1. Global convergence of policy gradient methods for the linear quadratic regulator;fazel;Proc Int Conf Mach Learn Res,0
2. First Order Methods For Globally Optimal Distributed Controllers Beyond Quadratic Invariance
3. Stochastic gradient learning in neural networks;bottou;Proc Neuro-Nîmes,0
4. The power of interpolation: Understanding the effectiveness of SGD in modern over-parametrized learning;ma;Proc Int Conf Mach Learn Res,0
5. A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization;josz;Proc Adv Neural Inf Process Syst,0