BOOOM parametrizes Stiefel manifold optimization into Euclidean angle space using global Givens rotations and solves it with recursive modified pattern search for loss-agnostic black-box problems.
O-vit: Orthogonal vision transformer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2roles
method 1polarities
use method 1representative citing papers
Replacing additive residual connections with a gated rank-1 delta update that interpolates identity, projection, and reflection slightly improves language modeling and downstream averages in reported 124M/353M runs.
citing papers explorer
-
BOOOM: Loss-Function-Agnostic Black-Box Optimization over Orthonormal Manifolds for Machine Learning and Statistical Inference
BOOOM parametrizes Stiefel manifold optimization into Euclidean angle space using global Givens rotations and solves it with recursive modified pattern search for loss-agnostic black-box problems.
-
Deep Delta Learning
Replacing additive residual connections with a gated rank-1 delta update that interpolates identity, projection, and reflection slightly improves language modeling and downstream averages in reported 124M/353M runs.