Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Diego Granziol"'
Publikováno v:
Algorithms, Vol 15, Iss 6, p 209 (2022)
We propose an alternative maximum entropy approach to learning the spectra of massive graphs. In contrast to state-of-the-art Lanczos algorithm for spectral density estimation and applications thereof, our approach does not require kernel smoothing.
Externí odkaz:
https://doaj.org/article/4a1b55785a39473ba2e3ce9abb0c4fac
Publikováno v:
Entropy, Vol 21, Iss 6, p 551 (2019)
Efficient approximation lies at the heart of large-scale machine learning problems. In this paper, we propose a novel, robust maximum entropy algorithm, which is capable of dealing with hundreds of moments and allows for computationally efficient app
Externí odkaz:
https://doaj.org/article/14429d1f4da8433aac39e50f42fa7433
Autor:
Nicholas P Baskerville, Jonathan P Keating, Francesco Mezzadri, Joseph Najnudel, Diego Granziol
Publikováno v:
Baskerville, N P, Keating, J, Mezzadri, F, Najnudel, J & Granziol, D 2022, ' Universal characteristics of deep neural network loss surfaces from random matrix theory ', Journal of Physics A: Mathematical and Theoretical, vol. 55, no. 49, 494002 . https://doi.org/10.1088/1751-8121/aca7f5
This paper considers several aspects of random matrix universality in deep neural networks. Motivated by recent experimental work, we use universal properties of random matrices related to local statistics to derive practical implications for deep ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec082a1e277108d203a7bffc78ddaa8e
http://arxiv.org/abs/2205.08601
http://arxiv.org/abs/2205.08601
We investigate the local spectral statistics of the loss surface Hessians of artificial neural networks, where we discover excellent agreement with Gaussian Orthogonal Ensemble statistics across several network architectures and datasets. These resul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac75f5cb23120ef91a120064f434120b
https://doi.org/10.1016/j.physa.2021.126742
https://doi.org/10.1016/j.physa.2021.126742
Autor:
Nicholas Baskerville, Diego Granziol
Publikováno v:
Journal of Physics: Complexity. 3:024001
We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate that typica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8d99c015fe52ac3547ac085f533acacb
https://doi.org/10.1088/2632-072x/ac730c
https://doi.org/10.1088/2632-072x/ac730c
Autor:
Diego Granziol, Jack K. Fitzsimons, Stephen J. Roberts, Kurt Cutajar, Michael A. Osborne, Maurizio Filippone
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783319712482
ECML/PKDD (1)
ECML/PKDD (1)
The scalable calculation of matrix determinants has been a bottleneck to the widespread application of many machine learning methods such as determinantal point processes, Gaussian processes, generalised Markov random fields, graph models and many ot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ea663a7eb13202ae2f1c87a0fd77061
http://arxiv.org/abs/1704.07223
http://arxiv.org/abs/1704.07223