In two, we recognized that many machine learning problems involve minimizing empirical risk functions with well-behaved population risks. Instead of analyzing the non-convex empirical risk directly, ...

Samy Wu Fung, Department of Applied Mathematics and Statistics, Colorado School of Mines Efficient Training of Infinite-depth Neural Networks via Jacobian-free Backpropagation A promising trend in ...

Optimization and statistics are everywhere, touching all engineering disciplines in an ever more sophisticated way. Nowhere are they more important than in the rapidly evolving field of machine ...

Machine learning uncovers opportunities for business optimization hidden in the data lake by supercharging analysis of ever-more-complex information.

Proximal algorithms are useful for obtaining solutions to difficult optimization problems, especially those involving nonsmooth or composite objective functions. A proximal algorithm is one whose ...

When you listen to quantum enthusiasts, you may feel tempted to treat QML as an emerging silver bullet, which it isn’t.

If you rotate an image of a molecular structure, a human can tell the rotated image is still the same molecule, but a machine ...

The earlier edition has been used for a variety of senior-level undergraduate and graduate courses in machine learning, deep learning, mathematical optimization, and reinforcement learning. The second ...