Sequential pulling policies to flatten and smooth fabrics have applications from surgery to manufacturing to home tasks such as bed making and folding clothes. Due to the complexity of fabric states and dynamics, we apply deep imitation learning to learn policies that, given color or depth images of a rectangular fabric sample, estimate pick points and pull vectors to spread the fabric to maximize coverage. To generate data, we develop a fabric simulator and an algorithmic demonstrator that has access to complete state information. We train policies in simulation using domain randomization and dataset aggregation (DAgger) on three tiers of difficulty in the initial randomized configuration. We present results comparing five baseline policies to learned policies and report systematic comparisons of color vs. depth images as inputs. In simulation, learned policies achieve comparable or superior performance to analytic baselines. In 120 physical experiments with the da Vinci Research Kit (dVRK) surgical robot, policies trained in simulation attain 86% and 69% final coverage for color and depth inputs, respectively, suggesting the feasibility of learning fabric smoothing policies from simulation. Supplementary material is available at https://sites.google.com/view/ fabric-smoothing.

Mixed effects (ME) models inform a vast array of problems in the physical and social sciences, and are pervasive in meta-analysis. We consider ME models where the random effects component is linear. We then develop an efficient approach for a broad problem class that allows nonlinear measurements, priors, and constraints, and finds robust estimates in all of these cases using trimming in the associated marginal likelihood. We illustrate the efficacy of the approach on a range of applications for meta-analysis of global health data. Constraints and priors are used to impose monotonicity, convexity and other characteristics on dose-response relationships, while nonlinear observations enable new epidemiological analyses in place of approximations. Robust extensions ensure that spurious studies do not drive our understanding of between-study heterogeneity. The software accompanying this paper is disseminated as an open-source Python package called limeTR.

Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbitrary advantage estimators, which allows the control of the bias and variance of any-order derivatives when using function approximation. Furthermore, we propose a method to trade off bias and variance of higher order derivatives by discounting the impact of more distant causal dependencies. We demonstrate the correctness and utility of our objective in analytically tractable MDPs and in meta-reinforcement-learning for continuous control.

We study the impact of the constraint set and gradient geometry on the convergence of online and stochastic methods for convex optimization, providing a characterization of the geometries for which stochastic gradient and adaptive gradient methods are (minimax) optimal. In particular, we show that when the constraint set is quadratically convex, diagonally pre-conditioned stochastic gradient methods are minimax optimal. We further provide a converse that shows that when the constraints are not quadratically convex---for example, any $\ell_p$-ball for $p < 2$---the methods are far from optimal. Based on this, we can provide concrete recommendations for when one should use adaptive, mirror or stochastic gradient methods.

For commonly used kernels such as Gaussian, the gradient computations mainly consist of matrix products and linear system solutions, thus they can be sped up significantly with GPU-accelerated linear system solvers. For instance, our imple - mentation took less than 80 miliseconds to compute DI/KDI gradients on an nVidia P100 GPU with feature dimensionalities up to 2000 and batch sizes up to 4000 using Gaussian kernels on the 3 datasets considered. In common learning methodologies, where a linear predictor is trained in conjunction with a parametric non-line ar mapping, the overall objective is to minimize a loss functio n averaged over the entire training sample, i.e., to minimize the expected loss over a single empirical distribution. Since D I directly measures the loss of the best linear predictor on a batch, however, stochastic gradient methods have a differe nt interpretation when utilizing this objective. Since each m ini-batch represents a different empirical distribution, DI ba sed training instead aims to find a feature mapping that adapts to various empirical distributions, which can reduce overfitt ing analogous to how bagging can improve generalization [ 27 ].

Decentralized stochastic gradient method emerges as a promising solution for solving large-scale machine learning problems. This paper studies the decentralized Markov chain gradient descent (DMGD) algorithm - a variant of the decentralized stochastic gradient methods where the random samples are taken along the trajectory of a Markov chain. This setting is well-motivated when obtaining independent samples is costly or impossible, which excludes the use of the traditional stochastic gradient algorithms. Specifically, we consider the first- and zeroth-order versions of decentralized Markov chain gradient descent over a connected network, where each node only communicates with its neighbors about intermediate results. The nonergodic convergence and the ergodic convergence rate of the proposed algorithms have been rigorously established, and their critical dependences on the network topology and the mixing time of Markov chain have been highlighted. The numerical tests further validate the sample efficiency of our algorithm.

There has been an emerging trend in non-Euclidean dimension reduction of aiming to recover a low dimensional structure, namely a manifold, underlying the high dimensional data. Recovering the manifold requires the noise to be of certain concentration. Existing methods address this problem by constructing an output manifold based on the tangent space estimation at each sample point. Although theoretical convergence for these methods is guaranteed, either the samples are noiseless or the noise is bounded. However, if the noise is unbounded, which is a common scenario, the tangent space estimation of the noisy samples will be blurred, thereby breaking the manifold fitting. In this paper, we introduce a new manifold-fitting method, by which the output manifold is constructed by directly estimating the tangent spaces at the projected points on the underlying manifold, rather than at the sample points, to decrease the error caused by the noise. Our new method provides theoretical convergence, in terms of the upper bound on the Hausdorff distance between the output and underlying manifold and the lower bound on the reach of the output manifold, when the noise is unbounded. Numerical simulations are provided to validate our theoretical findings and demonstrate the advantages of our method over other relevant methods. Finally, our method is applied to real data examples.

In the Bayesian analysis of signals immersed in noise [1], we seek a representation for the posterior probability of one or more parameters that govern the shape of the signals. Unless the parameter-to-signal map (the forward model) is very simple, the analysis (or inverse solution) comes at significant computational cost, as it requires the stochastic exploration of the likelihood surface at a large number of locations in parameter space. Such is the case, for instance, of parameter estimation for gravitational-wave sources such as the compact binaries detected by LIGO-Virgo [2, 3]; here each likelihood evaluation requires that we generate the gravitational waveform corresponding to a set of source parameters, and compute its noise-weighted correlation with detector data [4]. Waveform generation is usually the costlier operation, so gravitational-wave analysts often utilize faster, less accurate waveform models [5, 6], or accelerated surrogates of slower, more accurate models [7]. Extending the analysis from the data we have to the data we might measure (i.e., characterizing the parameter-estimation prospects of future experiments) compounds the expense, since we need to explore posteriors for many noise realizations, and across the domain of possible source parameters. For concreteness, we price the evaluation of a single Bayesian posterior at null 10 6 times the cost of generating a waveform, and the characterization of parameter-estimation prospects at null 10 6 times the cost of a posterior. With current computational resources, this means that (for instance) accurate component-mass estimates only become available hours or days after the detection of a binary black-hole coalescence [8, 9], while any extensive study of parameter-estimation prospects must rely on less reliable techniques such as the Fisher-matrix approximation [10]. In this Letter, we show how one-or two-dimensional marginalized Bayesian posteriors may be produced using deep neural networks [11] trained on large ensembles of signal noise data streams.

Messages in human conversations inherently convey emotions. The task of detecting emotions in textual conversations leads to a wide range of applications such as opinion mining in social networks. However, enabling machines to analyze emotions in conversations is challenging, partly because humans often rely on the context and commonsense knowledge to express emotions. In this paper, we address these challenges by proposing a Knowledge-Enriched Transformer (KET), where contextual utterances are interpreted using hierarchical self-attention and external commonsense knowledge is dynamically leveraged using a context-aware affective graph attention mechanism. Experiments on multiple textual conversation datasets demonstrate that both context and commonsense knowledge are consistently beneficial to the emotion detection performance. In addition, the experimental results show that our KET model outperforms the state-of-the-art models on most of the tested datasets in F1 score.

Palo Alto Research Center, Mail Stop: 3333 Coyote Hill Road, Palo Alto, CA 94034 USA Abstract Our research aims at developing intelligent systems to reduce the transportation-related energy expenditure of a large city by influencing individual behavior. We introduce Copter - an intelligent travel assistant that evaluates multi-modal travel alternatives to find a plan that is acceptable to a person given their context and preferences. We propose a formulation for acceptable planning that brings together ideas from AI, machine learning, and economics. This formulation has been incorporated in Copter that produces acceptable plans in real-time. We adopt a novel empirical evaluation framework that combines human decision data with a high fidelity multi-modal transportation simulation to demonstrate a 4% energy reduction and 20% delay reduction in a realistic deployment scenario in Los Angeles, California, USA. 1. Introduction Transportation is one of the largest consumers of energy in the ...