Bloomberg L.P.

Designing Better Approximations for Machine Learning

In the era of Machine Learning (ML), Natural Language Processing (NLP), and Artificial Intelligence (AI), high-dimensional matrices are ubiquitous. In these fields (and in many others), matrices are ...
Nature

Deep Learning and Neural Network Approximations

Deep learning has emerged as a transformative paradigm in modern computational science, leveraging neural networks to approximate complex functions across a variety of domains. Central to this ...
Harvard Business School

Learning and Equilibrium as Useful Approximations: Accuracy of Prediction on Randomly Selected Constant Sum Games

Erev, Ido, Alvin E. Roth, R. Slonim, and Greg Barron. "Learning and Equilibrium as Useful Approximations: Accuracy of Prediction on Randomly Selected Constant Sum Games." Special Issue on Behavioral ...
Harvard Business School

Learning and Equilibrium As Useful Approximations: Accuracy of Prediction on Randomly Selected Constant Sum Games

Erev, Ido, Alvin E. Roth, Robert L. Slonim, and Greg Barron. "Learning and Equilibrium As Useful Approximations: Accuracy of Prediction on Randomly Selected Constant Sum Games." Harvard Business ...