arXiv subjects

Quynh Nguyen

Publications and source records attributed to Quynh Nguyen.

30 records · Page 2Linked to original sources

arXiv2019

Jupiter: A Networked Computing Architecture

In the era of Internet of Things, there is an increasing demand for networked computing to support the requirements of the time-constrained, compute-intensive distributed applications such as multi-camera video processing and data fusion for security. We present Jupiter, an open source networked computing system that inputs a Directed Acyclic Graph (DAG)-based computational task graph to efficiently distribute the tasks among a set of networked compute nodes regardless of their geographical separations and orchestrates the execution of the DAG thereafter. This Kubernetes container-orchestration-based system supports both centralized and decentralized scheduling algorithms for optimally mapping the tasks based on information from a range of profilers: network profilers, resource profilers, and execution time profilers. While centralized scheduling algorithms with global knowledge have been popular among the grid/cloud computing community, we argue that a distributed scheduling approach is better suited for networked computing due to lower communication and computation overhead in the face of network dynamics. To this end, we propose and implement a new class of distributed scheduling algorithms called WAVE on the Jupiter system. We present a set of real world experiments on two separate testbeds - one a world-wide network of 90 cloud computers across 8 cities and the other a cluster of 30 Raspberry pi nodes, over a simple networked computing application called Distributed Network Anomaly Detector (DNAD). We show that despite using more localized knowledge, a distributed WAVE greedy algorithm can achieve similar performance as a classical centralized scheduling algorithm called Heterogeneous Earliest Finish Time (HEFT), suitably enhanced for the Jupiter system.

cs.DC↗

arXiv2019

On Connected Sublevel Sets in Deep Learning

This paper shows that every sublevel set of the loss function of a class of deep over-parameterized neural nets with piecewise linear activation functions is connected and unbounded. This implies that the loss has no bad local valleys and all of its global minima are connected within a unique and potentially very large global valley.

cs.LG↗

arXiv2019

Light with a self-torque: extreme-ultraviolet beams with time-varying orbital angular momentum

Twisted light fields carrying orbital angular momentum (OAM) provide powerful capabilities for applications in optical communications, microscopy, quantum optics and microparticle rotation. Here we introduce and experimentally validate a new class of light beams, whose unique property is associated with a temporal OAM variation along a pulse: the self-torque of light. Self-torque is a phenomenon that can arise from matter-field interactions in electrodynamics and general relativity, but to date, there has been no optical analog. In particular, the self-torque of light is an inherent property, which is distinguished from the mechanical torque exerted by OAM beams when interacting with physical systems. We demonstrate that self-torqued beams in the extreme-ultraviolet (EUV) naturally arise as a necessary consequence of angular momentum conservation in non-perturbative high-order harmonic generation when driven by time-delayed pulses with different OAM. In addition, the time-dependent OAM naturally induces an azimuthal frequency chirp, which provides a signature for monitoring the self-torque of high-harmonic EUV beams. Such self-torqued EUV beams can serve as unique tools for imaging magnetic and topological excitations, for launching selective excitation of quantum matter, and for manipulating molecules and nanostructures on unprecedented time and length scales.

physics.optics↗

arXiv2018

On the loss landscape of a class of deep neural networks with no bad local valleys

We identify a class of over-parameterized deep neural networks with standard activation functions and cross-entropy loss which provably have no bad local valley, in the sense that from any point in parameter space there exists a continuous path on which the cross-entropy loss is non-increasing and gets arbitrarily close to zero. This implies that these networks have no sub-optimal strict local minima.

cs.LG↗

arXiv2018

Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions

In the recent literature the important role of depth in deep learning has been emphasized. In this paper we argue that sufficient width of a feedforward network is equally important by answering the simple question under which conditions the decision regions of a neural network are connected. It turns out that for a class of activation functions including leaky ReLU, neural networks having a pyramidal structure, that is no layer has more hidden units than the input dimension, produce necessarily connected decision regions. This implies that a sufficiently wide hidden layer is necessary to guarantee that the network can produce disconnected decision regions. We discuss the implications of this result for the construction of neural networks, in particular the relation to the problem of adversarial manipulation of classifiers.

cs.LG↗

arXiv2018

Optimization Landscape and Expressivity of Deep CNNs

We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has more neurons than the number of training samples. This condition holds e.g. for the VGG network. Furthermore, we provide for such wide CNNs necessary and sufficient conditions for global minima with zero training error. For the case where the wide layer is followed by a fully connected layer we show that almost every critical point of the empirical loss is a global minimum with zero training error. Our analysis suggests that both depth and width are very important in deep learning. While depth brings more representational power and allows the network to learn high level features, width smoothes the optimization landscape of the loss function in the sense that a sufficiently wide network has a well-behaved loss surface with almost no bad local minima.

cs.LG↗

arXiv2018

How well can machine learning predict demographics of social media users?

The wide use of social media sites and other digital technologies have resulted in an unprecedented availability of digital data that are being used to study human behavior across research domains. Although unsolicited opinions and sentiments are available on these platforms, demographic details are usually missing. Demographic information is pertinent in fields such as demography and public health, where significant differences can exist across sex, racial and socioeconomic groups. In an attempt to address this shortcoming, a number of academic studies have proposed methods for inferring the demographics of social media users using details such as names, usernames, and network characteristics. Gender is the easiest trait to accurately infer, with measures of accuracy higher than 90 percent in some studies. Race, ethnicity and age tend to be more challenging to predict for a variety of reasons including the novelty of social media to certain age groups and a lack of significant deviations in user details across racial and ethnic groups. Although the endeavor to predict user demographics is plagued with ethical questions regarding privacy and data ownership, knowing the demographics in a data sample can aid in addressing issues of bias and population representation, so that existing societal inequalities are not exacerbated.

cs.SI↗

arXiv2017

The loss surface of deep and wide neural networks

While the optimization problem behind deep neural networks is highly non-convex, it is frequently observed in practice that training deep networks seems possible without getting stuck in suboptimal points. It has been argued that this is the case as all local minima are close to being globally optimal. We show that this is (almost) true, in fact almost all local minima are globally optimal, for a fully connected network with squared loss and analytic activation function given that the number of hidden units of one layer of the network is larger than the number of training points and the network structure from this layer on is pyramidal.

cs.LG↗

arXiv2016

Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods

The optimization problem behind neural networks is highly non-convex. Training with stochastic gradient descent and variants requires careful parameter tuning and provides no guarantee to achieve the global optimum. In contrast we show under quite weak assumptions on the data that a particular class of feedforward neural networks can be trained globally optimal with a linear convergence rate with our nonlinear spectral method. Up to our knowledge this is the first practically feasible method which achieves such a guarantee. While the method can in principle be applied to deep networks, we restrict ourselves for simplicity in this paper to one and two hidden layer networks. Our experiments confirm that these models are rich enough to achieve good performance on a series of real-world datasets.

cs.LG↗

arXiv2016

An Efficient Multilinear Optimization Framework for Hypergraph Matching

Hypergraph matching has recently become a popular approach for solving correspondence problems in computer vision as it allows to integrate higher-order geometric information. Hypergraph matching can be formulated as a third-order optimization problem subject to the assignment constraints which turns out to be NP-hard. In recent work, we have proposed an algorithm for hypergraph matching which first lifts the third-order problem to a fourth-order problem and then solves the fourth-order problem via optimization of the corresponding multilinear form. This leads to a tensor block coordinate ascent scheme which has the guarantee of providing monotonic ascent in the original matching score function and leads to state-of-the-art performance both in terms of achieved matching score and accuracy. In this paper we show that the lifting step to a fourth-order problem can be avoided yielding a third-order scheme with the same guarantees and performance but being two times faster. Moreover, we introduce a homotopy type method which further improves the performance.

cs.CV↗

arXiv2016

Latent Embeddings for Zero-shot Classification

We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method augments the state-of-the-art bilinear compatibility model by incorporating latent variables. Instead of learning a single bilinear map, it learns a collection of maps with the selection, of which map to use, being a latent variable for the current image-class pair. We train the model with a ranking based objective function which penalizes incorrect rankings of the true class for a given image. We empirically demonstrate that our model improves the state-of-the-art for various class embeddings consistently on three challenging publicly available datasets for the zero-shot setting. Moreover, our method leads to visually highly interpretable results with clear clusters of different fine-grained object properties that correspond to different latent variable maps.

cs.CV↗

arXiv2015

A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching

The estimation of correspondences between two images resp. point sets is a core problem in computer vision. One way to formulate the problem is graph matching leading to the quadratic assignment problem which is NP-hard. Several so called second order methods have been proposed to solve this problem. In recent years hypergraph matching leading to a third order problem became popular as it allows for better integration of geometric information. For most of these third order algorithms no theoretical guarantees are known. In this paper we propose a general framework for tensor block coordinate ascent methods for hypergraph matching. We propose two algorithms which both come along with the guarantee of monotonic ascent in the matching score on the set of discrete assignment matrices. In the experiments we show that our new algorithms outperform previous work both in terms of achieving better matching scores and matching accuracy. This holds in particular for very challenging settings where one has a high number of outliers and other forms of noise.

cs.CV↗