A unified framework shows that NCE, RLR, MIS, and bridge sampling are equivalent under specific conditions for energy-based models, enabling new estimators.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
SSNG replaces sampling-based updates in MHNG with symmetric self-supervised representation alignment using Gumbel-Softmax for discrete messages, yielding higher linear-probe classification accuracy on CIFAR-10 and ImageNet-100 than referential, reconstruction, or MHNG baselines.
citing papers explorer
-
A unifying view of contrastive learning, importance sampling, and bridge sampling for energy-based models
A unified framework shows that NCE, RLR, MIS, and bridge sampling are equivalent under specific conditions for energy-based models, enabling new estimators.
-
SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication
SSNG replaces sampling-based updates in MHNG with symmetric self-supervised representation alignment using Gumbel-Softmax for discrete messages, yielding higher linear-probe classification accuracy on CIFAR-10 and ImageNet-100 than referential, reconstruction, or MHNG baselines.