DNNs arelargely composed ofmultiplication operations for both forward and backward propagation, which are much more computationally costly than addition [1].

Unlike commonly used iterative ODE solvers that necessitate time discretization, event-based simulations resolve neural network dynamics precisely between spike events.

Unlike commonly used iterative ODE solvers that necessitate time discretization, event-based simulations resolve neural network dynamics precisely between spike events.

Our lower bound analysis shows that the sample complexities ofBSGD cannot be improved for general convexobjectives and nonconvexobjectivesexcept for smooth nonconvexobjectiveswith Lipschitz continuous gradient estimator.

Despite their empirical success, there is alack oftheoretical explorations such asgeneralization properties.