Search Results for author:
Found 4 papers, 2 papers with code
A Projection Method for Metric-Constrained Optimization
We outline a new approach for solving optimization problems which enforce triangle inequalities on output variables.
Estimating the Spectral Density of Large Implicit Matrices
However, naive eigenvalue estimation is computationally expensive even when the matrix can be represented; in many of these situations the matrix is so large as to only be available implicitly via products with vectors.
Semidefinite approximations of the matrix logarithm
As such, we introduce strategies for constructing semidefinite approximations that we expect will be useful, more generally, for studying the approximation power of functions with small semidefinite representations.
Optimization and Control
Analyzing Hogwild Parallel Gaussian Gibbs Sampling
Sampling inference methods are computationally difficult to scale for many models in part because global dependencies can reduce opportunities for parallel computation.
