NM-PPG optimizes non-myopic acquisition policies for costly features by enabling pathwise gradients via continuous relaxation and straight-through rollouts in POMDPs, outperforming SOTA baselines.
Categorical reparameterization with gumbel-softmax
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
WTA bottlenecks enforce highly symbolic, disentangled categorical representations of latent factors under defined conditions in multi-task DNNs, shown via theorem and experiments on two datasets.
citing papers explorer
-
Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients
NM-PPG optimizes non-myopic acquisition policies for costly features by enabling pathwise gradients via continuous relaxation and straight-through rollouts in POMDPs, outperforming SOTA baselines.
-
Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
WTA bottlenecks enforce highly symbolic, disentangled categorical representations of latent factors under defined conditions in multi-task DNNs, shown via theorem and experiments on two datasets.