Accurately forecasting central bank policy decisions, particularly those of the Federal Open Market Committee (FOMC) has become increasingly important amid heightened economic uncertainty. While prior studies have used monetary policy texts to predict rate changes, most rely on static classification models that overlook the deliberative nature of policymaking. This study proposes a novel framework that structurally imitates the FOMC's collective decision-making process by modeling multiple large language models (LLMs) as interacting agents. Each agent begins with a distinct initial belief and produces a prediction based on both qualitative policy texts and quantitative macroeconomic indicators. Through iterative rounds, agents revise their predictions by observing the outputs of others, simulating deliberation and consensus formation. To enhance interpretability, we introduce a latent variable representing each agent's underlying belief (e.g., hawkish or dovish), and we theoretically demonstrate how this belief mediates the perception of input information and interaction dynamics. Empirical results show that this debate-based approach significantly outperforms standard LLMs-based baselines in prediction accuracy. Furthermore, the explicit modeling of beliefs provides insights into how individual perspectives and social influence shape collective policy forecasts.

This paper primarily focuses on learning robust visual-force policies in the context of high-precision object assembly tasks. Specifically, we focus on the contact phase of the assembly task where both objects (peg and hole) have made contact and the objective lies in maneuvering the objects to complete the assembly. Moreover, we aim to learn contact-rich manipulation policies with multisensory inputs on limited expert data by expanding human demonstrations via online data augmentation. We develop a simulation environment with a dual-arm robot manipulator to evaluate the effect of augmented expert demonstration data. Our focus is on evaluating the robustness of our model with respect to certain task variations: grasp pose, peg/hole shape, object body shape, scene appearance, camera pose, and force-torque/proprioception noise. We show that our proposed data augmentation method helps in learning a multisensory manipulation policy that is robust to unseen instances of these variations, particularly physical variations such as grasp pose. Additionally, our ablative studies show the significant contribution of force-torque data to the robustness of our model. For additional experiments and qualitative results, we refer to the project webpage at https://bit.ly/47skWXH .

Insurers are increasingly adopting more demand-based strategies to incorporate the indirect effect of premium changes on their policyholders' willingness to stay. However, since in practice both insurers' renewal premia and customers' responses to these premia typically depend on the customer's level of risk, it remains challenging in these strategies to determine how to properly control for this confounding. We therefore consider a causal inference approach in this paper to account for customers' price sensitivity and to deduce optimal, multi-period profit maximizing premium renewal offers. More specifically, we extend the discrete treatment framework of Guelman and Guill\'en (2014) by Extreme Gradient Boosting, or XGBoost, and by multiple imputation to better account for the uncertainty in the counterfactual responses. We additionally introduce the continuous treatment framework with XGBoost to the insurance literature to allow identification of the exact optimal renewal offers and account for any competition in the market by including competitor offers. The application of the two treatment frameworks to a Dutch automobile insurance portfolio suggests that a policy's competitiveness in the market is crucial for a customer's price sensitivity and that XGBoost is more appropriate to describe this than the traditional logistic regression. Moreover, an efficient frontier of both frameworks indicates that substantially more profit can be gained on the portfolio than realized, also already with less churn and in particular if we allow for continuous rate changes. A multi-period renewal optimization confirms these findings and demonstrates that the competitiveness enables temporal feedback of previous rate changes on future demand.

Assume an individual is represented by a multidimensional utility function that maps to the customer satisfaction domain. This function contains non-linear features and numerous feedback loops which may be negative, positive or either depending on market conditions. To illustrate, let's consider hyperbolic discounting, a well-established non-linear feature from behavior economics. As an exponential, small changes in the market interest rate can cause large changes in value perception. Each individual will have a different response ranging from almost none to dramatic changes in consumption and investment behavior. A change in interest rates could dramatically alter the cluster membership.

Numerical Optimization is one of the central techniques in Machine Learning. For many problems it is hard to figure out the best solution directly, but it is relatively easy to set up a loss function that measures how good a solution is - and then minimize the parameters of that function to find the solution. I ended up writing a bunch of numerical optimization routines back when I was first trying to learn javascript. Since I had all this code lying around anyway, I thought that it might be fun to provide some interactive visualizations of how these algorithms work. The cool thing about this post is that the code is all running in the browser, meaning you can interactively set hyper-parameters for each algorithm, change the initial location, and change what function is being called to get a better sense of how these algorithms work.