Anmelden
Einblick - Variational Inference Optimization
VISA: Variational Inference with Sequential Sample-Average Approximations
VISA optimizes variational inference efficiently by reusing samples, reducing computational cost.
Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inference
Optimizing amortized variational inference using Sequential Monte Carlo for inclusive KL minimization.
Variational Inference with Sequential Sample-Average Approximations: A Detailed Analysis
VISA optimizes forward KL-divergence efficiently.
Joint Control Variate for Faster Black-Box Variational Inference: A Comprehensive Study
The authors propose a new "joint" control variate to reduce variance from both data subsampling and Monte Carlo sampling, leading to faster optimization in various applications.
Produkte
© 2024 by Linnk AI