arXiv subjects

Haoran Sun

Publications and source records attributed to Haoran Sun.

134 records · Page 8Linked to original sources

arXiv2019

Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach

Many modern large-scale machine learning problems benefit from decentralized and stochastic optimization. Recent works have shown that utilizing both decentralized computing and local stochastic gradient estimates can outperform state-of-the-art centralized algorithms, in applications involving highly non-convex problems, such as training deep neural networks. In this work, we propose a decentralized stochastic algorithm to deal with certain smooth non-convex problems where there are $m$ nodes in the system, and each node has a large number of samples (denoted as $n$). Differently from the majority of the existing decentralized learning algorithms for either stochastic or finite-sum problems, our focus is given to both reducing the total communication rounds among the nodes, while accessing the minimum number of local data samples. In particular, we propose an algorithm named D-GET (decentralized gradient estimation and tracking), which jointly performs decentralized gradient estimation (which estimates the local gradient using a subset of local samples) and gradient tracking (which tracks the global full gradient using local estimates). We show that, to achieve certain $ε$ stationary solution of the deterministic finite sum problem, the proposed algorithm achieves an $\mathcal{O}(mn^{1/2}ε^{-1})$ sample complexity and an $\mathcal{O}(ε^{-1})$ communication complexity. These bounds significantly improve upon the best existing bounds of $\mathcal{O}(mnε^{-1})$ and $\mathcal{O}(ε^{-1})$, respectively. Similarly, for online problems, the proposed method achieves an $\mathcal{O}(m ε^{-3/2})$ sample complexity and an $\mathcal{O}(ε^{-1})$ communication complexity, while the best existing bounds are $\mathcal{O}(mε^{-2})$ and $\mathcal{O}(ε^{-2})$, respectively.

math.OC↗

arXiv2019

Boron isotope effect on the thermal conductivity of boron arsenide single crystals

Boron arsenide (BAs) with a zinc blende structure has recently been discovered to exhibit unusual and ultrahigh thermal conductivity (k), providing a new outlook for research on BAs and other high thermal conductivity materials. Technology for BAs crystal growth has been continuously improving, however, the influence of boron isotopes, pure or mixed, on the thermal conductivity in BAs is still not completely clear. Here we report detailed studies on the growth of single crystals of BAs with different isotopic ratios and demonstrate that the k of isotopically pure BAs is at least 10% higher than that of BAs grown from natural B. Raman spectroscopy characterization shows differences in scattering among various BAs samples. The presented results will be helpful in guiding further studies on the influence of isotopes on optimizing k in BAs.

cond-mat.mtrl-sci↗

arXiv2019

Distributed Non-Convex First-Order Optimization and Information Processing: Lower Complexity Bounds and Rate Optimal Algorithms

We consider a class of popular distributed non-convex optimization problems, in which agents connected by a network $\mathcal{G}$ collectively optimize a sum of smooth (possibly non-convex) local objective functions. We address the following question: if the agents can only access the gradients of local functions, what are the fastest rates that any distributed algorithms can achieve, and how to achieve those rates. First, we show that there exist difficult problem instances, such that it takes a class of distributed first-order methods at least $\mathcal{O}(1/\sqrt{ξ(\mathcal{G})} \times \bar{L} /ε)$ communication rounds to achieve certain $ε$-solution [where $ξ(\mathcal{G})$ denotes the spectral gap of the graph Laplacian matrix, and $\bar{L}$ is some Lipschitz constant]. Second, we propose (near) optimal methods whose rates match the developed lower rate bound (up to a polylog factor). The key in the algorithm design is to properly embed the classical polynomial filtering techniques into modern first-order algorithms. To the best of our knowledge, this is the first time that lower rate bounds and optimal methods have been developed for distributed non-convex optimization problems.

math.OC↗

arXiv2019

Alice's Adventures in the Markovian World

This paper proposes an algorithm Alice having no access to the physics law of the environment, which is actually linear with stochastic noise, and learns to make decisions directly online without a training phase or a stable policy as initial input. Neither estimating the system parameters nor the value functions online, the proposed algorithm generalizes one of the most fundamental online learning algorithms Follow-the-Leader into a linear Gauss-Markov process setting, with a regularization term similar to the momentum method in the gradient descent algorithm, and a feasible online constraint inspired by Lyapunov's Second Theorem. The proposed algorithm is considered as a mirror optimization to the model predictive control. Only knowing the state-action alignment relationship, with the ability to observe every state exactly, a no-regret proof of the algorithm without state noise is given. The analysis of the general linear system with stochastic noise is shown with a sufficient condition for the no-regret proof. The simulations compare the performance of Alice with another recent work and verify the great flexibility of Alice.

eess.SY↗

arXiv2019

Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms

Recently, there is a growing interest in the study of median-based algorithms for distributed non-convex optimization. Two prominent such algorithms include signSGD with majority vote, an effective approach for communication reduction via 1-bit compression on the local gradients, and medianSGD, an algorithm recently proposed to ensure robustness against Byzantine workers. The convergence analyses for these algorithms critically rely on the assumption that all the distributed data are drawn iid from the same distribution. However, in applications such as Federated Learning, the data across different nodes or machines can be inherently heterogeneous, which violates such an iid assumption. This work analyzes signSGD and medianSGD in distributed settings with heterogeneous data. We show that these algorithms are non-convergent whenever there is some disparity between the expected median and mean over the local gradients. To overcome this gap, we provide a novel gradient correction mechanism that perturbs the local gradients with noise, together with a series results that provable close the gap between mean and median of the gradients. The proposed methods largely preserve nice properties of these methods, such as the low per-iteration communication complexity of signSGD, and further enjoy global convergence to stationary solutions. Our perturbation technique can be of independent interest when one wishes to estimate mean through a median estimator.

cs.LG↗

arXiv2018

Locating the boundaries of Pareto fronts: A Many-Objective Evolutionary Algorithm Based on Corner Solution Search

In this paper, an evolutionary many-objective optimization algorithm based on corner solution search (MaOEA-CS) was proposed. MaOEA-CS implicitly contains two phases: the exploitative search for the most important boundary optimal solutions - corner solutions, at the first phase, and the use of angle-based selection [1] with the explorative search for the extension of PF approximation at the second phase. Due to its high efficiency and robustness to the shapes of PFs, it has won the CEC'2017 Competition on Evolutionary Many-Objective Optimization. In addition, MaOEA-CS has also been applied on two real-world engineering optimization problems with very irregular PFs. The experimental results show that MaOEA-CS outperforms other six state-of-the-art compared algorithms, which indicates it has the ability to handle real-world complex optimization problems with irregular PFs.

cs.AI↗

arXiv2017

Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management

For the past couple of decades, numerical optimization has played a central role in addressing wireless resource management problems such as power control and beamformer design. However, optimization algorithms often entail considerable complexity, which creates a serious gap between theoretical design/analysis and real-time processing. To address this challenge, we propose a new learning-based approach. The key idea is to treat the input and output of a resource allocation algorithm as an unknown non-linear mapping and use a deep neural network (DNN) to approximate it. If the non-linear mapping can be learned accurately by a DNN of moderate size, then resource allocation can be done in almost real time -- since passing the input through a DNN only requires a small number of simple operations. In this work, we address both the thereotical and practical aspects of DNN-based algorithm approximation with applications to wireless resource management. We first pin down a class of optimization algorithms that are `learnable' in theory by a fully connected DNN. Then, we focus on DNN-based approximation to a popular power allocation algorithm named WMMSE (Shi {\it et al} 2011). We show that using a DNN to approximate WMMSE can be fairly accurate -- the approximation error $ε$ depends mildly [in the order of $\log(1/ε)$] on the numbers of neurons and layers of the DNN. On the implementation side, we use extensive numerical simulations to demonstrate that DNNs can achieve orders of magnitude speedup in computational time compared to state-of-the-art power allocation algorithms based on optimization.

cs.IT↗

arXiv2016

Inexact Block Coordinate Descent Methods For Symmetric Nonnegative Matrix Factorization

Symmetric nonnegative matrix factorization (SNMF) is equivalent to computing a symmetric nonnegative low rank approximation of a data similarity matrix. It inherits the good data interpretability of the well-known nonnegative matrix factorization technique and have better ability of clustering nonlinearly separable data. In this paper, we focus on the algorithmic aspect of the SNMF problem and propose simple inexact block coordinate decent methods to address the problem, leading to both serial and parallel algorithms. The proposed algorithms have guaranteed stationary convergence and can efficiently handle large-scale and/or sparse SNMF problems. Extensive simulations verify the effectiveness of the proposed algorithms compared to recent state-of-the-art algorithms.

math.NA↗