Asia
Scalable Robust Matrix Factorization with Nonconvex Loss
Neural Information Processing Systems http://nips.cc/
e589022774244df75b97eae18bb3628d-Supplemental-Conference.pdf
But despite its wide applicability (see 2.2) and elegance, convergence theory for CCCP is quite limited.
TheFirstOptimalAccelerationofHigh-Order MethodsinSmoothConvexOptimization
Whenp = 1, first-order methods, such as gradient descent, are typically usedforsolvingproblem(1).
TheFirstOptimalAccelerationofHigh-Order MethodsinSmoothConvexOptimization
Whenp = 1, first-order methods, such as gradient descent, are typically usedforsolvingproblem(1).
End-to-End Learning on 3D Protein Structure for Interface Prediction
Raphael Townshend, Rishi Bedi, Patricia Suriana, Ron Dror
Toinvestigatethisproblem, wemine theProtein Data Bank (PDB) [1]toconstruct alargedataset of protein complex structures for which structures of the individual proteins on their own are not available.