Anish Acharya, PhD

Online Embedding Compression for Text Classification using Low Rank Matrix Factorization

Anish Acharya, R Goel, A Metallinou, I Dhillon

AAAI Conference on Artificial Intelligence (AAAI), 2019 · Spotlight — 5-minute presentation

Compresses the word-embedding layer during training with low-rank factorization, reaching 90% compression with minimal accuracy loss and no added latency.

All publications · Research