LoMETab is a rank-r generalization of multiplicative implicit ensembles that strictly enlarges the hypothesis class for r >= 2 and supplies tunable control over predictive diversity via adapter rank and initialization scale.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
BayesLoRA applies diagonal rank-wise variational inference to break LoRA gauge symmetry and learn adapter rank with O(r) parameters.
citing papers explorer
-
LoMETab: Beyond Rank-1 Ensembles for Tabular Deep Learning
LoMETab is a rank-r generalization of multiplicative implicit ensembles that strictly enlarges the hypothesis class for r >= 2 and supplies tunable control over predictive diversity via adapter rank and initialization scale.
-
Learning Adapter Rank via Symmetry Breaking
BayesLoRA applies diagonal rank-wise variational inference to break LoRA gauge symmetry and learn adapter rank with O(r) parameters.