A graduate lecture script covering deep learning methods for high-dimensional dynamic stochastic models, including deep equilibrium nets, physics-informed neural networks, deep surrogate models, and Gaussian processes, with applications to macroeconomics, asset pricing, and climate economics.

An online research resource featuring chapters from Risk, Uncertainty and Value, developing concepts and tools for uncertainty characterization in nonlinear stochastic equilibrium models.

Volume I covers dynamic programming theory and applications for finite state spaces, including operators and fixed points, Markov dynamics, optimal stopping, and Markov decision processes.

Volume II extends the finite state framework to general state spaces, covering abstract dynamic programs, stochastic discounting, valuation, recursive decision processes, and continuous time.

This book is an introduction to economic networks and it emphasizes quantitative modeling, with the main underlying tools being graph theory, linear algebra, fixed point theory and programming.