arXiv subjects

Duong Nguyen

Publications and source records attributed to Duong Nguyen.

At least 37 records · Page 2Linked to original sources

arXiv2023

Bayesian Rationality in Satisfaction Games

We introduce a new paradigm for game theory -- Bayesian satisfaction. This novel approach is a synthesis of the idea of Bayesian rationality introduced by Aumann, and satisfaction games. The concept of Bayesian rationality for which, in part, Robert Aumann was awarded the Nobel Prize in 2005, is concerned with players in a game acting in their own best interest given a subjective knowledge of the other players' behaviours as represented by a probability distribution. Satisfaction games have emerged in the engineering literature as a way of modelling competitive interactions in resource allocation problems where players seek to attain a specified level of utility, rather than trying to maximise utility. In this paper, we explore the relationship between optimality in Aumann's sense (correlated equilibria), and satisfaction in games. We show that correlated equilibria in a satisfaction game represent stable outcomes in which no player can increase their probability of satisfaction by unilateral deviation from the specified behaviour. Thus, we propose a whole new class of equilibrium outcomes in satisfaction games which include existing notions of equilibria in such games. Iterative algorithms for computing such equilibria based on the existing ideas of regret matching are presented and interpreted within the satisfaction framework. Numerical examples of resource allocation are presented to illustrate the behaviour of these algorithms. A notable feature of these algorithms is that they almost always find equilibrium outcomes whereas existing approaches in satisfaction games may not.

cs.GT↗

arXiv2022

Technical Report: Using Static Analysis to Compute Benefit of Tolerating Consistency

Synchronization is the Achilles heel of concurrent programs. Synchronization requirement is often used to ensure that the execution of the concurrent program can be serialized. Without synchronization requirement, a program suffers from consistency violations. Recently, it was shown that if programs are designed to tolerate such consistency violation faults (\cvf{s}) then one can obtain substantial performance gain. Previous efforts to analyze the effect of \cvf-tolerance are limited to run-time analysis of the program to determine if tolerating \cvf{s} can improve the performance. Such run-time analysis is very expensive and provides limited insight. In this work, we consider the question, `Can static analysis of the program predict the benefit of \cvf-tolerance?' We find that the answer to this question is affirmative. Specifically, we use static analysis to evaluate the cost of a \cvf and demonstrate that it can be used to predict the benefit of \cvf-tolerance. We also find that when faced with a large state space, partial analysis of the state space (via sampling) also provides the required information to predict the benefit of \cvf-tolerance. Furthermore, we observe that the \cvf-cost distribution is exponential in nature, i.e., the probability that a \cvf has a cost of $c$ is $A.B^{-c}$, where $A$ and $B$ are constants, i.e., most \cvf{s} cause no/low perturbation whereas a small number of \cvf{s} cause a large perturbation. This opens up new aveneus to evaluate the benefit of \cvf-tolerance.

cs.DC↗

arXiv2022

Impact of the Consistency Model on Checkpointing of Distributed Shared Memory

In this report, we consider the impact of the consistency model on checkpointing and rollback algorithms for distributed shared memory. In particular, we consider specific implementations of four consistency models for distributed shared memory, namely, linearizability, sequential consistency, causal consistency and eventual consistency, and develop checkpointing and rollback algorithms that can be integrated into the implementations of the consistency models. Our results empirically demonstrate that the mechanisms used to implement stronger consistency models lead to simpler or more efficient checkpointing algorithms.

cs.DC↗

arXiv2021

Structured Dropout Variational Inference for Bayesian Neural Networks

Approximate inference in Bayesian deep networks exhibits a dilemma of how to yield high fidelity posterior approximations while maintaining computational efficiency and scalability. We tackle this challenge by introducing a novel variational structured approximation inspired by the Bayesian interpretation of Dropout regularization. Concretely, we focus on the inflexibility of the factorized structure in Dropout posterior and then propose an improved method called Variational Structured Dropout (VSD). VSD employs an orthogonal transformation to learn a structured representation on the variational Gaussian noise with plausible complexity, and consequently induces statistical dependencies in the approximate posterior. Theoretically, VSD successfully addresses the pathologies of previous Variational Dropout methods and thus offers a standard Bayesian justification. We further show that VSD induces an adaptive regularization term with several desirable properties which contribute to better generalization. Finally, we conduct extensive experiments on standard benchmarks to demonstrate the effectiveness of VSD over state-of-the-art variational methods on predictive accuracy, uncertainty estimation, and out-of-distribution detection.

cs.LG↗

arXiv2021

Achieving Causality with Physical Clocks

Physical clocks provide more precision than applications can use. For example, a 64 bit NTP clock allows a precision of 233 picoseconds. In this paper, we focus on whether the least significant bits that are not useful to the applications could be used to track (one way) causality among events. We present PWC (Physical clock With Causality) that uses the extraneous bits in the physical clock. We show that PWC is very robust to errors in clock skew and transient errors. We show that PWC can be used as both a physical and logical clock for a typical distributed application even if just 6-9 extraneous bits (corresponding to precision of 15-120 nanoseconds) are available. Another important characteristic of PWC is that the standard integer < operation can be used to compare timestamps to deduce (one-way) causality among events. Thus, PWC is significantly more versatile than previous approaches for using the physical clock to provide causality information.

cs.DC↗

arXiv2021

Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations

The data-driven recovery of the unknown governing equations of dynamical systems has recently received an increasing interest. However, the identification of governing equations remains challenging when dealing with noisy and partial observations. Here, we address this challenge and investigate variational deep learning schemes. Within the proposed framework, we jointly learn an inference model to reconstruct the true states of the system and the governing laws of these states from series of noisy and partial data. In doing so, this framework bridges classical data assimilation and state-of-the-art machine learning techniques. We also demonstrate that it generalises state-of-the-art methods. Importantly, both the inference model and the governing model embed stochastic components to account for stochastic variabilities, model errors, and reconstruction uncertainties. Various experiments on chaotic and stochastic dynamical systems support the relevance of our scheme w.r.t. state-of-the-art approaches.

cs.LG↗

arXiv2021

GeoTrackNet-A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection

Representing maritime traffic patterns and detecting anomalies from them are key to vessel monitoring and maritime situational awareness. We propose a novel approach -- referred to as GeoTrackNet -- for maritime anomaly detection from AIS data streams. Our model exploits state-of-the-art neural network schemes to learn a probabilistic representation of AIS tracks and a contrario detection to detect abnormal events. The neural network provides a new means to capture complex and heterogeneous patterns in vessels' behaviours, while the \textit{a contrario} detector takes into account the fact that the learnt distribution may be location-dependent. Experiments on a real AIS dataset comprising more than 4.2 million AIS messages demonstrate the relevance of the proposed method compared with state-of-the-art schemes.

cs.LG↗

arXiv2020

Detection of Abnormal Vessel Behaviours from AIS data using GeoTrackNet: from the Laboratory to the Ocean

The constant growth of maritime traffic leads to the need of automatic anomaly detection, which has been attracting great research attention. Information provided by AIS (Automatic Identification System) data, together with recent outstanding progresses of deep learning, make vessel monitoring using neural networks (NNs) a very promising approach. This paper analyses a novel neural network we have recently introduced -- GeoTrackNet -- regarding operational contexts. Especially, we aim to evaluate (i) the relevance of the abnormal behaviours detected by GeoTrackNet with respect to expert interpretations, (ii) the extent to which GeoTrackNet may process AIS data streams in real time. We report experiments showing the high potential to meet operational levels of the model.

cs.CY↗

arXiv2020

Technical Report: Benefits of Stabilization versus Rollback in Self-Stabilizing Graph-Based Applications on Eventually Consistent Key-Value Stores

In this paper, we evaluate and compare the performance of two approaches, namely self-stabilization and rollback, to handling consistency violating faults (\cvf) that occur when a self-stabilizing distributed graph-based program is executed on an eventually consistent key-value store. Consistency violating faults are caused by reading wrong values due to weaker level of consistency provided by the key-value store. One way to deal with these faults is to utilize rollback whereas another way is to rely on the property of self-stabilization that is expected to provide recovery from arbitrary states. We evaluate both these approaches in different case studies --planar graph coloring, arbitrary graph coloring, and maximal matching-- as well as for different problem dimensions such as input data characteristics, workload partition, and network latency. We also consider the effect of executing non-stabilizing algorithm with rollback with a similar stabilizing algorithm that does not utilize rollback.

cs.DC↗

arXiv2020

Neuroevolution of Self-Interpretable Agents

Inattentional blindness is the psychological phenomenon that causes one to miss things in plain sight. It is a consequence of the selective attention in perception that lets us remain focused on important parts of our world without distraction from irrelevant details. Motivated by selective attention, we study the properties of artificial agents that perceive the world through the lens of a self-attention bottleneck. By constraining access to only a small fraction of the visual input, we show that their policies are directly interpretable in pixel space. We find neuroevolution ideal for training self-attention architectures for vision-based reinforcement learning (RL) tasks, allowing us to incorporate modules that can include discrete, non-differentiable operations which are useful for our agent. We argue that self-attention has similar properties as indirect encoding, in the sense that large implicit weight matrices are generated from a small number of key-query parameters, thus enabling our agent to solve challenging vision based tasks with at least 1000x fewer parameters than existing methods. Since our agent attends to only task critical visual hints, they are able to generalize to environments where task irrelevant elements are modified while conventional methods fail. Videos of our results and source code available at https://attentionagent.github.io/

cs.NE↗

arXiv2019

Benefits of Stabilization versus Rollback in Eventually Consistent Key-Value Stores

In this paper, we evaluate and compare the performance of two approaches, namely self-stabilization and rollback, to handling consistency violation faults (cvf) that occurred when a distributed program is executed on eventually consistent key-value store. We observe that self-stabilization is usually better than rollbacks in our experiments. Moreover, when we aggressively allow more cvf in exchange of eliminating mechanisms for guaranteeing atomicity requirements of actions, we observe the programs in our case studies achieve a speedup between 2--15 times compared with the standard implementation. We also analyze different factors that contribute to the results. Our results and analysis are useful in helping a system designer choose proper design options for their program.

cs.DC↗

arXiv2019

Using Weaker Consistency Models with Monitoring and Recovery for Improving Performance of Key-Value Stores

Consistency properties provided by most key-value stores can be classified into sequential consistency and eventual consistency. The former is easier to program with but suffers from lower performance whereas the latter suffers from potential anomalies while providing higher performance. We focus on the problem of what a designer should do if he/she has an algorithm that works correctly with sequential consistency but is faced with an underlying key-value store that provides a weaker consistency. We propose a detect-rollback based approach: The designer identifies a correctness predicate, say $P$, and continues to run the protocol, as our system monitors $P$. If $P$ is violated (because of weaker consistency), the system rolls back and resumes the computation at a state where $P$ holds. We evaluate this approach with graph-based applications running on the Voldemort key-value store. Our experiments with deployment on Amazon AWS EC2 instances shows that using eventual consistency with monitoring can provide a $50\%$ -- $80\%$ increase in throughput when compared with sequential consistency. We also observe that the overhead of the monitoring itself was low (typically less than $4\%$) and the latency of detecting violations was small. In particular, in a scenario designed to intentionally cause a large number of violations, more than $99.9\%$ of violations were detected in less than 50 milliseconds in regional networks, and in less than 3 seconds in global networks. We find that for some applications, frequent rollback can cause the program using eventual consistency to effectively \textit{stall}. We propose alternate mechanisms for dealing with re-occurring rollbacks. Overall, for applications considered in this paper, we find that even with rollback, eventual consistency provides better performance than using sequential consistency.

cs.DC↗

arXiv2019

Learning Latent Dynamics for Partially-Observed Chaotic Systems

This paper addresses the data-driven identification of latent dynamical representations of partially-observed systems, i.e., dynamical systems for which some components are never observed, with an emphasis on forecasting applications, including long-term asymptotic patterns. Whereas state-of-the-art data-driven approaches rely on delay embeddings and linear decompositions of the underlying operators, we introduce a framework based on the data-driven identification of an augmented state-space model using a neural-network-based representation. For a given training dataset, it amounts to jointly learn an ODE (Ordinary Differential Equation) representation in the latent space and reconstructing latent states. Through numerical experiments, we demonstrate the relevance of the proposed framework w.r.t. state-of-the-art approaches in terms of short-term forecasting performance and long-term behaviour. We further discuss how the proposed framework relates to Koopman operator theory and Takens' embedding theorem.

stat.ML↗

arXiv2019

EM-like Learning Chaotic Dynamics from Noisy and Partial Observations

The identification of the governing equations of chaotic dynamical systems from data has recently emerged as a hot topic. While the seminal work by Brunton et al. reported proof-of-concepts for idealized observation setting for fully-observed systems, {\em i.e.} large signal-to-noise ratios and high-frequency sampling of all system variables, we here address the learning of data-driven representations of chaotic dynamics for partially-observed systems, including significant noise patterns and possibly lower and irregular sampling setting. Instead of considering training losses based on short-term prediction error like state-of-the-art learning-based schemes, we adopt a Bayesian formulation and state this issue as a data assimilation problem with unknown model parameters. To solve for the joint inference of the hidden dynamics and of model parameters, we combine neural-network representations and state-of-the-art assimilation schemes. Using iterative Expectation-Maximization (EM)-like procedures, the key feature of the proposed inference schemes is the derivation of the posterior of the hidden dynamics. Using a neural-network-based Ordinary Differential Equation (ODE) representation of these dynamics, we investigate two strategies: their combination to Ensemble Kalman Smoothers and Long Short-Term Memory (LSTM)-based variational approximations of the posterior. Through numerical experiments on the Lorenz-63 system with different noise and time sampling settings, we demonstrate the ability of the proposed schemes to recover and reproduce the hidden chaotic dynamics, including their Lyapunov characteristic exponents, when classic machine learning approaches fail.

cs.LG↗

arXiv2019

Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection

In this paper, we adapt Recurrent Neural Networks with Stochastic Layers, which are the state-of-the-art for generating text, music and speech, to the problem of acoustic novelty detection. By integrating uncertainty into the hidden states, this type of network is able to learn the distribution of complex sequences. Because the learned distribution can be calculated explicitly in terms of probability, we can evaluate how likely an observation is then detect low-probability events as novel. The model is robust, highly unsupervised, end-to-end and requires minimum preprocessing, feature engineering or hyperparameter tuning. An experiment on a benchmark dataset shows that our model outperforms the state-of-the-art acoustic novelty detectors.

eess.AS↗

arXiv2018

Benefit of Self-Stabilizing Protocols in Eventually Consistent Key-Value Stores: A Case Study

In this paper, we focus on the implementation of distributed programs in using a key-value store where the state of the nodes is stored in a replicated and partitioned data store to improve performance and reliability. Applications of such algorithms occur in weather monitoring, social media, etc. We argue that these applications should be designed to be stabilizing so that they recover from an arbitrary state to a legitimate state. Specifically, if we use a stabilizing algorithm then we can work with more efficient implementations that provide eventual consistency rather than sequential consistency where the data store behaves as if there is just one copy of the data. We find that, although the use of eventual consistency results in consistency violation faults (cvf) where some node executes its action incorrectly because it relies on an older version of the data, the overall performance of the resulting protocol is better. We use experimental analysis to evaluate the expected improvement. We also identify other variations of stabilization that can provide additional guarantees in the presence of eventual consistency.Finally, we note that if the underlying algorithm is not stabilizing, even a single \cvf may cause the algorithm to fail completely thereby making it impossible to benefit from this approach.

cs.DC↗

arXiv2018

BiasedWalk: Biased Sampling for Representation Learning on Graphs

Network embedding algorithms are able to learn latent feature representations of nodes, transforming networks into lower dimensional vector representations. Typical key applications, which have effectively been addressed using network embeddings, include link prediction, multilabel classification and community detection. In this paper, we propose BiasedWalk, a scalable, unsupervised feature learning algorithm that is based on biased random walks to sample context information about each node in the network. Our random-walk based sampling can behave as Breath-First-Search (BFS) and Depth-First-Search (DFS) samplings with the goal to capture homophily and role equivalence between the nodes in the network. We have performed a detailed experimental evaluation comparing the performance of the proposed algorithm against various baseline methods, on several datasets and learning tasks. The experiment results show that the proposed method outperforms the baseline ones in most of the tasks and datasets.

cs.LG↗

arXiv2018

A Multi-task Deep Learning Architecture for Maritime Surveillance using AIS Data Streams

In a world of global trading, maritime safety, security and efficiency are crucial issues. We propose a multi-task deep learning framework for vessel monitoring using Automatic Identification System (AIS) data streams. We combine recurrent neural networks with latent variable modeling and an embedding of AIS messages to a new representation space to jointly address key issues to be dealt with when considering AIS data streams: massive amount of streaming data, noisy data and irregular timesampling. We demonstrate the relevance of the proposed deep learning framework on real AIS datasets for a three-task setting, namely trajectory reconstruction, anomaly detection and vessel type identification.

cs.LG↗