15 citations · 68 across the 22 of their papers we have counts for
22 papers
Provable Pruning for Efficient 3D Gaussian Splatting via Coresets
Waseem Mousa, Alaa Maalouf
3D Gaussian Splatting (3DGS) enables high-quality real-time novel-view synthesis, but practical scenes often contain millions of Gaussians, making compression essential for deploym…
Follow Anything: Open-set detection, tracking, and following in real-time
Alaa Maalouf, Ninad Jadhav, Krishna Murthy Jatavallabhula +5
Tracking and following objects of interest is critical to several robotics use cases, ranging from industrial automation to logistics and warehousing, to healthcare and security. I…
Dataset Distillation Meets Provable Subset Selection
Murad Tukan, Alaa Maalouf, Margarita Osadchy
Deep learning has grown tremendously over recent years, yielding state-of-the-art results in various fields. However, training such models requires huge amounts of data, increasing…
On the Size and Approximation Error of Distilled Sets
Alaa Maalouf, Murad Tukan, Noel Loo +3
Dataset Distillation is the task of synthesizing small datasets from large ones while still retaining comparable predictive accuracy to the original uncompressed dataset. Despite s…
AutoCoreset: An Automatic Practical Coreset Construction Framework
Alaa Maalouf, Murad Tukan, Vladimir Braverman +1
A coreset is a tiny weighted subset of an input set, that closely resembles the loss function, with respect to a certain set of queries. Coresets became prevalent in machine learni…
Provable Data Subset Selection For Efficient Neural Network Training
Murad Tukan, Samson Zhou, Alaa Maalouf +3
Radial basis function neural networks (\emph{RBFNN}) are {well-known} for their capability to approximate any continuous function on a closed bounded set with arbitrary precision g…
Deep Learning on Home Drone: Searching for the Optimal Architecture
Alaa Maalouf, Yotam Gurfinkel, Barak Diker +3
We suggest the first system that runs real-time semantic segmentation via deep learning on a weak micro-computer such as the Raspberry Pi Zero v2 (whose price was $15) attached to…
Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions
Murad Tukan, Loay Mualem, Alaa Maalouf
Pruning is one of the predominant approaches for compressing deep neural networks (DNNs). Lately, coresets (provable data summarizations) were leveraged for pruning DNNs, adding th…
Obstacle Aware Sampling for Path Planning
Murad Tukan, Alaa Maalouf, Dan Feldman +1
Many path planning algorithms are based on sampling the state space. While this approach is very simple, it can become costly when the obstacles are unknown, since samples hitting…
Coresets for Data Discretization and Sine Wave Fitting
Alaa Maalouf, Murad Tukan, Eric Price +2
In the \emph{monitoring} problem, the input is an unbounded stream of integers in , that are obtained from a sensor (such as GPS or heart b…
Introduction to Coresets: Approximated Mean
Alaa Maalouf, Ibrahim Jubran, Dan Feldman
A \emph{strong coreset} for the mean queries of a set in is a small weighted subset , which provably approximates its sum of squared distances to…
A Unified Approach to Coreset Learning
Alaa Maalouf, Gilad Eini, Ben Mussay +2
Coreset of a given dataset and loss function is usually a small weighed set that approximates this loss for every query from a given set of queries. Coresets have shown to be very…
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
Lucas Liebenwein, Alaa Maalouf, Oren Gal +2
We present a novel global compression framework for deep neural networks that automatically analyzes each layer to identify the optimal per-layer compression ratio, while simultane…
Provably Approximated ICP
Ibrahim Jubran, Alaa Maalouf, Ron Kimmel +1
The goal of the \emph{alignment problem} is to align a (given) point cloud to another (observed) point cloud . That is, to compute…
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…
Compressed Deep Networks: Goodbye SVD, Hello Robust Low-Rank Approximation
Murad Tukan, Alaa Maalouf, Matan Weksler +1
A common technique for compressing a neural network is to compute the -rank approximation of the matrix that corresponds to a ful…
Coresets for Near-Convex Functions
Murad Tukan, Alaa Maalouf, Dan Feldman
Coreset is usually a small weighted subset of input points in , that provably approximates their loss function for a given set of queries (models, classifiers, et…
Faster PAC Learning and Smaller Coresets via Smoothed Analysis
Alaa Maalouf, Ibrahim Jubran, Murad Tukan +1
PAC-learning usually aims to compute a small subset (-sample/net) from items, that provably approximates a given loss function for every query (model, classifier,…
Sets Clustering
Ibrahim Jubran, Murad Tukan, Alaa Maalouf +1
The input to the \emph{sets--means} problem is an integer and a set of sets in . The goal is to compute a set of …
Introduction to Coresets: Accurate Coresets
Ibrahim Jubran, Alaa Maalouf, Dan Feldman
A coreset (or core-set) of an input set is its small summation, such that solving a problem on the coreset as its input, provably yields the same result as solving the same problem…
Tight Sensitivity Bounds For Smaller Coresets
Alaa Maalouf, Adiel Statman, Dan Feldman
An -coreset for Least-Mean-Squares (LMS) of a matrix is a small weighted subset of its rows that approximates the sum of squared distanc…
Fast and Accurate Least-Mean-Squares Solvers
Alaa Maalouf, Ibrahim Jubran, Dan Feldman
Least-mean squares (LMS) solvers such as Linear / Ridge / Lasso-Regression, SVD and Elastic-Net not only solve fundamental machine learning problems, but are also the building bloc…