SITA performs scalable inference-time annealing of flow-based models on molecular systems by substituting energy-based surrogate likelihoods for divergence-based importance weights.
Sequential monte carlo samplers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper shows how one can use Sequential Monte Carlo methods to perform what is typically done using Markov chain Monte Carlo methods. This leads to a general class of principled integration and genetic type optimization methods based on interacting particle systems.
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scalable Inference-Time Annealing with Surrogate Likelihood Estimators
SITA performs scalable inference-time annealing of flow-based models on molecular systems by substituting energy-based surrogate likelihoods for divergence-based importance weights.