Considered here is on-line portfolio management aimed at maximizing the long-run growth of financial wealth. The portfolio is repeatedly rebalanced in response to observed returns on diverse assets. Suppose statistical information and related methods are not available - or deemed too diffcult....

We introduce an adaptive importance sampling method for the loss distribution of credit portfolios based on the Robbins-Monro stochastic approximation procedure. After presenting the subtle construction of the algorithm, we apply our adaptive scheme for calculating the risk figures of a typical...

In this paper we prove a deterministic approximation theorem for a sequence of Markov decision processeswith finitely many actions and general state spaces as they appear frequently in economics, game theory and operations research. Using viscosity solution methods no a-priori differentiabililty...

Linking the statistic and the machine learning literature, we provide new general results on the convergence of stochastic approximation schemes and inexact Newton methods. Building on these results, we put forward a new optimization scheme that we call generalized inexact Newton method (GINM)....

In this paper we consider regression models with forecast feedback. Agents' expectations are formed via the recursive estimation of the parameters in an auxiliary model. The learning scheme employed by the agents belongs to the class of stochastic approximation algorithms whose gain sequence is...

While payoff-based learning models are almost exclusively devised for finite action games, where players can test every action, it is harder to design such learning processes for continuous games. We construct a stochastic learning rule, designed for games with continuous action sets, which...

We present a framework for statistical analysis of discrete event systems which combines tools such as simulation of marked point processes, likelihood methods, kernel density estimation and stochastic approximation to enable statistical analysis of the discrete event system, even if...

In this study we consider a linear model with forecast feedback in which boundedly rational agents are learning the parameter values of the rational expectations equilibrium by the OLS learning procedure. We show strong consistency of the OLS estimates under much weaker assumptions on the...

In this paper we consider regression models with forecast feedback. Agents' expectations are formed via the recursive estimation of the parameters in an auxiliary model. The learning scheme employed by the agents belongs to the class of stochastic approximation algorithms whose gain sequence is...

We exploit a unique opportunity to study how a large population of players in the field learn to play a novel game with a complicated and non-intuitive mixed strategy equilibrium.  We argue that standard models of belief-based learning and reinforcement learning are unable to explain the data,...