Decentralized non-convex online optimization with adaptive momentum estimation and quantized communication by Yunshan Lv, Hailing Xiong, Fuqing Zhang, Shengying Dong, Xiangguang Dai

Subjects: Get full text

Variance Reduction Optimization Algorithm Based on Random Sampling by GUO Zhenhua, YAN Ruidong, QIU Zhiyong, ZHAO Yaqian, LI Rengang

“…In this paper, a sublinear convergence rate of DM-SRG algorithm is theoretically guaranteed for both non-convex and convex objective functions. …”
Get full text

Getting the Best Out of Both Worlds: Algorithms for Hierarchical Inference at the Edge by Vishnu Narayanan Moothedath, Jaya Prakash Champati, James Gross

“…For a full feedback scenario, where the ED receives feedback on the correctness of the S-ML once it accepts the inference, we propose the HIL-F algorithm and prove a sublinear regret bound <inline-formula> <tex-math notation="LaTeX">$\sqrt {n\ln (1/\lambda _{\text {min}})/2}$ </tex-math></inline-formula> without any assumption on the smoothness of the loss function, where <inline-formula> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> is the number of data samples and <inline-formula> <tex-math notation="LaTeX">$\lambda _{\text {min}}$ </tex-math></inline-formula> is the minimum difference between any two distinct maximum probability values across the data samples. …”
Get full text

Research on distributed economic dispatching algorithm for information security and privacy protection in smart grid by ZHANG Yanjun, SONG Mingshu, MA Xiaolei

“…In addition, the economic dispatching problem is extended to the distributed online framework to adapt to the time-varying cost function scenario. Under the proposed algorithm, the economic dispatching problem can be solved in an online way, and the algorithm can achieve the same sublinear rate regret $O\left( \sqrt{T} \right)$. …”
Get full text

A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced Digraphs by Rong Hu, Binru Zhang

“…Under mild conditions, we then show that the proposed algorithm can achieve a sublinear expected bound of regret for general local convex objective functions. …”
Get full text

Projection-Free Methods for Online Distributed Quantized Optimization With Strongly Pseudoconvex Cost Functions by Xiaoxi Yan, Yu Li, Muyuan Ma

“…The performance of the algorithm is evaluated using the expectation of dynamic regret. …”
Get full text

Multi-Dimensional Arms for Combinatorial Multi-Armed Bandit by Qi Li, Lijun Cai

“…Previous works have indeed made substantial advancements in designing efficient online selection algorithms. However, the limitation of these works is that they fail to achieve a sublinear regret bound with multi-dimensional arms. …”
Get full text

Heisenberg-Limited Adaptive Gradient Estimation for Multiple Observables by Kaito Wada, Naoki Yamamoto, Nobuyuki Yoshioka

“…This remarkably achieves the scaling of Heisenberg limit 1/ε, a fundamental bound on the estimation precision in terms of mean squared error, together with the sublinear scaling of the number of observables M. The proposed method is an adaptive version of the quantum gradient-estimation algorithm and has a resource-efficient implementation due to its adaptiveness. …”
Get full text

Multilevel Constrained Bandits: A Hierarchical Upper Confidence Bound Approach with Safety Guarantees by Ali Baheri

“…We propose the HC-UCB (hierarchical constrained upper confidence bound) algorithm to solve the HCB problem. The algorithm uses confidence bounds within a hierarchical setting to balance exploration and exploitation while respecting constraints at all levels. …”
Get full text

Partial symmetric regularized alternating direction method of multipliers for non-convex split feasibility problems by Yue Zhao, Meixia Li, Xiaowei Pan, Jingjing Tan

“…And when the augmented Lagrangian function satisfies the KL property, the strong convergence of the algorithm is obtained. Furthermore, when the correlation function has a special structure, the sublinear and linear convergence rates of the algorithm are ensured. …”
Get full text

Joint-Pixel Inversion for Ground Phase and Forest Height Estimation Using Spaceborne Polarimetric SAR Interferometry by Zenghui Huang, Jingyu Gao, Xiaolei Lv, Xiaoshuai Li

“…To solve the non-parallelizable problem of the alternating direction method of multipliers (ADMM), we devise a new parallelizable ADMM algorithm and prove its sublinear convergence. With the contextual information of neighboring pixels, JPO can provide more reliable forest height estimation and reduce the overestimation caused by additional decorrelation. …”
Get full text

Behavior-driven forecasts of neighborhood-level COVID-19 spread in New York City. by Renquan Zhang, Jilei Tai, Qing Yao, Wan Yang, Kai Ruggeri, Jeffrey Shaman, Sen Pei

“…We fit this model to neighborhood-level COVID-19 case data in NYC and further couple this model with a data assimilation algorithm to generate short-term forecasts of neighborhood-level COVID-19 cases in 2020. …”
Get full text