most citedFast as CHITA: Neural Network Pruning with Combinatorial Optimization

3 citations · 9 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV20242 cited

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization

Xiang Meng, Shibal Ibrahim, Kayhan Behdin +3

Structured pruning is a promising approach for reducing the inference costs of large vision and language models. By removing carefully chosen structures, e.g., neurons or attention…

cs.LG2024

DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation

Yunjuan Wang, Hussein Hazimeh, Natalia Ponomareva +3

Distribution shifts and adversarial examples are two major challenges for deploying machine learning models. While these challenges have been studied individually, their combinatio…

cs.LG20232 cited

Explaining and Adapting Graph Conditional Shift

Qi Zhu, Yizhu Jiao, Natalia Ponomareva +2

Graph Neural Networks (GNNs) have shown remarkable performance on graph-structured data. However, recent empirical studies suggest that GNNs are very susceptible to distribution sh…

cs.LG20232 cited

COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search

Shibal Ibrahim, Wenyu Chen, Hussein Hazimeh +3

The sparse Mixture-of-Experts (Sparse-MoE) framework efficiently scales up model capacity in various domains, such as natural language processing and vision. Sparse-MoEs select a s…

cs.LG20233 cited

Fast as CHITA: Neural Network Pruning with Combinatorial Optimization

Riade Benbaki, Wenyu Chen, Xiang Meng +4

The sheer size of modern neural networks makes model serving a serious computational challenge. A popular class of compression techniques overcomes this challenge by pruning or spa…

cs.LG2023

Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets

Hussein Hazimeh, Natalia Ponomareva

Adversarial nets have proved to be powerful in various domains including generative modeling (GANs), transfer learning, and fairness. However, successfully training adversarial net…