Subsampling in SGLD does not asymptotically reduce the total computation needed for accurate posterior sampling in typical exponential-family models.
Lower Bounds for the Total Variation Distance Given Means and Variances of Distributions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
For arbitrary two probability measures on real d-space with given means and variances (covariance matrices), we provide lower bounds for their total variation distance. In the one-dimensional case, a tight bound is given.
fields
stat.CO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
No Free Lunch for Stochastic Gradient Langevin Dynamics
Subsampling in SGLD does not asymptotically reduce the total computation needed for accurate posterior sampling in typical exponential-family models.