Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Alessandro Achille"'
Publikováno v:
Quantum, Vol 8, p 1257 (2024)
We propose a novel deterministic method for preparing arbitrary quantum states. When our protocol is compiled into CNOT and arbitrary single-qubit gates, it prepares an $N$-dimensional state in depth $O(\log(N))$ and $\textit{spacetime allocation}$ (
Externí odkaz:
https://doaj.org/article/f197fa6f90d44b538dd19c1e294d4e70
Publikováno v:
Entropy, Vol 23, Iss 7, p 922 (2021)
We introduce the Redundant Information Neural Estimator (RINE), a method that allows efficient estimation for the component of information about a target variable that is common to a set of sources, known as the “redundant information”. We show t
Externí odkaz:
https://doaj.org/article/42dc337b4d4545ac8b4134b23d2948b2
Autor:
Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto
We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language models on large public datasets has enabled strong differential priva
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d61a32561946f4362f02ff0bf57bebc
Publikováno v:
CVPR
Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization. Such desirable properties are absent in d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d2279bff34330f62920803dc96089dda
https://doi.org/10.1109/cvpr46437.2021.01547
https://doi.org/10.1109/cvpr46437.2021.01547
Autor:
Alex Edward Powers, Julia C. Pitino, Luis Fonseca-Ornelas, Jobin Varkey, Ralf Langen, Haiyang Jiang, Tim Bartels, Dushyant S. Patel, Matteo Rovere, Alessandro Achille
Publikováno v:
The Journal of Biological Chemistry
Parkinson's disease (PD) is one of the most common neurodegenerative disorders, and both genetic and histopathological evidence have implicated the ubiquitous presynaptic protein α-synuclein (αSyn) in its pathogenesis. Recent work has investigated
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::698c9b2595966533dbd3ac6bbf4a7d6c
https://doi.org/10.1074/jbc.ra118.006551
https://doi.org/10.1074/jbc.ra118.006551
Publikováno v:
CVPR
We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of remaining inf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b8a2d965e37be94cda1e8ab42d1ef652
http://arxiv.org/abs/2012.13431
http://arxiv.org/abs/2012.13431
Publikováno v:
CVPR
We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidden from the output of the network, insights may still be gleaned by pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::96349bd3f6676a2a8c65c0ecbbab9fde
https://doi.org/10.1109/cvpr42600.2020.00932
https://doi.org/10.1109/cvpr42600.2020.00932
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585259
ECCV (29)
ECCV (29)
We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout functions, and can be extended to ensure forgetting in the final activat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8e6c95cd9a98fb4c7273e60725a5402
https://doi.org/10.1007/978-3-030-58526-6_23
https://doi.org/10.1007/978-3-030-58526-6_23
Autor:
Rahul Bhotika, Orchid Majumder, Alessandro Achille, Avinash Ravichandran, Qing Liu, Stefano Soatto
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585709
ECCV (7)
ECCV (7)
We propose a method to train a model so it can learn new classification tasks while improving with each task solved. This amounts to combining meta-learning with incremental learning. Different tasks can have disjoint classes, so one cannot directly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::15c587e74bcf982db938cb5d979e551f
https://doi.org/10.1007/978-3-030-58571-6_40
https://doi.org/10.1007/978-3-030-58571-6_40
Autor:
Kamal Gupta, Justin Lazarow, Alessandro Achille, Larry Davis, Vijay Mahadevan, Abhinav Shrivastava
We address the problem of scene layout generation for diverse domains such as images, mobile applications, documents, and 3D objects. Most complex scenes, natural or human-designed, can be expressed as a meaningful arrangement of simpler compositiona
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::978424b0844c627ad83e3e7bb72e4314