DiSCO: Distributed Optimization for Self-Concordant Empirical Loss thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

DiSCO: Distributed Optimization for Self-Concordant Empirical Loss

Published on Dec 05, 20151888 Views

We propose a new distributed algorithm for empirical risk minimization in machine learning. The algorithm is based on an inexact damped Newton method, where the inexact Newton steps are computed by a

Related categories