new sec 20.5 (training objectives for deep generative models)

[murphyk]

I added a very short new section on training objectives for deep generative models, going beyond the likelihood maximization approach adopted in most of the book. This is motivated by problems caused by data living on low-dimensional manifolds.

For a long discussion of this topic, see this paper

G. Loaiza-Ganem, B. L. Ross, R. Hosseinzadeh, A. L. Caterini, and J. C. Cresswell, “Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections,” Transactions on Machine Learning Research, Apr. 2024, Available: https://openreview.net/pdf?id=a90WpmSi0I