Search Results for author:
Found 5 papers, 0 papers with code
Reinforcement Learning with Differential Privacy
Motivated by high-stakes decision-making domains like personalized medicine where user information is inherently sensitive, we design privacy preserving exploration policies for episodic reinforcement learning (RL).
Oracle-Efficient Differentially Private Learning with Public Data
Due to statistical lower bounds on the learnability of many function classes under privacy constraints, there has been recent interest in leveraging public data to improve the performance of private learning algorithms.
A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms
This stylized setup offers the distinct capability of testing fairness interventions beyond observational data and against an unbiased benchmark.
The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
To this end, we first conduct interviews with data scientists to understand what constitutes disagreement between explanations generated by different methods for the same model prediction, and introduce a novel quantitative framework to formalize this understanding.
What Would the Expert $do(\cdot)$?: Causal Imitation Learning
Both approaches are able to find policies that match the result of a query to an unconfounded expert.
