Optimization and Control (math.OC)

Statistical Inference for the Population Landscape via Moment Adjusted Stochastic Gradients

Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits

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

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

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