Accuracy is the most important parameter among few others which defines the effectiveness of a machine learning algorithm. Higher accuracy is always desirable. Now, there is a vast number of well established learning algorithms already present in the scientific domain. Each one of them has its own merits and demerits. Merits and demerits are evaluated in terms of accuracy, speed of convergence, complexity of the algorithm, generalization property, and robustness among many others. Also the learning algorithms are data-distribution dependent. Each learning algorithm is suitable for a particular distribution of data. Unfortunately, no dominant classifier exists for all the data distribution, and the data distribution task at hand is usually unknown. Not one classifier can be discriminative well enough if the number of classes are huge. So the underlying problem is that a single classifier is not enough to classify the whole sample space correctly. This thesis is about exploring the different techniques of combining the classifiers so as to obtain the optimal accuracy. Three classifiers are implemented namely plain old nearest neighbor on raw pixels, a structural feature extracted neighbor and Gabor feature extracted nearest neighbor. Five different combination strategies are devised and tested on Tibetan character images and analyzed
Suppose some classifiers are selected from a set of hypothesis classifiers to form an equally-weighted ensemble that selects a member classifier at random for each input example. Then the ensemble has an error bound consisting of the average error bound for the member classifiers, a term for selectivity that varies from zero (if all hypothesis classifiers are selected) to a standard uniform error bound (if only a single classifier is selected), and small constants. There is no penalty for using a richer hypothesis set if the same fraction of the hypothesis classifiers are selected for the ense…
In few-shot domain adaptation (FDA), classifiers for the target domain are trained with accessible labeled data in the source domain (SD) and few labeled data in the target domain (TD). However, data usually contain private information in the current era, e.g., data distributed on personal phones. Thus, the private information will be leaked if we directly access data in SD to train a target-domain classifier (required by FDA methods). In this paper, to thoroughly prevent the privacy leakage in SD, we consider a very challenging problem setting, where the classifier for the TD has to be traine…
In this paper, we propose a simple yet effective method to deal with the violation of the Closed-World Assumption for a classifier. Previous works tend to apply a threshold either on the classification scores or the loss function to reject the inputs that violate the assumption. However, these methods cannot achieve the low False Positive Ratio (FPR) required in safety applications. The proposed method is a rejection option based on hypothesis testing with probabilistic networks. With probabilistic networks, it is possible to estimate the distribution of outcomes instead of a single output. By…
Dalian University of Technology（大连理工大学）；University of Electronic Science and Technology of China（电子科技大学）
Classification is a fundamental problem in machine learning and data mining. During the past decades, numerous classification methods have been presented based on different principles. However, most existing classifiers cast the classification problem as an optimization problem and do not address the issue of statistical significance. In this paper, we formulate the binary classification problem as a two-sample testing problem. More precisely, our classification model is a generic framework that is composed of two steps. In the first step, the distance between the test instance and each traini…
University of Iowa（爱荷华大学）；Hogwarts School of Witchcraft and Wizardry（霍格沃茨魔法学校）
We present a simple hypothesis about a compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations. We also propose a new method for detecting when small input perturbations cause classifier errors, and show theoretical guarantees for the performance of this detection method. We present experimental results with a voice recognition system to demonstrate this method. The ideas in this paper are motivated by a simple analogy bet…
Istituto Dalle Molle di studi sull’Intelligenza Artificiale (IDSIA)（达勒莫勒人工智能研究所 (IDSIA)）；University of Ljubljana（卢布尔雅那大学）
Usually one compares the accuracy of two competing classifiers via null hypothesis significance tests (nhst). Yet the nhst tests suffer from important shortcomings, which can be overcome by switching to Bayesian hypothesis testing. We propose a Bayesian hierarchical model which jointly analyzes the cross-validation results obtained by two classifiers on multiple data sets. It returns the posterior probability of the accuracies of the two classifiers being practically equivalent or significantly different. A further strength of the hierarchical model is that, by jointly analyzing the results ob…
Google Research（谷歌研究院）；Hebrew University（希伯来大学）；Tel-Aviv University（特拉维夫大学）
Complex classifiers may exhibit "embarassing" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. In this work, we focus on one such setting, where a label is perfectly predictable if the input contains certain features, or rules, and otherwise it is predictable by a linear classifier. We define a hypothesis class that captures this notion and determine its sample complexity. We also give evidence that efficient algorithms cannot achieve this sample complexity. We then derive a simple and efficient algorithm and s…
Rajiv Gandhi University of Knowledge Technologies（拉吉夫·甘地知识技术大学）
The Bayesian Classification represents a supervised learning method as well as a statistical method for classification. Assumes an underlying probabilistic model and it allows us to capture uncertainty about the model in a principled way by determining probabilities of the outcomes. This Classification is named after Thomas Bayes (1702-1761), who proposed the Bayes Theorem. Bayesian classification provides practical learning algorithms and prior knowledge and observed data can be combined. Bayesian Classification provides a useful perspective for understanding and evaluating many learning algo…
Samsung AI Center Cambridge（三星剑桥人工智能中心）；University of Edinburgh（爱丁堡大学）
We tackle the domain generalisation (DG) problem by posing it as a domain adaptation (DA) task where we adversarially synthesise the worst-case target domain and adapt a model to that worst-case domain, thereby improving the model's robustness. To synthesise data that is challenging yet semantics-preserving, we generate Fourier amplitude images and combine them with source domain phase images, exploiting the widely believed conjecture from signal processing that amplitude spectra mainly determines image style, while phase data mainly captures image semantics. To synthesise a worst-case domain …
Although deep neural networks are effective on supervised learning tasks, they have been shown to be brittle. They are prone to overfitting on their training distribution and are easily fooled by small adversarial perturbations. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. We propose a generative model of the features extracted by a classifier, and show using rigorous hypothesis testing that errors tend to occur when features are assigned low-probability by our model. From this observation, we develop a detection crit…
Prince of Songkla University（宋卡王子大学）；Khon Kaen University（孔敬大学）
In this paper ensemble learning based feature selection and classifier ensemble model is proposed to improve classification accuracy. The hypothesis is that good feature sets contain features that are highly correlated with the class from ensemble feature selection to SVM ensembles which can be achieved on the performance of classification accuracy. The proposed approach consists of two phases: (i) to select feature sets that are likely to be the support vectors by applying ensemble based feature selection methods; and (ii) to construct an SVM ensemble using the selected features. The proposed…
We compare and contrast two approaches to validating a trained classifier while using all in-sample data for training. One is simultaneous validation over an organized set of hypotheses (SVOOSH), the well-known method that began with VC theory. The other is withhold and gap (WAG). WAG withholds a validation set, trains a holdout classifier on the remaining data, uses the validation data to validate that classifier, then adds the rate of disagreement between the holdout classifier and one trained using all in-sample data, which is an upper bound on the difference in error rates. We show that co…
Current techniques in machine learning are so far are unable to learn classifiers that are robust to adversarial perturbations. However, they are able to learn non-robust classifiers with very high accuracy, even in the presence of random perturbations. Towards explaining this gap, we highlight the hypothesis that $\textit{robust classification may require more complex classifiers (i.e. more capacity) than standard classification.}$ In this note, we show that this hypothesis is indeed possible, by giving several theoretical examples of classification tasks and sets of "simple" classifiers for …
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
Hong Kong Baptist University（香港浸会大学）；The University of Melbourne（墨尔本大学）；RIKEN（理化学研究所）；Tianjin Artificial Intelligence Innovation Center（天津人工智能创新中心）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；The University of Sydney（悉尼大学）；The University of Tokyo（东京大学）
Institute of Information Transmission Problems（信息传输问题研究所）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）
We consider a problem of risk estimation for large-margin multi-class classifiers. We propose a novel risk bound for the multi-class classification problem. The bound involves the marginal distribution of the classifier and the Rademacher complexity of the hypothesis class. We prove that our bound is tight in the number of classes. Finally, we compare our bound with the related ones and provide a simplified version of the bound for the multi-class classification with kernel based hypotheses.
Statistical learning theory chiefly studies restricted hypothesis classes, particularly those with finite Vapnik-Chervonenkis (VC) dimension. The fundamental quantity of interest is the sample complexity: the number of samples required to learn to a specified level of accuracy. Here we consider learning over the set of all computable labeling functions. Since the VC-dimension is infinite and a priori (uniform) bounds on the number of samples are impossible, we let the learning algorithm decide when it has seen sufficient samples to have learned. We first show that learning in this setting is i…
We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show that in the initial epochs, almost all of the performance improvement of the classifier obtained by SGD can be explained by a linear classifier. More generally, we give evidence for the hypothesis that, as iterations progress, SGD learns functions of increasing complexity. This hypothesis can be helpful in explaining why SGD-learned classifiers tend to generalize well even in the over-parameterized regime. We also sh…
The manifold hypothesis (real world data concentrates near low-dimensional manifolds) is suggested as the principle behind the effectiveness of machine learning algorithms in very high dimensional problems that are common in domains such as vision and speech. Multiple methods have been proposed to explicitly incorporate the manifold hypothesis as a prior in modern Deep Neural Networks (DNNs), with varying success. In this paper, we propose a new method, Distance Learner, to incorporate this prior for DNN-based classifiers. Distance Learner is trained to predict the distance of a point from the…
Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we present a simple hypothesis about a feature compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations. Drawing on ideas from information and coding theory, we propose a general class of de…
Federal Technological University of Paraná (UTFPR)（巴拉那联邦理工大学（UTFPR））
In supervised learning, simple baseline classifiers can be constructed by only looking at the class, i.e., ignoring any other information from the dataset. The single-label learning community frequently uses as a reference the one which always predicts the majority class. Although a classifier might perform worse than this simple baseline classifier, this behaviour requires a special explanation. Aiming to motivate the community to compare experimental results with the ones provided by a multi-label baseline classifier, calling the attention about the need of special explanations related to cl…
Mila（米拉研究所）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；Facebook AI Research（脸书人工智能研究院）
The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development of safeguards against them. This includes attack methods in the challenging non-interactive blackbox setting, where adversarial attacks are generated without any access, including queries, to the target model. Prior attacks in this setting have relied mainly on algorithmic innovations derived from empirical observations (e.g., that momentum helps), lacking principled transferability guarantees. In this work, we provide a …
SZTAKI: Institute for Computer Science and Control（SZTAKI：计算机科学与控制研究所）；Eötvös Loránd Research Network（厄特沃什·罗兰研究网络）
In this paper we suggest two statistical hypothesis tests for the regression function of binary classification based on conditional kernel mean embeddings. The regression function is a fundamental object in classification as it determines both the Bayes optimal classifier and the misclassification probabilities. A resampling based framework is presented and combined with consistent point estimators of the conditional kernel mean map, in order to construct distribution-free hypothesis tests. These tests are introduced in a flexible manner allowing us to control the exact probability of type I e…
Algorithms are now routinely used to make consequential decisions that affect human lives. Examples include college admissions, medical interventions or law enforcement. While algorithms empower us to harness all information hidden in vast amounts of data, they may inadvertently amplify existing biases in the available datasets. This concern has sparked increasing interest in fair machine learning, which aims to quantify and mitigate algorithmic discrimination. Indeed, machine learning models should undergo intensive tests to detect algorithmic biases before being deployed at scale. In this pa…
Malware detection is a popular application of Machine Learning for Information Security (ML-Sec), in which an ML classifier is trained to predict whether a given file is malware or benignware. Parameters of this classifier are typically optimized such that outputs from the model over a set of input samples most closely match the samples' true malicious/benign (1/0) target labels. However, there are often a number of other sources of contextual metadata for each malware sample, beyond an aggregate malicious/benign label, including multiple labeling sources and malware type information (e.g., ra…
Fuzzy Cognitive Maps (FCMs) are considered a soft computing technique combining elements of fuzzy logic and recurrent neural networks. They found multiple application in such domains as modeling of system behavior, prediction of time series, decision making and process control. Less attention, however, has been turned towards using them in pattern classification. In this work we propose an FCM based classifier with a fully connected map structure. In contrast to methods that expect reaching a steady system state during reasoning, we chose to execute a few FCM iterations (steps) before collecti…
University of Ljubljana（卢布尔雅那大学）；Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)（达莱莫勒人工智能研究所（IDSIA））
The machine learning community adopted the use of null hypothesis significance testing (NHST) in order to ensure the statistical validity of results. Many scientific fields however realized the shortcomings of frequentist reasoning and in the most radical cases even banned its use in publications. We should do the same: just as we have embraced the Bayesian paradigm in the development of new machine learning methods, so we should also use it in the analysis of our own results. We argue for abandonment of NHST by exposing its fallacies and, more importantly, offer better - more sound and useful…
Motivated by the need of the linking records across various databases, we propose a novel graphical model based classifier that uses a mixture of Poisson distributions with latent variables. The idea is to derive insight into each pair of hypothesis records that match by inferring its underlying latent rate of error using Bayesian Modeling techniques. The novel approach of using gamma priors for learning the latent variables along with supervised labels is unique and allows for active learning. The naive assumption is made deliberately as to the independence of the fields to propose a generali…
Hertie Institute for Artificial Intelligence in Brain Health（赫蒂脑健康人工智能研究所）；Institute of Ophthalmic Research（眼科研究所）；Tübingen AI Center（图宾根人工智能中心）；University of Tübingen（图宾根大学）；Department of Pathology and Neuropathology（病理与神经病理科）；University Hospital Tübingen（图宾根大学医院）；Comprehensive Cancer Center Tübingen（图宾根综合癌症中心）；Cluster of Excellence Machine Learning: New Perspectives for Science（机器学习卓越集群：科学新视角）；Gatsby Computational Neuroscience Unit（盖茨比计算神经科学研究组）；University College London（伦敦大学学院）
Distribution shifts remain a fundamental problem for the safe application of machine learning systems. If undetected, they may impact the real-world performance of such systems or will at least render original performance claims invalid. In this paper, we focus on the detection of subgroup shifts, a type of distribution shift that can occur when subgroups have a different prevalence during validation compared to the deployment setting. For example, algorithms developed on data from various acquisition settings may be predominantly applied in hospitals with lower quality data acquisition, leadi…
Many researches have been devoted to learn a Mahalanobis distance metric, which can effectively improve the performance of kNN classification. Most approaches are iterative and computational expensive and linear rigidity still critically limits metric learning algorithm to perform better. We proposed a computational economical framework to learn multiple metrics in closed-form.
Center for Advanced Intelligence Project, RIKEN（理化学研究所先进智能项目中心）；Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院）；Department of Statistics, Seoul National University（首尔国立大学统计系）
We consider the problem of learning a binary classifier from only positive and unlabeled observations (called PU learning). Recent studies in PU learning have shown superior performance theoretically and empirically. However, most existing algorithms may not be suitable for large-scale datasets because they face repeated computations of a large Gram matrix or require massive hyperparameter optimization. In this paper, we propose a computationally efficient and theoretically grounded PU learning algorithm. The proposed PU learning algorithm produces a closed-form classifier when the hypothesis …
Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model, making them risky and inefficient for decentralized private data. This work tackles a practical setting where only a trained source model is available and investigates how we can effectively utilize such a model without source data to solve UDA problems. We propose a simple yet generic representation learning framework, named \emph{Source HypOthe…
A supervised learning algorithm has access to a distribution of labeled examples, and needs to return a function (hypothesis) that correctly labels the examples. The hypothesis of the learner is taken from some fixed class of functions (e.g., linear classifiers, neural networks etc.). A failure of the learning algorithm can occur due to two possible reasons: wrong choice of hypothesis class (hardness of approximation), or failure to find the best function within the hypothesis class (hardness of learning). Although both approximation and learnability are important for the success of the algori…
Basque Center for Applied Mathematics (BCAM)（巴斯克应用数学中心（BCAM））；IKERBASQUE-Basque Foundation for Science（IKERBASQUE-巴斯克科学基金会）；Federal University of Bahia（巴伊亚联邦大学）；National Research Institute for Mathematics and Computer Science (CWI)（国家数学与计算机科学研究院（CWI））
University of the West of England（西英格兰大学）；Northumbria University（诺森比亚大学）；Flanders Mechatronic Technology Centre（法兰德斯机电技术中心）；Katholieke Universiteit Leuven（鲁汶大学）
The accuracy of machine learning systems is a widely studied research topic. Established techniques such as cross-validation predict the accuracy on unseen data of the classifier produced by applying a given learning method to a given training data set. However, they do not predict whether incurring the cost of obtaining more data and undergoing further training will lead to higher accuracy. In this paper we investigate techniques for making such early predictions. We note that when a machine learning algorithm is presented with a training set the classifier produced, and hence its error, will…
University of California, Berkeley（加州大学伯克利分校）；The Simons Institute for the Theory of Computing at UC Berkeley（加州大学伯克利分校西蒙斯计算理论研究所）
We study several questions in the reliable agnostic learning framework of Kalai et al. (2009), which captures learning tasks in which one type of error is costlier than others. A positive reliable classifier is one that makes no false positive errors. The goal in the positive reliable agnostic framework is to output a hypothesis with the following properties: (i) its false positive error rate is at most $ε$, (ii) its false negative error rate is at most $ε$ more than that of the best positive reliable classifier from the class. A closely related notion is fully reliable agnostic learning, whic…
IBM Research（IBM研究院）；Carnegie Mellon University（卡内基梅隆大学）
A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease with increased fairness. Novel to this work, we examine fair classification through the lens of mismatched hypothesis testing: trying to find a classifier that distinguishes between two ideal distributions when given two mismatched distributions that are biased. Using Chernoff information, a tool in information theory, we theoretically demonstrate that, contrary to popular belief, there always exist ideal distr…
Automated feature selection is important for text categorization to reduce the feature size and to speed up the learning process of classifiers. In this paper, we present a novel and efficient feature selection framework based on the Information Theory, which aims to rank the features with their discriminative capacity for classification. We first revisit two information measures: Kullback-Leibler divergence and Jeffreys divergence for binary hypothesis testing, and analyze their asymptotic properties relating to type I and type II errors of a Bayesian classifier. We then introduce a new diver…
We consider the use of machine learning for hypothesis testing with an emphasis on target detection. Classical model-based solutions rely on comparing likelihoods. These are sensitive to imperfect models and are often computationally expensive. In contrast, data-driven machine learning is often more robust and yields classifiers with fixed computational complexity. Learned detectors usually provide high accuracy with low complexity but do not have a constant false alarm rate (CFAR) as required in many applications. To close this gap, we propose to add a term to the loss function that promotes …
We propose a novel class of deep stochastic predictors for classifying metric data on graphs within the PAC-Bayes risk certification paradigm. Classifiers are realized as linearly parametrized deep assignment flows with random initial conditions. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables (i) to use risk bounds as training objectives for learning posterior distributions on the hypothesis space and (ii) to compute tight out-of-sample risk certificates of randomized classifiers more efficiently than related work. Comparison with empirical test se…
Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness
School of Mathematical and Data Sciences（数学与数据科学学院）；West Virginia University（西弗吉尼亚大学）；Department of Industrial and Management Systems Engineering（工业与管理系统工程系）
Sichuan University（四川大学）；Rutgers University – New Brunswick（罗格斯大学新不伦瑞克分校）；Zhejiang University（浙江大学）；Tennessee State University（田纳西州立大学）
The dynamic ensemble selection of classifiers is an effective approach for processing label-imbalanced data classifications. However, such a technique is prone to overfitting, owing to the lack of regularization methods and the dependence of the aforementioned technique on local geometry. In this study, focusing on binary imbalanced data classification, a novel dynamic ensemble method, namely adaptive ensemble of classifiers with regularization (AER), is proposed, to overcome the stated limitations. The method solves the overfitting problem through implicit regularization. Specifically, it lev…
In previous work, a novel supervised framework implementing a binary classifier was presented that obtained excellent results for side effect discovery. Interestingly, unique side effects were identified when different binary classifiers were used within the framework, prompting the investigation of applying a multiple classifier system. In this paper we investigate tuning a side effect multiple classifying system using genetic algorithms. The results of this research show that the novel framework implementing a multiple classifying system trained using genetic algorithms can obtain a higher p…
In this paper, we deal with the task of building a dynamic ensemble of chain classifiers for multi-label classification. To do so, we proposed two concepts of classifier chains algorithms that are able to change label order of the chain without rebuilding the entire model. Such modes allows anticipating the instance-specific chain order without a significant increase in computational burden. The proposed chain models are built using the Naive Bayes classifier and nearest neighbour approach as a base single-label classifiers. To take the benefits of the proposed algorithms, we developed a simpl…
Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differential fairness. Multi-differential fairness is a guarantee that a black box classifier's outcomes do not leak information on the sensitive attributes of a small group of individuals. We reduce the problem of identifying worst-case violations to matching distributions and predicting …
Weizmann Institute of Science（魏茨曼科学研究所）；Yale University, School of Medicine（耶鲁大学医学院）；New York University, Langone Medical Center（纽约大学朗格尼医学中心）
In various situations one is given only the predictions of multiple classifiers over a large unlabeled test data. This scenario raises the following questions: Without any labeled data and without any a-priori knowledge about the reliability of these different classifiers, is it possible to consistently and computationally efficiently estimate their accuracies? Furthermore, also in a completely unsupervised manner, can one construct a more accurate unsupervised ensemble classifier? In this paper, focusing on the binary case, we present simple, computationally efficient algorithms to solve thes…
