We present an efficient coresets-based neural network compression algorithm that sparsifies
the parameters of a trained fully-connected neural network in a manner that provably …

We examine a class of embeddings based on structured random matrices with orthogonal
rows which can be applied in many machine learning applications including dimensionality …

Transformer networks are able to capture patterns in data coming from many domains (text,
images, videos, proteins, etc.) with little or no change to architecture components. We …

We introduce a family of pruning algorithms that sparsifies the parameters of a trained model
in a way that approximately preserves the model's predictive accuracy. Our algorithms use a …

We present an in-depth examination of the effectiveness of radial basis function kernel
(beyond Gaussian) estimators based on orthogonal random feature maps. We show that …

We propose a scheme for recycling Gaussian random vectors into structured matrices to ap-
proximate various kernel functions in sublin-ear time via random embeddings. Our frame …

We consider an efficient computational framework for speeding up several machine learning
algorithms with almost no loss of accuracy. The proposed framework relies on projections …

Many hashing methods, especially those that are in the data-dependent category with good
learning accuracy, are still inefficient when dealing with three critical problems in modern …

This review considers methods and algorithms for fast estimation of distance/similarity
measures between initial data from vector representations with binary or integer-valued …

Binary embeddings provide efficient and powerful ways to perform operations on large scale
data. However binary embedding typically requires long codes in order to preserve the …