Zobrazeno 1 - 10
of 220
pro vyhledávání: '"Bartan, A."'
Autor:
Bartan, Burak, Pilanci, Mert
We present a novel distributed computing framework that is robust to slow compute nodes, and is capable of both approximate and exact computation of linear operations. The proposed mechanism integrates the concepts of randomized sketching and polar c
Externí odkaz:
http://arxiv.org/abs/2309.00682
The deployment and training of neural networks on edge computing devices pose many challenges. The low memory nature of edge devices is often one of the biggest limiting factors encountered in the deployment of large neural network models. Tensor rem
Externí odkaz:
http://arxiv.org/abs/2304.14463
Autor:
Toledo, Sivan, Mendel, Shai, Levi, Anat, Vortman, Yoni, Ullmann, Wiebke, Scherer, Lena-Rosa, Pufelski, Jan, van Maarseveen, Frank, Denissen, Bas, Bijleveld, Allert, Orchan, Yotam, Bartan, Yoav, Margalit, Sivan, Talmon, Idan, Nathan, Ran
Publikováno v:
Proceedings of the 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), 2022
We describe the design and implementation of Vildehaye, a family of versatile, widely-applicable, and field-proven tags for wildlife sensing and radio tracking. The family includes 6 distinct hardware designs for tags, 3 add-on boards, a programming
Externí odkaz:
http://arxiv.org/abs/2206.06171
Autor:
Bartan, Burak, Pilanci, Mert
We consider distributed optimization methods for problems where forming the Hessian is computationally challenging and communication is a significant bottleneck. We leverage randomized sketches for reducing the problem dimensions as well as preservin
Externí odkaz:
http://arxiv.org/abs/2203.09755
Autor:
Sahiner, Arda, Ergen, Tolga, Ozturkler, Batu, Bartan, Burak, Pauly, John, Mardani, Morteza, Pilanci, Mert
Generative Adversarial Networks (GANs) are commonly used for modeling complex distributions of data. Both the generators and discriminators of GANs are often modeled by neural networks, posing a non-transparent optimization problem which is non-conve
Externí odkaz:
http://arxiv.org/abs/2107.05680
Autor:
Bartan, Burak, Pilanci, Mert
Neural networks (NNs) have been extremely successful across many tasks in machine learning. Quantization of NN weights has become an important topic due to its impact on their energy efficiency, inference time and deployment on hardware. Although pos
Externí odkaz:
http://arxiv.org/abs/2105.01420
Autor:
Bartan, Burak, Pilanci, Mert
The training of two-layer neural networks with nonlinear activation functions is an important non-convex optimization problem with numerous applications and promising performance in layerwise deep learning. In this paper, we develop exact convex opti
Externí odkaz:
http://arxiv.org/abs/2101.02429
In distributed second order optimization, a standard strategy is to average many local estimates, each of which is based on a small sketch or batch of the data. However, the local estimates on each machine are typically biased, relative to the full s
Externí odkaz:
http://arxiv.org/abs/2007.01327
Autor:
Bartan, Burak, Pilanci, Mert
In this work, we study distributed sketching methods for large scale regression problems. We leverage multiple randomized sketches for reducing the problem dimensions as well as preserving privacy and improving straggler resilience in asynchronous di
Externí odkaz:
http://arxiv.org/abs/2002.06538