Large language models (LLMs) with hundreds of billions of parameters have sparked a new
wave of exciting AI applications. However, they are computationally expensive at inference …

Many convex optimization problems with important applications in machine learning are
formulated as empirical risk minimization (ERM). There are several examples: linear and …

The expressive power and computational complexity of deep visual generative models, such
as flow-based and autoregressive (AR) models, have gained considerable interest for their …