107 citations · 140 across the 9 of their papers we have counts for
10 papers
A simple and provable algorithm for sparse diagonal CCA
Megasthenis Asteris, Anastasios Kyrillidis, Oluwasanmi Koyejo +1
Given two sets of variables, derived from a common set of samples, sparse Canonical Correlation Analysis (CCA) seeks linear combinations of a small number of variables in each set,…
Trading-off variance and complexity in stochastic gradient descent
Vatsal Shah, Megasthenis Asteris, Anastasios Kyrillidis +1
Stochastic gradient descent is the method of choice for large-scale machine learning problems, by virtue of its light complexity per iteration. However, it lags behind its non-stoc…
Bipartite Correlation Clustering -- Maximizing Agreements
Megasthenis Asteris, Anastasios Kyrillidis, Dimitris Papailiopoulos +1
In Bipartite Correlation Clustering (BCC) we are given a complete bipartite graph with `+' and `-' edges, and we seek a vertex clustering that maximizes the number of agreement…
Sparse PCA via Bipartite Matchings
Megasthenis Asteris, Dimitris Papailiopoulos, Anastasios Kyrillidis +1
We consider the following multi-component sparse PCA problem: given a set of data points, we seek to extract a small number of sparse components with disjoint supports that jointly…
Stay on path: PCA along graph paths
Megasthenis Asteris, Anastasios Kyrillidis, Alexandros G. Dimakis +2
We introduce a variant of (sparse) PCA in which the set of feasible support sets is determined by a graph. In particular, we consider the following setting: given a directed acycli…
On Approximating the Sum-Rate for Multiple-Unicasts
Karthikeyan Shanmugam, Megasthenis Asteris, Alexandros G. Dimakis
We study upper bounds on the sum-rate of multiple-unicasts. We approximate the Generalized Network Sharing Bound (GNS cut) of the multiple-unicasts network coding problem with …
Repairable Fountain Codes
Megasthenis Asteris, Alexandros G. Dimakis
We introduce a new family of Fountain codes that are systematic and also have sparse parities. Given an input of symbols, our codes produce an unbounded number of output symbol…
The Sparse Principal Component of a Constant-rank Matrix
Megasthenis Asteris, Dimitris S. Papailiopoulos, George N. Karystinos
The computation of the sparse principal component of a matrix is equivalent to the identification of its principal submatrix with the largest maximum eigenvalue. Finding this optim…
XORing Elephants: Novel Erasure Codes for Big Data
Maheswaran Sathiamoorthy, Megasthenis Asteris, Dimitris Papailiopoulos +4
Distributed storage systems for large clusters typically use replication to provide reliability. Recently, erasure codes have been used to reduce the large storage overhead of thre…
Sparse Principal Component of a Rank-deficient Matrix
Megasthenis Asteris, Dimitris S. Papailiopoulos, George N. Karystinos
We consider the problem of identifying the sparse principal component of a rank-deficient matrix. We introduce auxiliary spherical variables and prove that there exists a set of ca…