Results 71 to 80 of about 1,424,164 (189)

Balancing Privacy and Utility in Artificial Intelligence-Based Clinical Decision Support: Empirical Evaluation Using De-Identified Electronic Health Record Data

Applied Sciences
The secondary use of electronic health records is essential for developing artificial intelligence-based clinical decision support systems. However, even after direct identifiers are removed, de-identified electronic health records remain vulnerable to ...
Jungwoo Lee, Kyu Hee Lee
doaj   +1 more source

Stability and Generalization of Decentralized Stochastic Gradient Descent

, 2021
The stability and generalization of stochastic gradient-based methods provide valuable insights into understanding the algorithmic performance of machine learning models.
Li, Dongsheng, Wang, Bao, Sun, Tao
core   +1 more source

Adaptive Step Sizes for Stochastic Gradient Descent

, 2023
In this thesis, we first lay some theoretical groundwork before motivating and discussing the stochastic gradient descent method along with its variations. We then analyze some popular step size strategies with a focus on the stochastic Polyak step size,
Karakoc, Dylan
core   +1 more source

Revisiting Stochastic Approximation and Stochastic Gradient Descent

CoRR
31 ...
Rajeeva Laxman Karandikar, Bhamidi Visweswara Rao, Mathukumalli Vidyasagar   +2 more
openaire   +3 more sources

Pengembangan Stochastic Gradient Descent Dengan Penambahan Variabel Tetap [PDF]

, 2022
Stochastic Gradient Descent (SGD) adalah salah satu dari optimizer yang sering digunakan dalam deep learning, maka dari itu dalam penelitian ini akan melakukan sebuah modifikasi terhadap Stochastic Gradient Descent (SGD). Stochastic Gradient Descent (SGD)
Adimas Tristan Nagara Hartono
core   +1 more source

Stochastic gradient descent with finite samples sizes [PDF]

, 2016
The minimization of empirical risks over finite sample sizes is an important problem in large-scale machine learning. A variety of algorithms has been proposed in the literature to alleviate the computational burden per iteration at the expense of ...
Ying, Bicheng, Yuan, Kun, Vlaski, Stefan, Ali H. Sayed, Bicheng Ying, Kun Yuan, Sayed, Ali H, Stefan Vlaski   +7 more
core   +2 more sources

Parle: parallelizing stochastic gradient descent

CoRR, 2017
We propose a new algorithm called Parle for parallel training of deep networks that converges 2-4x faster than a data-parallel implementation of SGD, while achieving significantly improved error rates that are nearly state-of-the-art on several benchmarks including CIFAR-10 and CIFAR-100, without introducing any additional hyper-parameters.
Chaudhari, Pratik, Baldassi, Carlo, Zecchina, Riccardo, Soatto, Stefano, Talwalkar, Ameet, Oberman, Adam   +5 more
openaire   +2 more sources

Federated Accelerated Stochastic Gradient Descent

CoRR, 2020
Accepted to NeurIPS 2020. Best paper in International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020 (FL-ICML'20).
Honglin Yuan, Tengyu Ma 0001
openaire   +4 more sources

A Static Security Region Analysis of New Power Systems Based on Improved Stochastic–Batch Gradient Pile Descent

Applied Sciences
The uncertainty in the new power system has increased, leading to limitations in traditional stability analysis methods. Therefore, considering the perspective of the three-dimensional static security region (SSR), we propose a novel approach for system ...
Jiahui Wu, Yide Zhou, Haiyun Wang, Weiqing Wang   +3 more
doaj   +1 more source

Unforgeability in Stochastic Gradient Descent

Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023
Teodora Baluta, Ivica Nikolic, Racchit Jain, Divesh Aggarwal, Prateek Saxena   +4 more
openaire   +1 more source