Abstract:Both optimization and learning play important roles in a system for intelligent tasks. This talk introduces three types of optimization tasks studied in the machine learning literature, corresponding to the three levels of inverse problems in an intelligent system.?Though a good optimization?algorithm is an essential tool in a learning process, the key task of learning is not simply optimization, i.e., not as misunderstood sometimes in the optimization literature. The key challenges of learning and the current status of efforts will be introduced, and?learning versus optimization?in an intelligent system will be discussed from a unified perspective.