no code implementations • 4 Nov 2019 • Xubo Yue, Raed Al Kontar
We then provide both a theoretical and practical guideline to decide on the rolling horizon stagewise.
no code implementations • 19 Feb 2020 • Seokhyun Chung, Raed Al Kontar, Zhenke Wu
A fundamental assumption is that the output/group membership labels for all observations are known.
no code implementations • 28 Sep 2020 • Xubo Yue, Maher Nouiehed, Raed Al Kontar
In an effort to improve generalization in deep learning, we propose SALR: a sharpness-aware learning rate update technique designed to recover flat minimizers.
no code implementations • 10 Nov 2020 • Xubo Yue, Maher Nouiehed, Raed Al Kontar
In an effort to improve generalization in deep learning and automate the process of learning rate scheduling, we propose SALR: a sharpness-aware learning rate update technique designed to recover flat minimizers.
no code implementations • NeurIPS 2020 • Hao Chen, Lili Zheng, Raed Al Kontar, Garvesh Raskutti
Stochastic gradient descent (SGD) and its variants have established themselves as the go-to algorithms for large-scale machine learning problems with independent samples due to their generalization performance and intrinsic computational advantage.
1 code implementation • 21 Jul 2021 • Naichen Shi, Fan Lai, Raed Al Kontar, Mosharaf Chowdhury
In this paper we propose Fed-ensemble: a simple approach that bringsmodel ensembling to federated learning (FL).
no code implementations • 5 Aug 2021 • Xubo Yue, Maher Nouiehed, Raed Al Kontar
In this paper we propose \texttt{GIFAIR-FL}: a framework that imposes \textbf{G}roup and \textbf{I}ndividual \textbf{FAIR}ness to \textbf{F}ederated \textbf{L}earning settings.
no code implementations • 19 Nov 2021 • Hao Chen, Lili Zheng, Raed Al Kontar, Garvesh Raskutti
Stochastic gradient descent (SGD) and its variants have established themselves as the go-to algorithms for large-scale machine learning problems with independent samples due to their generalization performance and intrinsic computational advantage.
1 code implementation • 28 Nov 2021 • Xubo Yue, Raed Al Kontar
In this paper, we propose \texttt{FGPR}: a Federated Gaussian process ($\mathcal{GP}$) regression framework that uses an averaging strategy for model aggregation and stochastic gradient descent for local client computations.
no code implementations • 16 Mar 2022 • Wenbo Sun, Raed Al Kontar, Judy Jin, Tzyy-Shuh Chang
Machine-vision-based defect classification techniques have been widely adopted for automatic quality inspection in manufacturing processes.
no code implementations • 15 Jun 2022 • Xubo Yue, Raed Al Kontar, Ana María Estrada Gómez
In this work, we take a step back to develop an FDA treatment for one of the most fundamental statistical models: linear regression.
1 code implementation • 17 Jul 2022 • Naichen Shi, Raed Al Kontar
In this paper, we tackle a significant challenge in PCA: heterogeneity.
no code implementations • 24 Aug 2022 • Qiyuan Chen, Raed Al Kontar, Maher Nouiehed, Jessie Yang, Corey Lester
This necessitates rethinking cost-sensitive classification in DNNs.
1 code implementation • 25 Jun 2023 • Xubo Yue, Raed Al Kontar, Albert S. Berahas, Yang Liu, Blake N. Johnson
Empirically, through simulated datasets and a real-world collaborative sensor design experiment, we show that our framework can effectively accelerate and improve the optimal design process and benefit all participants.
no code implementations • 7 Sep 2023 • Jiuyun Hu, Naichen Shi, Raed Al Kontar, Hao Yan
We propose personalized Tucker decomposition (perTucker) to address the limitations of traditional tensor decomposition methods in capturing heterogeneity across different datasets.
no code implementations • 12 Oct 2023 • Xiaoyang Song, Wenbo Sun, Maher Nouiehed, Raed Al Kontar, Judy Jin
Current techniques for Out-of-Distribution (OoD) detection predominantly rely on quantifying predictive uncertainty and incorporating model regularization during the training phase, using either real or synthetic OoD samples.
no code implementations • 21 Mar 2024 • Naichen Shi, Salar Fattahi, Raed Al Kontar
In this work, we study the problem of common and unique feature extraction from noisy data.
no code implementations • 25 Mar 2024 • Seokhyun Chung, Raed Al Kontar
Numerical studies on both synthetic and real-world data in reliability engineering highlight the advantageous features of our model in real-time adaptation, enhanced signal prediction with uncertainty quantification, and joint prediction for labels and signals.