no code implementations23 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.

Causal Inference Experimental Design +1

Preserving Privacy in Personalized Models for Distributed Mobile Services

no code implementations14 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.

Attribute Privacy Preserving

How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference

no code implementations6 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.

Causal Inference

Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates

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.

Causal Inference

Bayesian causal inference via probabilistic program synthesis

no code implementations30 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.

Causal Inference Probabilistic Programming +1

The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data

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.

Causal Inference Fairness +1

Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments

1 code implementation12 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.

Atari Games Deep Reinforcement Learning +2

Measuring and Characterizing Generalization in Deep Reinforcement Learning

no code implementations7 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.

Deep Reinforcement Learning reinforcement-learning +2

Evaluating Causal Models by Comparing Interventional Distributions

no code implementations16 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.

Causal Discovery for Manufacturing Domains

no code implementations13 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.

Causal Discovery

Learning to Generate Networks

no code implementations22 May 2014 James Atwood, Don Towsley, Krista Gile, David Jensen

We investigate the problem of learning to generate complex networks from data.

A Sound and Complete Algorithm for Learning Causal Models from Relational Data

no code implementations26 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.

Causal Discovery

Reasoning about Independence in Probabilistic Models of Relational Data

no code implementations18 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.

Identifying Independence in Relational Models

no code implementations15 Jun 2012 Marc Maier, David Jensen

The rules of d-separation provide a framework for deriving conditional independence facts from model structure.

Cannot find the paper you are looking for? You can Submit a new open access paper.