亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Model compression and model defense for deep neural networks (DNNs) have been extensively and individually studied. Considering the co-importance of model compactness and robustness in practical applications, several prior works have explored to improve the adversarial robustness of the sparse neural networks. However, the structured sparse models obtained by the exiting works suffer severe performance degradation for both benign and robust accuracy, thereby causing a challenging dilemma between robustness and structuredness of the compact DNNs. To address this problem, in this paper, we propose CSTAR, an efficient solution that can simultaneously impose the low-rankness-based Compactness, high STructuredness and high Adversarial Robustness on the target DNN models. By formulating the low-rankness and robustness requirement within the same framework and globally determining the ranks, the compressed DNNs can simultaneously achieve high compression performance and strong adversarial robustness. Evaluations for various DNN models on different datasets demonstrate the effectiveness of CSTAR. Compared with the state-of-the-art robust structured pruning methods, CSTAR shows consistently better performance. For instance, when compressing ResNet-18 on CIFAR-10, CSTAR can achieve up to 20.07% and 11.91% improvement for benign accuracy and robust accuracy, respectively. For compressing ResNet-18 with 16x compression ratio on Imagenet, CSTAR can obtain 8.58% benign accuracy gain and 4.27% robust accuracy gain compared to the existing robust structured pruning method.

We study the classical metric $k$-median clustering problem over a set of input rankings (i.e., permutations), which has myriad applications, from social-choice theory to web search and databases. A folklore algorithm provides a $2$-approximate solution in polynomial time for all $k=O(1)$, and works irrespective of the underlying distance measure, so long it is a metric; however, going below the $2$-factor is a notorious challenge. We consider the Ulam distance, a variant of the well-known edit-distance metric, where strings are restricted to be permutations. For this metric, Chakraborty, Das, and Krauthgamer [SODA, 2021] provided a $(2-\delta)$-approximation algorithm for $k=1$, where $\delta\approx 2^{-40}$. Our primary contribution is a new algorithmic framework for clustering a set of permutations. Our first result is a $1.999$-approximation algorithm for the metric $k$-median problem under the Ulam metric, that runs in time $(k \log (nd))^{O(k)}n d^3$ for an input consisting of $n$ permutations over $[d]$. In fact, our framework is powerful enough to extend this result to the streaming model (where the $n$ input permutations arrive one by one) using only polylogarithmic (in $n$) space. Additionally, we show that similar results can be obtained even in the presence of outliers, which is presumably a more difficult problem.

With the development of Information and Communication Technologies, trust has been applied more and more in various scenarios. At the same time, different organizations have published a series of trust frameworks to support the implementation of trust. There are also academic paper discussing about these trust standards, however, most of them only focus on a specific application. Unlike existing works, this paper provides an overview of all current available trust standards related to communication networks and future digital world from several main organizations. To be specific, this paper summarizes and organizes all these trust standards into three layers: trust foundation, trust elements, and trust applications. We then analysis these trust standards and discuss their contribution in a systematic way. We discuss the motivations behind each current in forced standards, analyzes their frameworks and solutions, and presents their role and impact on communication works and future digital world. Finally, we give our suggestions on the trust work that needs to be standardized in future.

The research area of algorithms with predictions has seen recent success showing how to incorporate machine learning into algorithm design to improve performance when the predictions are correct, while retaining worst-case guarantees when they are not. Most previous work has assumed that the algorithm has access to a single predictor. However, in practice, there are many machine learning methods available, often with incomparable generalization guarantees, making it hard to pick a best method a priori. In this work we consider scenarios where multiple predictors are available to the algorithm and the question is how to best utilize them. Ideally, we would like the algorithm's performance to depend on the quality of the best predictor. However, utilizing more predictions comes with a cost, since we now have to identify which prediction is the best. We study the use of multiple predictors for a number of fundamental problems, including matching, load balancing, and non-clairvoyant scheduling, which have been well-studied in the single predictor setting. For each of these problems we introduce new algorithms that take advantage of multiple predictors, and prove bounds on the resulting performance.

Financial institutions manage operational risk by carrying out the activities required by regulation, such as collecting loss data, calculating capital requirements, and reporting. The information necessary for this purpose is then collected in the OpRisk databases. Recorded for each OpRisk event are loss amounts, dates, organizational units involved, event types and descriptions. In recent years, operational risk functions have been required to go beyond their regulatory tasks to proactively manage the operational risk, preventing or mitigating its impact. As OpRisk databases also contain event descriptions, usually defined as free text fields, an area of opportunity is the valorization of all the information contained in such records. As far as we are aware of, the present work is the first one that has addressed the application of text analysis techniques to the OpRisk event descriptions. In this way, we have complemented and enriched the established framework of statistical methods based on quantitative data. Specifically, we have applied text analysis methodologies to extract information from descriptions in the OpRisk database. After delicate tasks like data cleaning, text vectorization, and semantic adjustment, we apply methods of dimensionality reduction and several clustering models and algorithms to develop a comparison of their performances and weaknesses. Our results improve retrospective knowledge of loss events and enable to mitigate future risks.

Trust calibration presents a main challenge during the interaction between drivers and automated vehicles (AVs). In order to calibrate trust, it is important to measure drivers' trust in real time. One possible method is through modeling its dynamic changes using machine learning models and physiological measures. In this paper, we proposed a technique based on machine learning models to predict drivers' dynamic trust in conditional AVs using physiological measurements in real time. We conducted the study in a driving simulator where participants were requested to take over control from automated driving in three conditions that included a control condition, a false alarm condition, a miss condition with eight takeover requests (TORs) in different scenarios. Drivers' physiological measures were recorded during the experiment, including galvanic skin response (GSR), heart rate (HR) indices, and eye-tracking metrics. Using five machine learning models, we found that eXtreme Gradient Boosting (XGBoost) performed the best and was able to predict drivers' trust in real time with an f1-score of 89.1%. Our findings provide good implications on how to design an in-vehicle trust monitoring system to calibrate drivers' trust to facilitate interaction between the driver and the AV in real time.

The adaptive processing of structured data is a long-standing research topic in machine learning that investigates how to automatically learn a mapping from a structured input to outputs of various nature. Recently, there has been an increasing interest in the adaptive processing of graphs, which led to the development of different neural network-based methodologies. In this thesis, we take a different route and develop a Bayesian Deep Learning framework for graph learning. The dissertation begins with a review of the principles over which most of the methods in the field are built, followed by a study on graph classification reproducibility issues. We then proceed to bridge the basic ideas of deep learning for graphs with the Bayesian world, by building our deep architectures in an incremental fashion. This framework allows us to consider graphs with discrete and continuous edge features, producing unsupervised embeddings rich enough to reach the state of the art on several classification tasks. Our approach is also amenable to a Bayesian nonparametric extension that automatizes the choice of almost all model's hyper-parameters. Two real-world applications demonstrate the efficacy of deep learning for graphs. The first concerns the prediction of information-theoretic quantities for molecular simulations with supervised neural models. After that, we exploit our Bayesian models to solve a malware-classification task while being robust to intra-procedural code obfuscation techniques. We conclude the dissertation with an attempt to blend the best of the neural and Bayesian worlds together. The resulting hybrid model is able to predict multimodal distributions conditioned on input graphs, with the consequent ability to model stochasticity and uncertainty better than most works. Overall, we aim to provide a Bayesian perspective into the articulated research field of deep learning for graphs.

This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or textures for supervision. Instead, we use the same training data as traditional CNNs. Our method automatically assigns each interpretable filter in a high conv-layer with an object part of a certain category during the learning process. Such explicit knowledge representations in conv-layers of CNN help people clarify the logic encoded in the CNN, i.e., answering what patterns the CNN extracts from an input image and uses for prediction. We have tested our method using different benchmark CNNs with various structures to demonstrate the broad applicability of our method. Experiments have shown that our interpretable filters are much more semantically meaningful than traditional filters.

Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.

Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8,730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.