Search Results for author:
Found 3 papers, 0 papers with code
On the Algorithmic Stability and Generalization of Adaptive Optimization Methods
Despite their popularity in deep learning and machine learning in general, the theoretical properties of adaptive optimizers such as Adagrad, RMSProp, Adam or AdamW are not yet fully understood.
Adaptive Sampling Distributed Stochastic Variance Reduced Gradient for Heterogeneous Distributed Datasets
It often leads to the dependence of convergence rate on maximum Lipschitz constant of gradients across the devices.
Policy Optimization In the Face of Uncertainty
Under this framework, the objective function can represented end-to-end as a single computational graph, which allows seamless policy gradient computation via backpropagation through the models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
