Search Results - "Tukan, Murad"

No Fine-Tuning, No Cry: Robust SVD for Compressing Deep Networks by Tukan, Murad, Maalouf, Alaa, Weksler, Matan, Feldman, Dan

“…A common technique for compressing a neural network is to compute the k-rank ℓ2 approximation Ak of the matrix A∈Rn×d via SVD that corresponds to a fully…”
Get full text

Coresets for the Average Case Error for Finite Query Sets by Maalouf, Alaa, Jubran, Ibrahim, Tukan, Murad, Feldman, Dan

“…Coreset is usually a small weighted subset of an input set of items, that provably approximates their loss function for a given set of queries (models,…”
Get full text

An Efficient Drifters Deployment Strategy to Evaluate Water Current Velocity Fields by Tukan, Murad, Biton, Eli, Diamant, Roee

“…Water current prediction is essential for understanding ecosystems, and to shed light on the role of the ocean in the global climate context. Solutions vary…”
Get full text

On coresets for support vector machines by Tukan, Murad, Baykal, Cenk, Feldman, Dan, Rus, Daniela

“…•A coreset construction algorithm for boosting support vector machines.•Lower bound on the number of coreset size with respect to support vector…”
Get full text

Obstacle Aware Sampling for Path Planning by Tukan, Murad, Maalouf, Alaa, Feldman, Dan, Poranne, Roi

“…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,…”
Get full text

Coreset Construction Frameworks for Machine Learning Models by Tukan, Murad, טוקאן, מורד

“…We consider the common family of machine learning and optimization problems of the following type. Given a finite set ⊆ R of input points (training data), a…”
Get full text

A Unified Framework for Core-Set Construction of Convex Functions by Tukan, Murad

“…We consider the common family of machine learning and optimization problems of the fol-lowing type. Given a finite set P ⊆ Rd of m input points (training data)…”
Get full text

Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint by Tukan, Murad, Mualem, Loay, Feldman, Moran

“…Non-monotone constrained submodular maximization plays a crucial role in various machine learning applications. However, existing algorithms often struggle…”
Get full text

Bridging the Gap Between General and Down-Closed Convex Sets in Submodular Maximization by Mualem, Loay, Tukan, Murad, Fledman, Moran

“…Optimization of DR-submodular functions has experienced a notable surge in significance in recent times, marking a pivotal development within the domain of…”
Get full text

Dataset Distillation Meets Provable Subset Selection by Tukan, Murad, Maalouf, Alaa, Osadchy, Margarita

“…Deep learning has grown tremendously over recent years, yielding state-of-the-art results in various fields. However, training such models requires huge…”
Get full text

An Efficient Drifters Deployment Strategy to Evaluate Water Current Velocity Fields by Tukan, Murad, Biton, Eli, Diamant, Roee

“…Water current prediction is essential for understanding ecosystems, and to shed light on the role of the ocean in the global climate context. Solutions vary…”
Get full text

Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions by Tukan, Murad, Mualem, Loay, Maalouf, Alaa

“…Pruning is one of the predominant approaches for compressing deep neural networks (DNNs). Lately, coresets (provable data summarizations) were leveraged for…”
Get full text

AutoCoreset: An Automatic Practical Coreset Construction Framework by Maalouf, Alaa, Tukan, Murad, Braverman, Vladimir, Rus, Daniela

“…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…”
Get full text

ORBSLAM3-Enhanced Autonomous Toy Drones: Pioneering Indoor Exploration by Tukan, Murad, Fares, Fares, Grufinkle, Yotam, Talmor, Ido, Mualem, Loay, Braverman, Vladimir, Feldman, Dan

“…Navigating toy drones through uncharted GPS-denied indoor spaces poses significant difficulties due to their reliance on GPS for location determination. In…”
Get full text

Obstacle Aware Sampling for Path Planning by Tukan, Murad, Maalouf, Alaa, Feldman, Dan, Poranne, Roi

“…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,…”
Get full text

New Coresets for Projective Clustering and Applications by Tukan, Murad, Wu, Xuan, Zhou, Samson, Braverman, Vladimir, Feldman, Dan

“…$(j,k)$-projective clustering is the natural generalization of the family of $k$-clustering and $j$-subspace clustering problems. Given a set of points $P$ in…”
Get full text

Coresets for Data Discretization and Sine Wave Fitting by Maalouf, Alaa, Tukan, Murad, Price, Eric, Kane, Daniel, Feldman, Dan

“…In the \emph{monitoring} problem, the input is an unbounded stream $P={p_1,p_2\cdots}$ of integers in $[N]:=\{1,\cdots,N\}$, that are obtained from a sensor…”
Get full text

Coresets for Near-Convex Functions by Tukan, Murad, Maalouf, Alaa, Feldman, Dan

“…Coreset is usually a small weighted subset of $n$ input points in $\mathbb{R}^d$, that provably approximates their loss function for a given set of queries…”
Get full text

On the Size and Approximation Error of Distilled Sets by Maalouf, Alaa, Tukan, Murad, Loo, Noel, Hasani, Ramin, Lechner, Mathias, Rus, Daniela

“…Dataset Distillation is the task of synthesizing small datasets from large ones while still retaining comparable predictive accuracy to the original…”
Get full text

Provable Data Subset Selection For Efficient Neural Network Training by Tukan, Murad, Zhou, Samson, Maalouf, Alaa, Rus, Daniela, Braverman, Vladimir, Feldman, Dan

“…Radial basis function neural networks (\emph{RBFNN}) are {well-known} for their capability to approximate any continuous function on a closed bounded set with…”
Get full text