2 papers
cs.CL2026
Geometric Structure Predicts Per-Example Neighborhood Loss Under PCA Truncation
Sriram Loganathan, Gokul Anand, Ragavan Arivazhagan
Dimensionality reduction can preserve the average performance of text embeddings even when a substantial fraction of their dimensions is removed. Aggregate metrics, however, do not…
cs.CL2026
Sparse PPMI Graph Averaging for Random Indexing Embeddings
Sriram Loganathan, Gokul Anand, Aung Bo Bo +2
We study a specific sparse post-processing pipeline for Random Indexing (RI) on kinship analogies in a small fairytales corpus. The published artifacts use uniform RI context accum…