Search Results for author:
Found 25 papers, 5 papers with code
Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability
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
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.
Automated Discovery of Functional Actual Causes in Complex Environments
This paper introduces functional actual cause (FAC), a framework that uses context-specific independencies in the environment to restrict the set of actual causes.
Algorithmic Robustness
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.
Improving the Efficiency of the PC Algorithm by Using Model-Based Conditional Independence Tests
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
Recent work in reinforcement learning has focused on several characteristics of learned policies that go beyond maximizing reward.
Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program
The advances in artificial intelligence enabled by deep learning architectures are undeniable.
SBI: A Simulation-Based Test of Identifiability for Bayesian Causal Inference
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.
Preserving Privacy in Personalized Models for Distributed Mobile Services
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.
How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference
Methods that infer causal dependence from observational data are central to many areas of science, including medicine, economics, and the social sciences.
Causal Inference using Gaussian Processes with Structured Latent Confounders
Latent confounders---unobserved variables that influence both treatment and outcome---can bias estimates of causal effects.
Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates
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.
Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning
Saliency maps are frequently used to support explanations of the behavior of deep reinforcement learning (RL) agents.
Bayesian causal inference via probabilistic program synthesis
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.
The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data
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.
Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning
We show that TOYBOX enables a wide range of experiments and analyses that are impossible in other environments.
Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments
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.
Measuring and Characterizing Generalization in Deep Reinforcement Learning
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.
ToyBox: Better Atari Environments for Testing Reinforcement Learning Agents
It is a widely accepted principle that software without tests has bugs.
Evaluating Causal Models by Comparing Interventional Distributions
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
Specifically, the goal of this work is to learn interpretable causal models from observational data produced by manufacturing lines.
Learning to Generate Networks
We investigate the problem of learning to generate complex networks from data.
A Sound and Complete Algorithm for Learning Causal Models from Relational Data
However, there is no equivalent complete algorithm for learning the structure of relational models, a more expressive generalization of Bayesian networks.
Reasoning about Independence in Probabilistic Models of Relational Data
We extend the theory of d-separation to cases in which data instances are not independent and identically distributed.
Identifying Independence in Relational Models
The rules of d-separation provide a framework for deriving conditional independence facts from model structure.
