@InProceedings{senuma-aizawa:2016:COLING,
  author    = {Senuma, Hajime  and  Aizawa, Akiko},
  title     = {Learning Succinct Models: Pipelined Compression with L1-Regularization, Hashing, Elias-Fano Indices, and Quantization},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {2774--2784},
  abstract  = {The recent proliferation of smart devices necessitates
	  methods to learn small-sized models.
	This paper demonstrates that
	if there are $m$ features in total but
	only $n = o(\sqrt{m})$ features are required to distinguish examples,
	with $\Omega(\log m)$ training examples and reasonable settings,
	it is possible to obtain a good model in a \textit{succinct} representation
	using $n \log\_2 \frac{m}{n} + o(m)$ bits,
	by using a pipeline of existing compression methods: L1-regularized logistic
	regression, feature hashing, Elias--Fano indices, and randomized quantization.
	An experiment shows that a noun phrase chunking task
	for which an existing library requires 27 megabytes can be compressed to less
	than 13 \underline{kilo}bytes without notable loss of accuracy.},
  url       = {http://aclweb.org/anthology/C16-1261}
}