Deterministic particle gradient descent, run forward to uniformity and backward from a new point, generates samples from a data distribution without estimating a score function.
Without this reduction, computing W (s), as required in EFS, becomes numerically infeasible
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Data Generation without Function Estimation
Deterministic particle gradient descent, run forward to uniformity and backward from a new point, generates samples from a data distribution without estimating a score function.