Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Halabi, Marwa"'
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 compression methods remove redundant non-linear activation functions and me
Externí odkaz:
http://arxiv.org/abs/2406.12837
Submodular maximization over a matroid constraint is a fundamental problem with various applications in machine learning. Some of these applications involve decision-making over datapoints with sensitive attributes such as gender or race. In such set
Externí odkaz:
http://arxiv.org/abs/2312.14299
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 gender or race, it becomes important to enforce fairness to avoid bias
Externí odkaz:
http://arxiv.org/abs/2305.15118
Publikováno v:
Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023
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 be equivalently formulated as the minimization of the difference of tw
Externí odkaz:
http://arxiv.org/abs/2305.11046
Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance. However, most current structured pruning methods do not provide any performance guarantees, and often req
Externí odkaz:
http://arxiv.org/abs/2203.04940
Autor:
Al-smadi, Ahmed Mohammad, Bani Hani, Salam, Shajrawi, Abedalmajeed, Ashour, Ala, Halabi, Marwa, Mousa, Areej, Al Smadi, Mustafa Mohammad
Publikováno v:
Working with Older People, 2022, Vol. 27, Issue 4, pp. 323-334.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/WWOP-09-2022-0039
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 attributes such as gender or age, such machine learning algorithms, l
Externí odkaz:
http://arxiv.org/abs/2010.07431
Autor:
Halabi, Marwa El, Jegelka, Stefanie
Publikováno v:
Proceedings of the 37 th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020
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 learning or batch Bayesian optimization, the objective function is not ex
Externí odkaz:
http://arxiv.org/abs/1905.12145
Publikováno v:
Working with Older People, 2021, Vol. 26, Issue 2, pp. 120-129.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/WWOP-08-2021-0044
Publikováno v:
Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018, Lanzarote, Spain. PMLR: Volume 84
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 tightness of the resulting relaxations through the notion of the lower com
Externí odkaz:
http://arxiv.org/abs/1710.06273