Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Potapczynski, Andres"'
Autor:
Potapczynski, Andres, Qiu, Shikai, Finzi, Marc, Ferri, Christopher, Chen, Zixi, Goldblum, Micah, Bruss, Bayan, De Sa, Christopher, Wilson, Andrew Gordon
Dense linear layers are the dominant computational bottleneck in large neural networks, presenting a critical need for more efficient alternatives. Previous efforts focused on a small number of hand-crafted structured matrices and neglected to invest
Externí odkaz:
http://arxiv.org/abs/2410.02117
Dense linear layers are the dominant computational bottleneck in foundation models. Identifying more efficient alternatives to dense matrices has enormous potential for building more compute-efficient models, as exemplified by the success of convolut
Externí odkaz:
http://arxiv.org/abs/2406.06248
Many areas of machine learning and science involve large linear algebra problems, such as eigendecompositions, solving linear systems, computing matrix exponentials, and trace estimation. The matrices involved often have Kronecker, convolutional, blo
Externí odkaz:
http://arxiv.org/abs/2309.03060
Publikováno v:
40th International Conference on Machine Learning 2023
A major challenge to out-of-distribution generalization is reliance on spurious features -- patterns that are predictive of the class label in the training data distribution, but not causally related to the target. Standard methods for reducing the r
Externí odkaz:
http://arxiv.org/abs/2306.11074
Unlike conventional grid and mesh based methods for solving partial differential equations (PDEs), neural networks have the potential to break the curse of dimensionality, providing approximate solutions to problems where using classical solvers is d
Externí odkaz:
http://arxiv.org/abs/2304.14994
Autor:
Lotfi, Sanae, Finzi, Marc, Kapoor, Sanyam, Potapczynski, Andres, Goldblum, Micah, Wilson, Andrew Gordon
While there has been progress in developing non-vacuous generalization bounds for deep neural networks, these bounds tend to be uninformative about why deep learning works. In this paper, we develop a compression approach based on quantizing neural n
Externí odkaz:
http://arxiv.org/abs/2211.13609
Low-precision arithmetic has had a transformative effect on the training of neural networks, reducing computation, memory and energy requirements. However, despite its promise, low-precision arithmetic has received little attention for Gaussian proce
Externí odkaz:
http://arxiv.org/abs/2207.06856
Probability distributions supported on the simplex enjoy a wide range of applications across statistics and machine learning. Recently, a novel family of such distributions has been discovered: the continuous categorical. This family enjoys remarkabl
Externí odkaz:
http://arxiv.org/abs/2204.13290
Publikováno v:
38th International Conference on Machine Learning (ICML 2021)
Scalable Gaussian Process methods are computationally attractive, yet introduce modeling biases that require rigorous study. This paper analyzes two common techniques: early truncated conjugate gradients (CG) and random Fourier features (RFF). We fin
Externí odkaz:
http://arxiv.org/abs/2102.06695
Publikováno v:
Published: NeurIPS 2020
The Gumbel-Softmax is a continuous distribution over the simplex that is often used as a relaxation of discrete distributions. Because it can be readily interpreted and easily reparameterized, it enjoys widespread use. We propose a modular and more f
Externí odkaz:
http://arxiv.org/abs/1912.09588