Learning (cs.LG)

Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastability

Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks

How Well Can Generative Adversarial Networks Learn Densities: A Nonparametric View

Fisher-Rao Metric, Geometry, and Complexity of Neural Networks

Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP

Learning with Square Loss: Localization through Offset Rademacher Complexity

Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions