Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Zhang, Qinzi"'
Autor:
Zhang, Qinzi, Tseng, Lewis
This paper studies the power of the "abstract MAC layer" model in a single-hop asynchronous network. The model captures primitive properties of modern wireless MAC protocols. In this model, Newport [PODC '14] proves that it is impossible to achieve d
Externí odkaz:
http://arxiv.org/abs/2408.10779
There is a significant gap between our theoretical understanding of optimization algorithms used in deep learning and their practical performance. Theoretical development usually focuses on proving convergence guarantees under a variety of different
Externí odkaz:
http://arxiv.org/abs/2407.01825
We introduce a new zeroth-order algorithm for private stochastic optimization on nonconvex and nonsmooth objectives. Given a dataset of size $M$, our algorithm ensures $(\alpha,\alpha\rho^2/2)$-R\'enyi differential privacy and finds a $(\delta,\epsil
Externí odkaz:
http://arxiv.org/abs/2406.19579
Autor:
Zhang, Qinzi, Cutkosky, Ashok
Training neural networks requires optimizing a loss function that may be highly irregular, and in particular neither convex nor smooth. Popular training algorithms are based on stochastic gradient descent with momentum (SGDM), for which classical ana
Externí odkaz:
http://arxiv.org/abs/2405.09742
Autor:
Zhang, Qinzi, Tseng, Lewis
This paper studies the feasibility of reaching consensus in an anonymous dynamic network. In our model, $n$ anonymous nodes proceed in synchronous rounds. We adopt a hybrid fault model in which up to $f$ nodes may suffer crash or Byzantine faults, an
Externí odkaz:
http://arxiv.org/abs/2405.03017
We develop a new reduction that converts any online convex optimization algorithm suffering $O(\sqrt{T})$ regret into an $\epsilon$-differentially private stochastic convex optimization algorithm with the optimal convergence rate $\tilde O(1/\sqrt{T}
Externí odkaz:
http://arxiv.org/abs/2210.06593
Autor:
Zhang, Qinzi, Tseng, Lewis
In this paper, we focus on a popular DML framework -- the parameter server computation paradigm and iterative learning algorithms that proceed in rounds. We aim to reduce the communication complexity of Byzantine-tolerant DML algorithms in the single
Externí odkaz:
http://arxiv.org/abs/2011.07447
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Fault-tolerant consensus is of great importance in distributed systems. This paper studies the asynchronous approximate consensus problem in the crash-recovery model with fair-loss links. In our model, up to f nodes may crash forever, while the rest
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7e8babb6769fbd0922bd45c00f94823
Autor:
Ben Youssef, Adel, Mejri, Issam
Publikováno v:
Sustainability (2071-1050); May2023, Vol. 15 Issue 9, p7465, 20p
