A significant challenge for a supervised learning approach to inertial human activity recognition is the heterogeneity of data between individual users, resulting in very poor performance of impersonal algorithms for some subjects. We present an approach to personalized activity recognition based on deep embeddings derived from a fully convolutional neural network. We experiment with both categorical cross entropy loss and triplet loss for training the embedding, and describe a novel triplet loss function based on subject triplets. We evaluate these methods on three publicly available inertial human activity recognition data sets (MHEALTH, WISDM, and SPAR) comparing classification accuracy, out-of-distribution activity detection, and embedding generalization to new activities. The novel subject triplet loss provides the best performance overall, and all personalized deep embeddings out-perform our baseline personalized engineered feature embedding and an impersonal fully convolutional neural network classifier.

We study the problem of independence testing given independent and identically distributed pairs taking values in a $\sigma$-finite, separable measure space. Defining a natural measure of dependence $D(f)$ as the squared $L_2$-distance between a joint density $f$ and the product of its marginals, we first show that there is no valid test of independence that is uniformly consistent against alternatives of the form $\{f: D(f) \geq \rho^2 \}$. We therefore restrict attention to alternatives that impose additional Sobolev-type smoothness constraints, and define a permutation test based on a basis expansion and a $U$-statistic estimator of $D(f)$ that we prove is minimax optimal in terms of its separation rates in many instances. Finally, for the case of a Fourier basis on $[0,1]^2$, we provide an approximation to the power function that offers several additional insights.

We address the challenging open problem of learning an effective latent space for symbolic music data in generative music modeling. We focus on leveraging adversarial regularization as a flexible and natural mean to imbue variational autoencoders with context information concerning music genre and style. Through the paper, we show how Gaussian mixtures taking into account music metadata information can be used as an effective prior for the autoencoder latent space, introducing the first Music Adversarial Autoencoder (MusAE). The empirical analysis on a large scale benchmark shows that our model has a higher reconstruction accuracy than state-of-the-art models based on standard variational autoencoders. It is also able to create realistic interpolations between two musical sequences, smoothly changing the dynamics of the different tracks. Experiments show that the model can organise its latent space accordingly to low-level properties of the musical pieces, as well as to embed into the latent variables the high-level genre information injected from the prior distribution to increase its overall performance. This allows us to perform changes to the generated pieces in a principled way.

Feature selection places an important role in improving the performance of outlier detection, especially for noisy data. Existing methods usually perform feature selection and outlier scoring separately, which would select feature subsets that may not optimally serve for outlier detection, leading to unsatisfying performance. In this paper, we propose an outlier detection ensemble framework with embedded feature selection (ODEFS), to address this issue. Specifically, for each random sub-sampling based learning component, ODEFS unifies feature selection and outlier detection into a pairwise ranking formulation to learn feature subsets that are tailored for the outlier detection method. Moreover, we adopt the thresholded self-paced learning to simultaneously optimize feature selection and example selection, which is helpful to improve the reliability of the training set. After that, we design an alternate algorithm with proved convergence to solve the resultant optimization problem. In addition, we analyze the generalization error bound of the proposed framework, which provides theoretical guarantee on the method and insightful practical guidance. Comprehensive experimental results on 12 real-world datasets from diverse domains validate the superiority of the proposed ODEFS.

In high-energy physics (HEP) experiments, a thorough understanding of the properties of known physics forms the basis of any searches that look for new effects. This can only be achieved by an accurate simulation, which in many cases boils down to performing an integral and sampling from it. Often high-dimensional phase space integrals with nontrivial correlations between dimensions are required in important theory calculations. Monte-Carlo (MC) methods still remain as the most important techniques for solving high-dimensional problems across many fields, including for instance: biology [1, 2], chemistry [3], astronomy [4], medical physics [5], finance [6] and image rendering [7]. In high-energy physics, all analyses at the Large Hadron Collider (LHC) rely strongly on multipurpose Monte Carlo event generators [8, 9] for signal or background prediction.

The imperfectness of data acquisition processes, however, presents several common yet critical challenges: (1) random noise: which reflects the uncertainty of the environment and/or the measurement processes; (2) outliers: which represent a sort of corruption that exhibits abnormal behavior; and (3) incomplete data, namely, we might only get to observe a fraction of the matrix entries. Low-rank matrix estimation algorithms aimed at addressing these challenges have been extensively studied under the umbrella of robust principal component analysis (Robust PCA) [CSPW11, CLMW11], a terminology popularized by the seminal work [CLMW11]. To formulate the above-mentioned problem in a more precise manner, imagine that we seek to estimate an unknown low-rank matrix L null R n n . 1 What we can obtain is a collection of partially observed and corrupted entries as follows M ij L null ij S null ij E ij, (i,j) Ω obs, (1.1) where S null [ S null ij] 1 i,j n is a matrix consisting of outliers, E [ E ij] 1 i,j n represents the random noise, and we only observe entries over an index subset Ω obs [n ] [n ] with [n ]: {1, 2, ···,n }. The current paper assumes that S null is a relatively sparse matrix whose nonzero entries might have arbitrary magnitudes. This assumption has been commonly adopted in prior work to model gross outliers, while enabling reliable disentanglement of the outlier component and the low-rank component [CSPW11,CLMW11,CJSC13,Li13]. In addition, we suppose that the entries {E ij} are independent zero-mean sub-Gaussian random variables, as commonly assumed in the statistics literature to model a large family of random noise. The aim is to reliably estimate L null given the grossly corrupted and possibly incomplete data (1.1). Ideally, this task should be accomplished without knowing the locations and magnitudes of the outliers S null . 1 To avoid cluttered notation, this paper works with square matrices of size n by n. Our results and analysis can be extended to accommodate rectangular matrices.

Quantum effects are known to provide an advantage in particle transfer across networks. In order to achieve this advantage, requirements on both a graph type and a quantum system coherence must be found. Here we show that the process of finding these requirements can be automated by learning from simulated examples. The automation is done by using a convolutional neural network of a particular type that learns to understand with which network and under which coherence requirements quantum advantage is possible. Our machine learning approach is applied to study noisy quantum walks on cycle graphs of different sizes. We found that it is possible to predict the existence of quantum advantage for the entire decoherence parameter range, even for graphs outside of the training set. Our results are of importance for demonstration of advantage in quantum experiments and pave the way towards automating scientific research and discoveries.

We consider a decentralized multi-agent Multi Armed Bandit (MAB) setup consisting of $N$ agents, solving the same MAB instance to minimize individual cumulative regret. In our model, agents collaborate by exchanging messages through pairwise gossip style communications. We develop two novel algorithms, where each agent only plays from a subset of all the arms. Agents use the communication medium to recommend only arm-IDs (not samples), and thus update the set of arms from which they play. We establish that, if agents communicate $\Omega(\log(T))$ times through any connected pairwise gossip mechanism, then every agent's regret is a factor of order $N$ smaller compared to the case of no collaborations. Furthermore, we show that the communication constraints only have a second order effect on the regret of our algorithm. We then analyze this second order term of the regret to derive bounds on the regret-communication tradeoffs. Finally, we empirically evaluate our algorithm and conclude that the insights are fundamental and not artifacts of our bounds. We also show a lower bound which gives that the regret scaling obtained by our algorithm cannot be improved even in the absence of any communication constraints. Our results demonstrate that even a minimal level of collaboration among agents greatly reduces regret for all agents.

Intelligent Object manipulation for grasping is a challenging problem for robots. Unlike robots, humans almost immediately know how to manipulate objects for grasping due to learning over the years. A grown woman can grasp objects more skilfully than a child because of learning skills developed over years, the absence of which in the present day robotic grasping compels it to perform well below the human object grasping benchmarks. In this paper we have taken up the challenge of developing learning based pose estimation by decomposing the problem into both position and orientation learning. More specifically, for grasp position estimation, we explore three different methods - a Genetic Algorithm (GA) based optimization method to minimize error between calculated image points and predicted end-effector (EE) position, a regression based method (RM) where collected data points of robot EE and image points have been regressed with a linear model, a PseudoInverse (PI) model which has been formulated in the form of a mapping matrix with robot EE position and image points for several observations. Further for grasp orientation learning, we develop a deep reinforcement learning (DRL) model which we name as Grasp Deep Q-Network (GDQN) and benchmarked our results with Modified VGG16 (MVGG16). Rigorous experimentations show that due to inherent capability of producing very high-quality solutions for optimization problems and search problems, GA based predictor performs much better than the other two models for position estimation. For orientation learning results indicate that off policy learning through GDQN outperforms MVGG16, since GDQN architecture is specially made suitable for the reinforcement learning. Based on our proposed architectures and algorithms, the robot is capable of grasping all rigid body objects having regular shapes.

We investigate the use of physics-informed neural networks-based solution of the PDE satisfied by the probability density function (pdf) of the state of a dynamical system subject to random forcing. Two alternatives for the PDE are considered: the Fokker-Planck equation and a PDE for the characteristic function (chf) of the state, both of which provide the same probabilistic information. Solving these PDEs using the finite element method is unfeasible when the dimension of the state is larger than 3. We examine analytically and numerically the advantages and disadvantages of solving the corresponding PDE of one over the other. It is also demonstrated how prior information of the dynamical system can be exploited to design and simplify the neural network architecture. Numerical examples show that: 1) the neural network solution can approximate the target solution even for partial integro-differential equations and system of PDEs, 2) solving either PDE using neural networks yields similar pdfs of the state, and 3) the solution to the PDE can be used to study the behavior of the state for different types of random forcings.