
The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models
Supervised learning models often make systematic errors on rare subsets ...
read it

Disinformation, Stochastic Harm, and Costly Filtering: A PrincipalAgent Analysis of Regulating Social Media Platforms
The spread of disinformation on social media platforms such as Facebook ...
read it

Efficient Deviation Types and Learning for Hindsight Rationality in ExtensiveForm Games
Hindsight rationality is an approach to playing multiagent, generalsum...
read it

Hindsight and Sequential Rationality of Correlated Play
Driven by recent successes in twoplayer, zerosum game solving and play...
read it

Game Theoretic Malware Detection
Large software platforms (e.g., mobile app stores, social media, email s...
read it

Alternative Function Approximation Parameterizations for Solving Games: An Analysis of fRegression Counterfactual Regret Minimization
Function approximation is a powerful approach for structuring large deci...
read it

Bounds for Approximate RegretMatching Algorithms
A dominant approach to solving large imperfectinformation games is Coun...
read it

A Formal Separation Between Strategic and Nonstrategic Behavior
It is common to make a distinction between `strategic' behavior and othe...
read it

Formalizing the Boundary Between Strategic and Nonstrategic Reasoning
Research in multiagent systems often does not draw a clear distinction b...
read it

Learning in the Repeated Secretary Problem
In the classical secretary problem, one attempts to find the maximum of ...
read it
James R. Wright
is this you? claim profile