Neural network based data-driven market simulation unveils a new and flexible way of modelling financial time series, without imposing assumptions on the underlying stochastic dynamics. Though in this sense generative market simulation is model-free, the concrete modelling choices are nevertheless decisive for the features of the simulated paths. We give a brief overview of currently used generative modelling approaches and performance evaluation metrics for financial time series, and address some of the challenges to achieve good results in the latter. We also contrast some classical approaches of market simulation with simulation based on generative modelling and highlight some advantages and pitfalls of the new approach. While most generative models tend to rely on large amounts of training data, we present here a generative model that works reliably even in environments where the amount of available training data is notoriously small. Furthermore, we show how a rough paths perspective combined with a parsimonious Variational Autoencoder framework provides a powerful way for encoding and evaluating financial time series in such environments where available training data is scarce. Finally, we also propose a suitable performance evaluation metric for financial time series and discuss some connections of our Market Generator to deep hedging.

Federated learning (FL) is a highly pursued machine learning technique that can train a model centrally while keeping data distributed. Distributed computation makes FL attractive for bandwidth limited applications especially in wireless communications. There can be a large number of distributed edge devices connected to a central parameter server (PS) and iteratively download/upload data from/to the PS. Due to the limited bandwidth, only a subset of connected devices can be scheduled in each round. There are usually millions of parameters in the state-of-art machine learning models such as deep learning, resulting in a high computation complexity as well as a high communication burden on collecting/distributing data for training. To improve communication efficiency and make the training model converge faster, we propose a new scheduling policy and power allocation scheme using non-orthogonal multiple access (NOMA) settings to maximize the weighted sum data rate under practical constraints during the entire learning process. NOMA allows multiple users to transmit on the same channel simultaneously. The user scheduling problem is transformed into a maximum-weight independent set problem that can be solved using graph theory. Simulation results show that the proposed scheduling and power allocation scheme can help achieve a higher FL testing accuracy in NOMA based wireless networks than other existing schemes.

Huge amount of applications in various fields, such as gene expression analysis or computer vision, undergo data sets with high-dimensional low-sample-size (HDLSS), which has putted forward great challenges for standard statistical and modern machine learning methods. In this paper, we propose a novel classification criterion on HDLSS, tolerance similarity, which emphasizes the maximization of within-class variance on the premise of class separability. According to this criterion, a novel linear binary classifier is designed, denoted by No-separated Data Maximum Dispersion classifier (NPDMD). The objective of NPDMD is to find a projecting direction w in which all of training samples scatter in as large an interval as possible. NPDMD has several characteristics compared to the state-of-the-art classification methods. First, it works well on HDLSS. Second, it combines the sample statistical information and local structural information (supporting vectors) into the objective function to find the solution of projecting direction in the whole feature spaces. Third, it solves the inverse of high dimensional matrix in low dimensional space. Fourth, it is relatively simple to be implemented based on Quadratic Programming. Fifth, it is robust to the model specification for various real applications. The theoretical properties of NPDMD are deduced. We conduct a series of evaluations on one simulated and six real-world benchmark data sets, including face classification and mRNA classification. NPDMD outperforms those widely used approaches in most cases, or at least obtains comparable results.

In order to prevent leaking input information from intermediate-layer features, this paper proposes a method to revise the traditional neural network into the rotation-equivariant neural network (RENN). Compared to the traditional neural network, the RENN uses d-ary vectors/tensors as features, in which each element is a d-ary number. These d-ary features can be rotated (analogous to the rotation of a d-dimensional vector) with a random angle as the encryption process. Input information is hidden in this target phase of d-ary features for attribute obfuscation. Even if attackers have obtained network parameters and intermediate-layer features, they cannot extract input information without knowing the target phase. Hence, the input privacy can be effectively protected by the RENN. Besides, the output accuracy of RENNs only degrades mildly compared to traditional neural networks, and the computational cost is significantly less than the homomorphic encryption.

In many product development problems, the performance of the product is governed by two types of parameters called design parameter and environmental parameter. While the former is fully controllable, the latter varies depending on the environment in which the product is used. The challenge of such a problem is to find the design parameter that maximizes the probability that the performance of the product will meet the desired requisite level given the variation of the environmental parameter. In this paper, we formulate this practical problem as active learning (AL) problems and propose efficient algorithms with theoretically guaranteed performance. Our basic idea is to use Gaussian Process (GP) model as the surrogate model of the product development process, and then to formulate our AL problems as Bayesian Quadrature Optimization problems for probabilistic threshold robustness (PTR) measure. We derive credible intervals for the PTR measure and propose AL algorithms for the optimization and level set estimation of the PTR measure. We clarify the theoretical properties of the proposed algorithms and demonstrate their efficiency in both synthetic and real-world product development problems.

This paper presents a framework to tackle constrained combinatorial optimization problems using deep Reinforcement Learning (RL). To this end, we extend the Neural Combinatorial Optimization (NCO) theory in order to deal with constraints in its formulation. Notably, we propose defining constrained combinatorial problems as fully observable Constrained Markov Decision Processes (CMDP). In that context, the solution is iteratively constructed based on interactions with the environment. The model, in addition to the reward signal, relies on penalty signals generated from constraint dissatisfaction to infer a policy that acts as a heuristic algorithm. Moreover, having access to the complete state representation during the optimization process allows us to rely on memory-less architectures, enhancing the results obtained in previous sequence-to-sequence approaches. Conducted experiments on the constrained Job Shop and Resource Allocation problems prove the superiority of the proposal for computing rapid solutions when compared to classical heuristic, metaheuristic, and Constraint Programming (CP) solvers.

Hyper-parameter optimization is crucial for pushing the accuracy of a deep learning model to its limits. A hyper-parameter optimization job, referred to as a study, involves numerous trials of training a model using different training knobs, and therefore is very computation-heavy, typically taking hours and days to finish. We observe that trials issued from hyper-parameter optimization algorithms often share common hyper-parameter sequence prefixes. Based on this observation, we propose Hippo, a hyper-parameter optimization system that removes redundancy in the training process to reduce the overall amount of computation significantly. Instead of executing each trial independently as in existing hyper-parameter optimization systems, Hippo breaks down the hyper-parameter sequences into stages and merges common stages to form a tree of stages (called a stage-tree), then executes a stage once per tree on a distributed GPU server environment. Hippo is applicable to not only single studies, but multi-study scenarios as well, where multiple studies of the same model and search space can be formulated as trees of stages. Evaluations show that Hippo's stage-based execution strategy outperforms trial-based methods such as Ray Tune for several models and hyper-parameter optimization algorithms, reducing GPU-hours and end-to-end training time significantly.

Pruning and quantization are proven methods for improving the performance and storage efficiency of convolutional neural networks (CNNs). Pruning removes near-zero weights in tensors and masks weak connections between neurons in neighbouring layers. Quantization reduces the precision of weights by replacing them with numerically similar values that require less storage. In this paper, we identify another form of redundancy in CNN weight tensors, in the form of repeated patterns of similar values. We observe that pruning and quantization both tend to drastically increase the number of repeated patterns in the weight tensors. We investigate several compression schemes to take advantage of this structure in CNN weight data, including multiple forms of Huffman coding, and other approaches inspired by block sparse matrix formats. We evaluate our approach on several well-known CNNs and find that we can achieve compaction ratios of 1.4x to 3.1x in addition to the saving from pruning and quantization.

Mining massive spatio-temporal data can help a variety of real-world applications such as city capacity planning, event management, and social network analysis. The tensor representation can be used to capture the correlation between space and time and simultaneously exploit the latent structure of the spatial and temporal patterns in an unsupervised fashion. However, the increasing volume of spatio-temporal data has made it prohibitively expensive to store and analyze using tensor factorization. In this paper, we propose SkeTenSmooth, a novel tensor factorization framework that uses adaptive sampling to compress the tensor in a temporally streaming fashion and preserves the underlying global structure. SkeTenSmooth adaptively samples incoming tensor slices according to the detected data dynamics. Thus, the sketches are more representative and informative of the tensor dynamic patterns. In addition, we propose a robust tensor factorization method that can deal with the sketched tensor and recover the original patterns. Experiments on the New York City Yellow Taxi data show that SkeTenSmooth greatly reduces the memory cost and outperforms random sampling and fixed rate sampling method in terms of retaining the underlying patterns.

Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets. Heterogeneity arises from data containing different types of features (categorical, ordinal, continuous, etc.) and features of the same type having different marginal distributions. We propose an extension of variational autoencoders (VAEs) called VAEM to handle such heterogeneous data. VAEM is a deep generative model that is trained in a two stage manner such that the first stage provides a more uniform representation of the data to the second stage, thereby sidestepping the problems caused by heterogeneous data. We provide extensions of VAEM to handle partially observed data, and demonstrate its performance in data generation, missing data prediction and sequential feature selection tasks. Our results show that VAEM broadens the range of real-world applications where deep generative models can be successfully deployed.