
0.25
0.5
0.75
1.25
1.5
1.75
2
DiSCO: Distributed Optimization for Self-Concordant Empirical Loss
Published on Feb 4, 20251891 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