9 papers
Malliavin Calculus for Counterfactual Gradient Estimation in Adaptive Inverse Reinforcement Learning
Vikram Krishnamurthy, Luke Snow
Inverse reinforcement learning (IRL) recovers the loss function of a forward learner from its observed responses. Adaptive IRL aims to reconstruct the loss function of a forward le…
Efficient Counterfactual Estimation of Conditional Greeks via Malliavin-based Weak Derivatives
Vikram Krishnamurthy, Luke Snow
We study counterfactual gradient estimation of conditional loss functionals of diffusion processes. In quantitative finance, these gradients are known as conditional Greeks: the se…
Data-Driven Mechanism Design using Multi-Agent Revealed Preferences
Luke Snow, Vikram Krishnamurthy
We study a sequence of independent one-shot non-cooperative games where agents play equilibria determined by a tunable mechanism. Observing only equilibrium decisions, without para…
Efficient Neural SDE Training using Wiener-Space Cubature
Luke Snow, Vikram Krishnamurthy
A neural stochastic differential equation (SDE) is an SDE with drift and diffusion terms parametrized by neural networks. The training procedure for neural SDEs consists of optimiz…
Malliavin Calculus with Weak Derivatives for Counterfactual Stochastic Optimization
Vikram Krishnamurthy, Luke Snow
We study counterfactual stochastic optimization of conditional loss functionals under misspecified and noisy gradient information. The difficulty is that when the conditioning even…
Multi-Agent Inverse Reinforcement Learning for Identifying Pareto-Efficient Coordination -- A Distributionally Robust Approach
Luke Snow, Vikram Krishnamurthy
Multi-agent inverse reinforcement learning (IRL) aims to identify Pareto-efficient behavior in a multi-agent system, and reconstruct utility functions of the individual agents. Mot…