Dimension d = O(m^{-2} log n) nearly achieves the optimal margin m^rd(+∞, A) for retrieval embeddings, with matching lower bounds showing d = O(k log(n/k)) suffices and is necessary for m = Θ(k^{-1/2}) on k-sparse query matrices.
Proceedings of the 38th International Conference on Machine Learning (ICML) , pages =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
FaithIR, a pixel-domain flow-matching infrared super-resolution model with patch-level structural conditioning, produces more task-faithful reconstructions that improve downstream detection and segmentation.
citing papers explorer
-
Is Dimensionality a Barrier for Retrieval Models?
Dimension d = O(m^{-2} log n) nearly achieves the optimal margin m^rd(+∞, A) for retrieval embeddings, with matching lower bounds showing d = O(k log(n/k)) suffices and is necessary for m = Θ(k^{-1/2}) on k-sparse query matrices.
-
FaithIR: Rethinking Infrared Image Super-Resolution from Perceptual Sharpness to Task Relevant Fidelity
FaithIR, a pixel-domain flow-matching infrared super-resolution model with patch-level structural conditioning, produces more task-faithful reconstructions that improve downstream detection and segmentation.