Online Embedding Compression for Text Classification using Low Rank Matrix Factorization — mentioned by anishacharya

Wed, 16 Jan 2019 03:47:21 GMT

The paper is here: https://arxiv.org/pdf/1811.00641.pdf

Paper and discussion history. A mention is not an endorsement.

Online Embedding Compression for Text Classification using Low Rank Matrix Factorization — mentioned by azhenley

Tue, 15 Jan 2019 18:21:58 GMT

The article's title is actually "New Method for Compressing Neural Networks Better Preserves Accuracy". Summary of a key result: "In one set of experiments, for instance, we showed that our system could shrink a neural network by 90 percent while reducing its accuracy by less than 1%. At the same compression rate, the best prior method reduced the accuracy by about 3.5%." Link to the 2019 AAAI paper: https://arxiv.org/pdf/1811.00641.pdf

Paper and discussion history. A mention is not an endorsement.

Online Embedding Compression for Text Classification using Low Rank Matrix Factorization · HackerPapers discussions

Online Embedding Compression for Text Classification using Low Rank Matrix Factorization — mentioned by anishacharya

Online Embedding Compression for Text Classification using Low Rank Matrix Factorization — mentioned by azhenley