no code implementations • 2 Feb 2019 • Belhal Karimi, Blazej Miasojedow, Eric Moulines, Hoi-To Wai
We illustrate these settings with the online EM algorithm and the policy-gradient method for average reward maximization in reinforcement learning.
no code implementations • ICLR 2020 • Jun-Kun Wang, Xiaoyun Li, Belhal Karimi, Ping Li
We propose a new variant of AMSGrad, a popular adaptive gradient based optimization algorithm widely used for training deep neural networks.
no code implementations • NeurIPS 2019 • Belhal Karimi, Hoi-To Wai, Eric Moulines, Marc Lavielle
To alleviate this problem, Neal and Hinton have proposed an incremental version of the EM (iEM) in which at each iteration the conditional expectation of the latent data (E-step) is updated only for a mini-batch of observations.
no code implementations • 11 Aug 2020 • Farzin Haddadpour, Belhal Karimi, Ping Li, Xiaoyun Li
Communication complexity and privacy are the two key challenges in Federated Learning where the goal is to perform a distributed learning through a large volume of devices.
no code implementations • pproximateinference AABI Symposium 2021 • Belhal Karimi, Ping Li
Bayesian neural networks attempt to combine the strong predictive performance of neural networks with formal quantification of uncertainty of the predicted output in the Bayesian framework.
no code implementations • NeurIPS 2020 • Yingxue Zhou, Belhal Karimi, Jinxing Yu, Zhiqiang Xu, Ping Li
Adaptive gradient methods such as AdaGrad, RMSprop and Adam have been optimizers of choice for deep learning due to their fast training speed.
no code implementations • 1 Jan 2021 • Belhal Karimi, Hoi To Wai, Eric Moulines, Ping Li
Many constrained, nonconvex and nonsmooth optimization problems can be tackled using the majorization-minimization (MM) method which alternates between constructing a surrogate function which upper bounds the objective function, and then minimizing this surrogate.
no code implementations • 1 Jan 2021 • Xiangyi Chen, Belhal Karimi, Weijie Zhao, Ping Li
Specifically, we propose a general algorithmic framework that can convert existing adaptive gradient methods to their decentralized counterparts.
no code implementations • 7 Sep 2021 • Xiangyi Chen, Belhal Karimi, Weijie Zhao, Ping Li
Adaptive gradient methods including Adam, AdaGrad, and their variants have been very successful for training deep learning models, such as neural networks.
no code implementations • 1 Oct 2021 • Belhal Karimi, Ping Li, Xiaoyun Li
In the emerging paradigm of Federated Learning (FL), large amount of clients such as mobile devices are used to train possibly high-dimensional models on their respective data.
no code implementations • 18 Mar 2022 • Belhal Karimi, Ping Li
We motivate the choice of a double dynamic by invoking the variance reduction virtue of each stage of the method on both sources of noise: the index sampling for the incremental update and the MC approximation.
no code implementations • 9 May 2022 • Hao Li, Xu Li, Belhal Karimi, Jie Chen, Mingming Sun
Modeling visual question answering(VQA) through scene graphs can significantly improve the reasoning accuracy and interpretability.
no code implementations • ICLR 2022 • Xiaoyun Li, Belhal Karimi, Ping Li
We study COMP-AMS, a distributed optimization framework based on gradient averaging and adaptive AMSGrad algorithm.
no code implementations • 6 Jul 2022 • Shaogang Ren, Belhal Karimi, Dingcheng Li, Ping Li
VFGs learn the representation of high dimensional data via a message-passing scheme by integrating flow-based functions through variational inference.
no code implementations • 26 Sep 2022 • Weijie Zhao, Xuewu Jiao, Xinsheng Luo, Jingxue Li, Belhal Karimi, Ping Li
In this paper, we propose FeatureBox, a novel end-to-end training framework that pipelines the feature extraction and the training on GPU servers to save the intermediate I/O of the feature extraction.
no code implementations • 19 Oct 2023 • Belhal Karimi, Jianwen Xie, Ping Li
We propose in this paper, STANLEY, a STochastic gradient ANisotropic LangEvin dYnamics, for sampling high dimensional data.