Binary embeddings with structured hashed projections

by   Anna Choromanska, et al.

We consider the hashing mechanism for constructing binary embeddings, that involves pseudo-random projections followed by nonlinear (sign function) mappings. The pseudo-random projection is described by a matrix, where not all entries are independent random variables but instead a fixed "budget of randomness" is distributed across the matrix. Such matrices can be efficiently stored in sub-quadratic or even linear space, provide reduction in randomness usage (i.e. number of required random values), and very often lead to computational speed ups. We prove several theoretical results showing that projections via various structured matrices followed by nonlinear mappings accurately preserve the angular distance between input high-dimensional vectors. To the best of our knowledge, these results are the first that give theoretical ground for the use of general structured matrices in the nonlinear setting. In particular, they generalize previous extensions of the Johnson-Lindenstrauss lemma and prove the plausibility of the approach that was so far only heuristically confirmed for some special structured matrices. Consequently, we show that many structured matrices can be used as an efficient information compression mechanism. Our findings build a better understanding of certain deep architectures, which contain randomly weighted and untrained layers, and yet achieve high performance on different learning tasks. We empirically verify our theoretical findings and show the dependence of learning via structured hashed projections on the performance of neural network as well as nearest neighbor classifier.


page 1

page 2

page 3

page 4


Invariance principle of random projection for the norm

Johnson-Lindenstrauss guarantees certain topological structure is preser...

Fast nonlinear embeddings via structured matrices

We present a new paradigm for speeding up randomized computations of sev...

Bilinear Random Projections for Locality-Sensitive Binary Codes

Locality-sensitive hashing (LSH) is a popular data-independent indexing ...

Analysis of SparseHash: an efficient embedding of set-similarity via sparse projections

Embeddings provide compact representations of signals in order to perfor...

TripleSpin - a generic compact paradigm for fast machine learning computations

We present a generic compact computational framework relying on structur...

Concentration of Random Feature Matrices in High-Dimensions

The spectra of random feature matrices provide essential information on ...

Demixing Structured Superposition Signals from Periodic and Aperiodic Nonlinear Observations

We consider the demixing problem of two (or more) structured high-dimens...

Please sign up or login with your details

Forgot password? Click here to reset