Christoffel-DPS is a distribution-free optimal sensor placement framework for diffusion posterior sampling that provides non-asymptotic recovery bounds and outperforms Gaussian baselines on non-Gaussian benchmarks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Develops a position-conditioned offline RL architecture with Point Attention for extracting policies that generalize across varying sensor placements in fluid control tasks.
citing papers explorer
-
Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions
Christoffel-DPS is a distribution-free optimal sensor placement framework for diffusion posterior sampling that provides non-asymptotic recovery bounds and outperforms Gaussian baselines on non-Gaussian benchmarks.
-
Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction
Develops a position-conditioned offline RL architecture with Point Attention for extracting policies that generalize across varying sensor placements in fluid control tasks.