In complex real-world environments, traditional (tabular) techniques for solving Reinforcement Learning (RL) do not scale. Function approximation is needed, but unfortunately, existing approaches generally have poor convergence and optimality guarantees. Additionally, for the case of human environments, it is valuable to be able to leverage human input. In this paper we introduce Expanding Valu...

The importance of the global financial system cannot be exaggerated. When a large financial institution becomes problematic and is bailed out, that bank is often claimed as “too big to fail”. On the other hand, to prevent bank’s failure, regulatory authorities adopt the Prompt Corrective Action (PCA) against a bank that violates certain criteria, often measured by its leverage ratio. In this ar...

We consider recommendation in the context of optimal matching, i.e., we need to pair or match a user with an item in an optimal way. The framework is particularly relevant when the supply of an individual item is limited and it can only satisfy a small number of users even though it may be preferred by many. We leverage the methodology of optimal transport of discrete distributions and formulat...

This paper characterizes the optimal bankruptcy exemption for risk averse borrowers who use unsecured contracts but have the possibility of defaulting. It provides a novel general formula — which holds in a wide variety of environments — for the optimal exemption as a function of a few observable sufficient statistics. Knowledge of borrowers’ leverage, the sensitivity of the interest rate sched...

In this work, we derive a generic overcomplete frame thresholding scheme based on risk minimization. Overcomplete frames being favored for analysis tasks such as classification, regression or anomaly detection, we provide a way to leverage those optimal representations in real-world applications through the use of thresholding. We validate the method on a large scale bird activity detection tas...

We study the leverage of firms making large dividend increases. Over the five years following the dividend increase they raise leverage enough to finance the entire dividend increase for that period with debt. This is not explained by trade-off variables or the pecking order. The effect is greatest for big firms with low-powered incentives, suggesting an agency effect whereby they make large di...