3 papers
cs.LG2020
Differentiable Unsupervised Feature Selection based on a Gated Laplacian
Ofir Lindenbaum, Uri Shaham, Jonathan Svirsky +2
Scientific observations may consist of a large number of variables (features). Identifying a subset of meaningful features is often ignored in unsupervised learning, despite its po…
cs.LG2020
The Spectral Underpinning of word2vec
Ariel Jaffe, Yuval Kluger, Ofir Lindenbaum +3
word2vec due to Mikolov \textit{et al.} (2013) is a word embedding method that is widely used in natural language processing. Despite its great success and frequent use, theoretica…
math.ST2018
Multidimensional Scaling of Noisy High Dimensional Data
Erez Peterfreund, Matan Gavish
Multidimensional Scaling (MDS) is a classical technique for embedding data in low dimensions, still in widespread use today. Originally introduced in the 1950's, MDS was not design…