Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Matrix Decomposition
Hanie Sedghi, Anima Anandkumar, Edmond Jonckheere
–Neural Information Processing Systems
In this paper, we consider a multi-step version of the stochastic ADMM method with efficient guarantees for high-dimensional problems. We first analyze the simple setting, where the optimization problem consists of a loss function and a single regularizer (e.g.
Neural Information Processing Systems
Feb-9-2025, 13:33:04 GMT
- Country:
- North America > United States
- California
- Los Angeles County > Los Angeles (0.28)
- Orange County > Irvine (0.04)
- Illinois (0.04)
- California
- North America > United States
- Technology: