no code implementations • 3 Feb 2022 • Zhen Dai, Yury Makarychev, Ali Vakilian
For this special case, we present an $O(\log k)$-approximation algorithm that runs in $(kf)^{O(\ell)}\log n + poly(n)$ time.
no code implementations • NeurIPS 2021 • Zhen Dai, Mina Karzand, Nathan Srebro
For different parameterizations (mappings from parameters to predictors), we study the regularization cost in predictor space induced by $l_2$ regularization on the parameters (weights).
no code implementations • 18 Nov 2020 • Zhen Dai, Joseph Euzebe Tate
This paper proposes a method of identifying single line outages in power systems based on phasor measurement unit (PMU) measurements and ac power flow models.
no code implementations • ICML 2020 • Blake Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai, Brian Bullins, H. Brendan McMahan, Ohad Shamir, Nathan Srebro
We study local SGD (also known as parallel SGD and federated averaging), a natural and frequently used stochastic distributed optimization method.