We strongly support a broad definition of learning theory, including, but not limited to:

• Design and analysis of learning algorithms

• Statistical and computational complexity of learning

• Optimization methods for learning

• Unsupervised, semisupervised, online and active learning

• Interactions with other mathematical fields

• Interactions with statistical physics

• Artificial neural networks, including deep learning

• Highdimensional and nonparametric statistics

• Learning with algebraic or combinatorial structure

• Geometric and topological data analysis

• Bayesian methods in learning

• Planning and control, including reinforcement learning

• Learning with system constraints: e.g. privacy, memory or communication budget

• Learning from complex data: e.g., networks, time series, etc.

• Learning in other settings: e.g. social, economic, and gametheoretic