21 citations · 52 across the 13 of their papers we have counts for
14 papers
Discrete and Continuous Difference of Submodular Minimization
George Orfanides, Tim Hoheisel, Marwa El Halabi
Submodular functions, defined on continuous or discrete domains, arise in numerous applications. We study the minimization of the difference of two submodular (DS) functions, over…
GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
Jinuk Kim, Marwa El Halabi, Wonpyo Park +5
Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retrain…
LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
Jinuk Kim, Marwa El Halabi, Mingi Ji +1
Recent works show that reducing the number of layers in a convolutional neural network can enhance efficiency while maintaining the performance of the network. Existing depth compr…
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard +1
Submodular maximization over a matroid constraint is a fundamental problem with various applications in machine learning. Some of these applications involve decision-making over da…
Fairness in Streaming Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Federico Fusco, Ashkan Norouzi-Fard +2
Streaming submodular maximization is a natural model for the task of selecting a representative subset from a large-scale dataset. If datapoints have sensitive attributes such as g…
Difference of Submodular Minimization via DC Programming
Marwa El Halabi, George Orfanides, Tim Hoheisel
Minimizing the difference of two submodular (DS) functions is a problem that naturally occurs in various machine learning problems. Although it is well known that a DS problem can…
Data-Efficient Structured Pruning via Submodular Optimization
Marwa El Halabi, Suraj Srinivas, Simon Lacoste-Julien
Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance. However, most current structured pr…
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard +2
Submodular maximization has become established as the method of choice for the task of selecting representative and diverse summaries of data. However, if datapoints have sensitive…
Optimal approximation for unconstrained non-submodular minimization
Marwa El Halabi, Stefanie Jegelka
Submodular function minimization is well studied, and existing algorithms solve it exactly or up to arbitrary accuracy. However, in many applications, such as structured sparse lea…
Combinatorial Penalties: Which structures are preserved by convex relaxations?
Marwa El Halabi, Francis Bach, Volkan Cevher
We consider the homogeneous and the non-homogeneous convex relaxations for combinatorial penalty functions defined on support sets. Our study identifies key differences in the tigh…
An Efficient Streaming Algorithm for the Submodular Cover Problem
Ashkan Norouzi-Fard, Abbas Bazzi, Marwa El Halabi +3
We initiate the study of the classical Submodular Cover (SC) problem in the data streaming model which we refer to as the Streaming Submodular Cover (SSC). We show that any single…
Frank-Wolfe Works for Non-Lipschitz Continuous Gradient Objectives: Scalable Poisson Phase Retrieval
Gergely Odor, Yen-Huan Li, Alp Yurtsever +4
We study a phase retrieval problem in the Poisson noise model. Motivated by the PhaseLift approach, we approximate the maximum-likelihood estimator by solving a convex program with…
Structured Sparsity: Discrete and Convex approaches
Anastasios Kyrillidis, Luca Baldassarre, Marwa El-Halabi +2
Compressive sensing (CS) exploits sparsity to recover sparse or compressible signals from dimensionality reducing, non-adaptive sensing mechanisms. Sparsity is also used to enhance…
A totally unimodular view of structured sparsity
Marwa El Halabi, Volkan Cevher
This paper describes a simple framework for structured sparse recovery based on convex optimization. We show that many structured sparsity models can be naturally represented by li…