Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Gibson, Travis E."'
Autor:
Gibson, Travis E., Acharya, Sawal, Parashar, Anjali, Gaudio, Joseph E., Annaswamy, Anurdha M.
Gradient based optimization algorithms deployed in Machine Learning (ML) applications are often analyzed and compared by their convergence rates or regret bounds. While these rates and bounds convey valuable information they don't always directly tra
Externí odkaz:
http://arxiv.org/abs/2405.13765
Autor:
Urtecho, Guillaume, Moody, Thomas, Huang, Yiming, Sheth, Ravi U., Richardson, Miles, Descamps, Hélène C., Kaufman, Andrew, Lekan, Opeyemi, Zhang, Zetian, Velez-Cortes, Florencia, Qu, Yiming, Cohen, Lucas, Ricaurte, Deirdre, Gibson, Travis E., Gerber, Georg K., Thaiss, Christoph A., Wang, Harris H.
Publikováno v:
In Cell Systems 20 November 2024 15(11):1002-1017
Autor:
Gaudio, Joseph E., Annaswamy, Anuradha M., Moreu, José M., Bolender, Michael A., Gibson, Travis E.
High order momentum-based parameter update algorithms have seen widespread applications in training machine learning models. Recently, connections with variational approaches have led to the derivation of new learning algorithms with accelerated lear
Externí odkaz:
http://arxiv.org/abs/2005.01529
Autor:
Gaudio, Joseph E., Gibson, Travis E., Annaswamy, Anuradha M., Bolender, Michael A., Lavretsky, Eugene
This paper demonstrates many immediate connections between adaptive control and optimization methods commonly employed in machine learning. Starting from common output error formulations, similarities in update law modifications are examined. Concept
Externí odkaz:
http://arxiv.org/abs/1904.05856
Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent methods un
Externí odkaz:
http://arxiv.org/abs/1903.04666
Autor:
Gibson, Travis E., Gerber, Georg K.
Publikováno v:
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:1763-1772, 2018
Microbes are everywhere, including in and on our bodies, and have been shown to play key roles in a variety of prevalent human diseases. Consequently, there has been intense interest in the design of bacteriotherapies or "bugs as drugs," which are co
Externí odkaz:
http://arxiv.org/abs/1805.04591
Recently a distributed algorithm has been proposed for multi-agent networks to solve a system of linear algebraic equations, by assuming each agent only knows part of the system and is able to communicate with nearest neighbors to update their local
Externí odkaz:
http://arxiv.org/abs/1603.04154
Autor:
Gibson, Travis E.
With the rise of network science old topics in ecology and economics are resurfacing. One such topic is structural stability (often referred to as qualitative stability or sign stability). A system is deemed structurally stable if the system remains
Externí odkaz:
http://arxiv.org/abs/1512.06026
Autor:
Vinayagam, Arunachalam, Gibson, Travis E., Lee, Ho-Joon, Yilmazel, Bahar, Roesel, Charles, Hu, Yanhui, Kwon, Young, Sharma, Amitabh, Liu, Yang-Yu, Perrimon, Norbert, Barabási, Albert-László
The protein-protein interaction (PPI) network is crucial for cellular information processing and decision-making. With suitable inputs, PPI networks drive the cells to diverse functional outcomes such as cell proliferation or cell death. Here we char
Externí odkaz:
http://arxiv.org/abs/1511.07768
The convergence properties of adaptive systems in terms of excitation conditions on the regressor vector are well known. With persistent excitation of the regressor vector in model reference adaptive control the state error and the adaptation error a
Externí odkaz:
http://arxiv.org/abs/1511.03222