Modern reinforcement learning (RL) often faces an enormous state-action space. Existing analytical results are typically for settings with a small number of state-actions, or simple models such as linearly modeled Q functions. To derive statistically efficient RL policies handling large state-action spaces, with more general Q functions, some recent works have considered nonlinear function approximation using kernel ridge regression. In this work, we derive sample complexities for kernel based Q-learning when a generative model exists. We propose a non-parametric Q-learning algorithm which finds an $\varepsilon$-optimal policy in an arbitrarily large scale discounted MDP. The sample complexity of the proposed algorithm is order optimal with respect to $\varepsilon$ and the complexity of the kernel (in terms of its information gain). To the best of our knowledge, this is the first result showing a finite sample complexity under such a general model.

In recent years, machine learning as a service (MLaaS) has brought considerable convenience to our daily lives. However, these services raise the issue of leaking users’ sensitive attributes, such as race, when provided through the cloud. The present work overcomes this issue by proposing an innovative privacy-preserving approach called privacy-preserving class overlap (PPCO), which incorporates both a Wasserstein generative adversarial network and the idea of class overlapping to obfuscate data for better resilience against the leakage of attribute-inference attacks(i.e., malicious inference on users’ sensitive attributes). Experiments show that the proposed method can be employed to enhance current state-of-the-art works and achieve superior privacy–utility trade-off. Furthermore, the proposed method is shown to be less susceptible to the influence of imbalanced classes in training data. Finally, we provide a theoretical analysis of the performance of our proposed method to give a flavour of the gap between theoretical and empirical performances.

Privacy-preserving neural inference helps protect both the user input data and the model weights from being leaked to others during the inference of a deep learning model. To achieve data protection, the inference is often performed within a secure domain, and the final result is revealed in plaintext. Nevertheless, performing the computations in the secure domain incurs about a thousandfold overhead compared with the insecure version, especially when the involved operations of the entire model are mapped to the secure domain, which is the computation scheme adopted by the existing works. This work is inspired by the transfer learning technique, where the weights of some parts of the model layers are transferred from a publicly available, pre-built deep learning model, and it opens a door to further boost the execution efficiency by allowing us to do the secure computations selectively on parts of the transferred model. We have built a compiler framework, SecureTVM, to automatically translate a trained model into the secure version, where the model layers to be protected can be selectively configured by its model provider. As a result, SecureTVM outperforms the state of the art, CrypTFlow2, by a factor of 55 for the transfer learning model. We believe that this work takes a step forward toward the practical uses of privacy-preserving neural inference for real-world applications.

Cloud occlusions obstruct some applications of remote sensing imagery, such as environment monitoring, land cover classification, and poverty prediction. In this paper, we propose the Cloud Transformer Generative Adversarial Network (CTGAN), taking three temporal cloudy images as input and generating a corresponding cloud-free image. Unlike previous work using generative networks, we design the feature extractor to maintain the weight of the cloudless region while reducing the weight of the cloudy region, and we pass the extracted features to a conformer module to find the most critical representations. Mean-while, to address the lack of datasets, we collected a new dataset named Sen2_MTC from the Sentinel-2 satellite and manually labeled each cloudy and cloud-free image. Finally, we conducted extensive experiments on FS-2, the STGAN dataset, and Sen2_MTC. Our proposed CTGAN demonstrates higher qualitative and quantitative performance than the previous work and achieves state-of-the-art performance on these three datasets. The code is available at https://github.com/come880412/CTGAN

To fulfill the need for high-accuracy indoor positioning in many location-based services (LBSs) and the emerging Internet of Things (IoT) applications, in this article, we propose a novel scene-analysis positioning solution of the multidetector deep neural network (DNN) architecture, with preprocessing steps, model optimization techniques, and variance estimation methods. During the offline site-surveying phase in our approach, fingerprint databases are created by purposely built robotic surveying devices traversing the target site to gather perceivable Wi-Fi and other signals including to create spatial positioning models for further use in the online positioning phase. The intricate nonlinear relationship between fingerprints and spatial positions are thus resolved by the multidetector DNN in our approach. Hyperparameter analyses were conducted to further optimize our proposed multidetector model in terms of complexity, achieving at least 6.7 times of parameter complexity reduction while retaining < 1% degradation of 0.9-m (3 ft) positioning accuracy level.

Machine learning as a service (MLaaS) has brought much convenience to our daily lives recently. However, the fact that the service is provided through cloud raises privacy leakage issues. In this work we propose the compressive privacy generative adversarial network (CPGAN), a data-driven adversarial learning framework for generating compressing representations that retain utility comparable to state-of-the-art, with the additional feature of defending against reconstruction attack. This is achieved by applying adversarial learning scheme to the design of compression network (privatizer), whose utility/privacy performances are evaluated by the utility classifier and the adversary reconstructor, respectively. Experimental results demonstrate that CPGAN achieves better utility/privacy trade-off in comparison with the previous work, and is applicable to real-world large datasets.

In this paper, a fast kernel ridge regression (KRR) learning algorithm is adopted with ( ) training cost for large-scale active authentication system. A truncated Gaussian radial basis function (TRBF) kernel is also implemented to provide better cost-performance tradeoff. The fast-KRR algorithm along with the TRBF kernel offers computational advantages over the traditional support vector machine (SVM) with Gaussian-RBF kernel while preserving the error rate performance. Experimental results validate the cost-effectiveness of the developed authentication system. In numbers, the fast-KRR learning model achieves an equal error rate (EER) of 1.39% with ( ) training time, while SVM with the RBF kernel shows an EER of 1.41% with ( ) training time.

In the Internet era, the data being collected on consumers like us are growing exponentially, and attacks on our privacy are becoming a real threat. To better ensure our privacy, it is safer to let the data owner control the data to be uploaded to the network as opposed to taking chance with data servers or third parties. To this end, we propose compressive privacy , a privacy-preserving technique to enable the data creator to compress data via collaborative learning so that the compressed data uploaded onto the Internet will be useful only for the intended utility and not be easily diverted to malicious applications. For data in a high-dimensional feature vector space, a common approach to data compression is dimension reduction or, equivalently, subspace projection. The most prominent tool is principal component analysis (PCA). For unsupervised learning, PCA can best recover the original data given a specific reduced dimensionality. However, for the supervised learning environment, it is more effective to adopt a supervised PCA, known as discriminant component analysis (DCA), to maximize the discriminant capability. The DCA subspace analysis embraces two different subspaces. The signal-subspace components of DCA are associated with the discriminant distance/power (related to the classification effectiveness), whereas the noise subspace components of DCA are tightly coupled with recoverability and/or privacy protection. This article presents three DCA-related data compression methods useful for privacy-preserving applications: — Utility-driven DCA : Because the rank of the signal subspace is limited by the number of classes, DCA can effectively support classification using a relatively small dimensionality (i.e., high compression). — Desensitized PCA : By incorporating a signal-subspace ridge into DCA, it leads to a variant especially effective for extracting privacy-preserving components. In this case, the eigenvalues of the noise-space are made to become insensitive to the privacy labels and are ordered according to their corresponding component powers. — Desensitized K-means/SOM : Since the revelation of the K-means or SOM cluster structure could leak sensitive information, it is safer to perform K-means or SOM clustering on a desensitized PCA subspace.

We explore the graph Laplacian eigenmap for the application of three-dimensional (3D) optical bioimaging. By using the density invariant graph Laplacian, each high-dimensional sampling (e.g. an image) could be represented by a low-dimensional description. These descriptions not only preserve key features of raw images but also estimate unobservable parameters for 3D imaging. In this paper, we apply this method for two 3D optical microscopies under following scenarios: (i) 3D optical tomography with projections of unknown orientation. (ii) 3D deconvolution microscopy with a disordered focal stack. To prove the robustness of the method, we use images from real biological systems and experimental measurements. In both cases, our results show that the density invariant graph Laplacian is able to overcome practical issues such as limited number of measurement, unstable environment, misalignment and experimental noise.

In this study a keystroke-based authentication system is implemented on a large-scale free-text keystroke data set, where cost effective kernel-based learning algorithms are designed to enable trade-off between computational cost and accuracy performance. The authentication process evaluates the user's typing behavior on a vocabulary of words, where the judgments based on each word are concatenated by weighted votes, whose weights are also trained to provide optimal fusion of independent judgments. A novel truncated-RBF kernel is also implemented to provide better cost-performance trade-off. Experimental results validate the cost-effectiveness of the developed authentication system.

Improving learning and classification efficiency has become increasingly important for machine learning. If the traditional RBF kernel is adopted, the learned kernel-based classifier usually delivers better performance by engaging a large training dataset. However, such a high performance comes at the expense of costly learning and classification complexities, which grow drastically with the training size N. To overcome this curse of dimensionality, we propose a so-called TRBF kernel(with finite intrinsic degree J) which approximates the RBF kernel. The contributions of this paper are as follows. First, the optimal classification efficiency attainable is shown to be J' ≈ J. To improve learning efficiency, we propose a fast PDA algorithm with learning complexity linearly growing with N. We adopt pruned-PDA (PPDA) to improve the accuracy by removing harmful “anti-support” vectors from the training set. Experiments on ECG dataset showed that TRBF-PPDA delivers nearly optimal performance with very low power.