23 citations · 44 across the 7 of their papers we have counts for
10 papers
Deep Learning Meets Projective Clustering
Alaa Maalouf, Harry Lang, Daniela Rus +1
A common approach for compressing NLP networks is to encode the embedding layer as a matrix , compute its rank- approximation via SVD, and then…
Sparse Coresets for SVD on Infinite Streams
Vladimir Braverman, Dan Feldman, Harry Lang +2
In streaming Singular Value Decomposition (SVD), -dimensional rows of a possibly infinite matrix arrive sequentially as points in . An -coreset is a (much small…
Provable Filter Pruning for Efficient Neural Networks
Lucas Liebenwein, Cenk Baykal, Harry Lang +2
We present a provable, sampling-based approach for generating compact Convolutional Neural Networks (CNNs) by identifying and removing redundant filters from an over-parameterized…
Improved Algorithms for Time Decay Streams
Vladimir Braverman, Harry Lang, Enayat Ullah +1
In the time-decay model for data streams, elements of an underlying data set arrive sequentially with the recently arrived elements being more important. A common approach for hand…
Nearly Optimal Distinct Elements and Heavy Hitters on Sliding Windows
Vladimir Braverman, Elena Grigorescu, Harry Lang +2
We study the distinct elements and -heavy hitters problems in the sliding window model, where only the most recent elements in the data stream form the underlying set.…
Approximate Convex Hull of Data Streams
Avrim Blum, Vladimir Braverman, Ananya Kumar +2
Given a finite set of points , we would like to find a small subset such that the convex hull of approximately contains . More form…