In this paper, we propose a concept learning architecture that enables a robot to build symbols through self-exploration by interacting with a varying number of objects. Our aim is to allow a robot to learn concepts without constraints, such as a fixed number of interacted objects or pre-defined symbolic structures. As such, the sought architecture should be able to build symbols for objects such as single objects that can be grasped, object stacks that cannot be grasped together, or other composite dynamic structures. Towards this end, we propose a novel architecture, a self-attentive predictive encoder-decoder network with binary activation layers. We show the validity of the proposed network through a robotic manipulation setup involving a varying number of rigid objects. The continuous sensorimotor experience of the robot is used by the proposed network to form effect predictors and symbolic structures that describe the interaction of the robot in a discrete way. We showed that the robot acquired reasoning capabilities to encode interaction dynamics of a varying number of objects in different configurations using the discovered symbols. For example, the robot could reason that (possible multiple numbers of) objects on top of another object would move together if the object below is moved by the robot. We also showed that the discovered symbols can be used for planning to reach goals by training a higher-level neural network that makes pure symbolic reasoning.

We perform quantum process tomography (QPT) for both discrete- and continuous-variable quantum systems by learning a process representation using Kraus operators. The Kraus form ensures that the reconstructed process is completely positive. To make the process trace-preserving, we use a constrained gradient-descent (GD) approach on the so-called Stiefel manifold during optimization to obtain the Kraus operators. Our ansatz uses a few Kraus operators to avoid direct estimation of large process matrices, e.g., the Choi matrix, for low-rank quantum processes. The GD-QPT matches the performance of both compressed-sensing (CS) and projected least-squares (PLS) QPT in benchmarks with two-qubit random processes, but shines by combining the best features of these two methods. Similar to CS (but unlike PLS), GD-QPT can reconstruct a process from just a small number of random measurements, and similar to PLS (but unlike CS) it also works for larger system sizes, up to at least five qubits. We envisage that the data-driven approach of GD-QPT can become a practical tool that greatly reduces the cost and computational effort for QPT in intermediate-scale quantum systems.

The oblique random survival forest (RSF) is an ensemble supervised learning method for right-censored outcomes. Trees in the oblique RSF are grown using linear combinations of predictors to create branches, whereas in the standard RSF, a single predictor is used. Oblique RSF ensembles often have higher prediction accuracy than standard RSF ensembles. However, assessing all possible linear combinations of predictors induces significant computational overhead that limits applications to large-scale data sets. In addition, few methods have been developed for interpretation of oblique RSF ensembles, and they remain more difficult to interpret compared to their axis-based counterparts. We introduce a method to increase computational efficiency of the oblique RSF and a method to estimate importance of individual predictor variables with the oblique RSF. Our strategy to reduce computational overhead makes use of Newton-Raphson scoring, a classical optimization technique that we apply to the Cox partial likelihood function within each non-leaf node of decision trees. We estimate the importance of individual predictors for the oblique RSF by negating each coefficient used for the given predictor in linear combinations, and then computing the reduction in out-of-bag accuracy. In general benchmarking experiments, we find that our implementation of the oblique RSF is approximately 450 times faster with equivalent discrimination and superior Brier score compared to existing software for oblique RSFs. We find in simulation studies that 'negation importance' discriminates between relevant and irrelevant predictors more reliably than permutation importance, Shapley additive explanations, and a previously introduced technique to measure variable importance with oblique RSFs based on analysis of variance. Methods introduced in the current study are available in the aorsf R package.

Under the arbitrage pricing theory (Ross, 1976; Chamberlain and Rothschild, 1983), we know that risk premia are drivers of expected excess returns. Hence, estimating them should be useful for prediction of future equity excess returns. The workhorse to estimate equity risk premia in a linear multi-factor setting is the two-pass crosssectional regression method developed by Black et al. (1972) and Fama and MacBeth (1973). A series of papers address its large and finite sample properties for linear factor models with time-invariant coefficients; see, for example, Shanken (1985, 1992), Jagannathan and Wang (1998), Shanken and Zhou (2007), Kan et al. (2013), and the review paper of Jagannathan et al. (2010) (see Bryzgalova et al. (2019) for a recent Bayesian approach). In a time-varying setting, Gagliardini et al. (2016) (henceforth referred as GOS) study how we can infer the dynamics of equity risk premia from large stock return data sets under conditional linear factor models (see also Gagliardini

Synthetic health data have the potential to mitigate privacy concerns when sharing data to support biomedical research and the development of innovative healthcare applications. Modern approaches for data generation based on machine learning, generative adversarial networks (GAN) methods in particular, continue to evolve and demonstrate remarkable potential. Yet there is a lack of a systematic assessment framework to benchmark methods as they emerge and determine which methods are most appropriate for which use cases. In this work, we introduce a generalizable benchmarking framework to appraise key characteristics of synthetic health data with respect to utility and privacy metrics. We apply the framework to evaluate synthetic data generation methods for electronic health records (EHRs) data from two large academic medical centers with respect to several use cases. The results illustrate that there is a utility-privacy tradeoff for sharing synthetic EHR data. The results further indicate that no method is unequivocally the best on all criteria in each use case, which makes it evident why synthetic data generation methods need to be assessed in context.

We introduce a distance-based neural network model for regression, in which prediction uncertainty is quantified by a belief function on the real line. The model interprets the distances of the input vector to prototypes as pieces of evidence represented by Gaussian random fuzzy numbers (GRFN's) and combined by the generalized product intersection rule, an operator that extends Dempster's rule to random fuzzy sets. The network output is a GRFN that can be summarized by three numbers characterizing the most plausible predicted value, variability around this value, and epistemic uncertainty. Experiments with real datasets demonstrate the very good performance of the method as compared to state-of-the-art evidential and statistical learning algorithms.

Federated learning (FL) is an emerging promising paradigm of privacy-preserving machine learning (ML). An important type of FL is cross-silo FL, which enables a small scale of organizations to cooperatively train a shared model by keeping confidential data locally and aggregating weights on a central parameter server. However, the central server may be vulnerable to malicious attacks or software failures in practice. To address this issue, in this paper, we propose DeFL, a novel decentralized weight aggregation framework for cross-silo FL. DeFL eliminates the central server by aggregating weights on each participating node and weights of only the current training round are maintained and synchronized among all nodes. We use Multi-Krum to enable aggregating correct weights from honest nodes and use HotStuff to ensure the consistency of the training round number and weights among all nodes. Besides, we theoretically analyze the Byzantine fault tolerance, convergence, and complexity of DeFL. We conduct extensive experiments over two widely-adopted public datasets, i.e. CIFAR-10 and Sentiment140, to evaluate the performance of DeFL. Results show that DeFL defends against common threat models with minimal accuracy loss, and achieves up to 100x reduction in storage overhead and up to 12x reduction in network overhead, compared to state-of-the-art decentralized FL approaches.

Domain generalization (DG) has been studied extensively over the past decade as an important practical problem arising in a number of areas such as computer vision, signal processing, and medical imaging [1] [2]. Like standard learning settings, DG aims to learn a model from several seen domains (training data) that can generalize well on an unseen domain (test data). However, in contrast to the standard setting where the test data is assumed to come from the same distribution as training data, in DG, the distribution of the test data is different, i.e., there is a presence of what is referred to as a distribution shift. This phenomena can be observed in many practical settings [3]. A number of approaches for DG are based on the assumption that there exist domain-invariant features that are transferable and unchanged from domain to domain. Thus, a classifier designed on top of these features will likely generalize well to the unseen domain.

We present a locally optimal tracking controller for Cable Driven Parallel Robot (CDPR) control based on a time-varying Linear Quadratic Gaussian (TV-LQG) controller. In contrast to many methods which use fixed feedback gains, our time-varying controller computes the optimal gains depending on the location in the workspace and the future trajectory. Meanwhile, we rely heavily on offline computation to reduce the burden of online implementation and feasibility checking. Following the growing popularity of probabilistic graphical models for optimal control, we use factor graphs as a tool to formulate our controller for their efficiency, intuitiveness, and modularity. The topology of a factor graph encodes the relevant structural properties of equations in a way that facilitates insight and efficient computation using sparse linear algebra solvers. We first use factor graph optimization to compute a nominal trajectory, then linearize the graph and apply variable elimination to compute the locally optimal, time varying linear feedback gains. Next, we leverage the factor graph formulation to compute the locally optimal, time-varying Kalman Filter gains, and finally combine the locally optimal linear control and estimation laws to form a TV-LQG controller. We compare the tracking accuracy of our TV-LQG controller to a state-of-the-art dual-space feed-forward controller on a 2.9m x 2.3m, 4-cable planar robot and demonstrate improved tracking accuracies of 0.8{\deg} and 11.6mm root mean square error in rotation and translation respectively.

Industrial robots play a vital role in automatic production, which have been widely utilized in industrial production activities, like handling and welding. However, due to an uncalibrated robot with machining tolerance and assembly tolerance, it suffers from low absolute positioning accuracy, which cannot satisfy the requirements of high-precision manufacture. To address this hot issue, we propose a novel calibration method based on an unscented Kalman filter and variable step-size Levenberg-Marquardt algorithm. This work has three ideas: a) proposing a novel variable step-size Levenberg-Marquardt algorithm to addresses the issue of local optimum in a Levenberg-Marquardt algorithm; b) employing an unscented Kalman filter to reduce the influence of the measurement noises; and c) developing a novel calibration method incorporating an unscented Kalman filter with a variable step-size Levenberg-Marquardt algorithm. Furthermore, we conduct enough experiments on an ABB IRB 120 industrial robot. From the experimental results, the proposed method achieves much higher calibration accuracy than some state-of-the-art calibration methods. Hence, this work is an important milestone in the field of robot calibration.