Foundational optimization algorithms are the core driving force behind deep learning, evolving from early stochastic gradient descent (SGD) to the widely adopted Adam family. However, as the scale of ...

We consider the problem of fitting a reinforcement learning (RL) model to some given behavioral data under a multi-armed bandit environment. These models have received much attention in recent years ...

This work proposes a framework for global optimization, showing that global optimization is equivalent to optimal strategy formation in a two-armed decision problem with known distributions, based on ...

Understanding how and why humans and other agents persist in repeating past choices—even when these lead to negative outcomes —has intrigued scientists across fields such as neuroscience, behavioral ...

Abstract: This article examines an online distributed optimization problem over an unbalanced digraph, in which a group of nodes in the network tries to collectively search for a minimizer of a ...

We propose a simple and nonparametric solution to this problem, Automatic Prompt Optimization (APO), which is inspired by numerical gradient descent to automatically improve prompts, assuming access ...