Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Masoomi, Aria"'
We present a comprehensive study of the degeneracy loci of the full flag varieties of all complex semisimple Lie groups equipped with the standard Poisson structures. The reduced Poisson degeneracy loci are shown to stratify under the action of the c
Externí odkaz:
http://arxiv.org/abs/2401.04833
Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-linear and thus have a zero Hessian almost everywhere. We propose Smoo
Externí odkaz:
http://arxiv.org/abs/2311.00858
Autor:
Masoomi, Aria, Hill, Davin, Xu, Zhonghui, Hersh, Craig P, Silverman, Edwin K., Castaldi, Peter J., Ioannidis, Stratis, Dy, Jennifer
Publikováno v:
International Conference on Learning Representations, 2022
As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain black-box models by capturing the most influential features for predicti
Externí odkaz:
http://arxiv.org/abs/2304.07670
Autor:
Ghimire, Sandesh, Liu, Jinyang, Comas, Armand, Hill, Davin, Masoomi, Aria, Camps, Octavia, Dy, Jennifer
In this work, we look at Score-based generative models (also called diffusion generative models) from a geometric perspective. From a new view point, we prove that both the forward and backward process of adding noise and generating from noise are Wa
Externí odkaz:
http://arxiv.org/abs/2302.04411
While score based generative models, or diffusion models, have found success in image synthesis, they are often coupled with text data or image label to be able to manipulate and conditionally generate images. Even though manipulation of images by ch
Externí odkaz:
http://arxiv.org/abs/2302.02272
Autor:
Singh, Ashutosh, Singh, Ashish, Masoomi, Aria, Imbiriba, Tales, Learned-Miller, Erik, Erdogmus, Deniz
Subspace clustering algorithms are used for understanding the cluster structure that explains the dataset well. These methods are extensively used for data-exploration tasks in various areas of Natural Sciences. However, most of these methods fail to
Externí odkaz:
http://arxiv.org/abs/2211.06780
Post-hoc explanation methods have become a critical tool for understanding black-box classifiers in high-stakes applications. However, high-performing classifiers are often highly nonlinear and can exhibit complex behavior around the decision boundar
Externí odkaz:
http://arxiv.org/abs/2210.02419
Machine learning methods have significantly improved in their predictive capabilities, but at the same time they are becoming more complex and less transparent. As a result, explainers are often relied on to provide interpretability to these black-bo
Externí odkaz:
http://arxiv.org/abs/2206.12481
Publikováno v:
AIStats 2022
There is currently a debate within the neuroscience community over the likelihood of the brain performing backpropagation (BP). To better mimic the brain, training a network \textit{one layer at a time} with only a "single forward pass" has been prop
Externí odkaz:
http://arxiv.org/abs/2202.01210
Publikováno v:
Advances in Neural Information Processing Systems 2021
Estimating Kullback Leibler (KL) divergence from samples of two distributions is essential in many machine learning problems. Variational methods using neural network discriminator have been proposed to achieve this task in a scalable manner. However
Externí odkaz:
http://arxiv.org/abs/2109.14688