Statistical Learning
Bidirectional Learning for Offline Infinite-width Model-based Optimization Can (Sam) Chen
The code is available here.
SGD: TheRoleofImplicitRegularization,Batch-size andMultipleEpochs
The goal is to perform the minimization based only on samplesS = {z1,...,zn}drawn i.i.d.
Quantum Algorithms for Non-smooth Non-convex Optimization
This paper considers the problem of finding the (ฮด,วซ)-Goldstein stationary point of the Lipschitz continuous objective, which is a rich funct ion class to cover a large number of important applications. We construct a nove l zeroth-order quantum estimator for the gradient of the smoothed surrogate.
Asymptotics for Sketching in Least Squares Regression
We consider a least squares regression problem where the data has been generated from alinear model, and weareinterested tolearn theunknownregression parameters.
HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs
Naganand Yadati, Madhav Nimishakavi, Prateek Yadav, Vikram Nitin, Anand Louis, Partha Talukdar
Neural Information Processing Systems http://nips.cc/