January 30, 2020

3199 words 16 mins read

Paper Group ANR 326

Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuning. Audio-Visual Kinship Verification. Web data mining for public health purposes. Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning. EM-like Learning Chaotic Dynamics from Noisy and Partial Observations. Statistical EL is ExpTime-comple …

Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuning


Title	Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuning
Authors	Marcello Fiducioso, Sebastian Curi, Benedikt Schumacher, Markus Gwerder, Andreas Krause
Abstract	We tune one of the most common heating, ventilation, and air conditioning (HVAC) control loops, namely the temperature control of a room. For economical and environmental reasons, it is of prime importance to optimize the performance of this system. Buildings account from 20 to 40% of a country energy consumption, and almost 50% of it comes from HVAC systems. Scenario projections predict a 30% decrease in heating consumption by 2050 due to efficiency increase. Advanced control techniques can improve performance; however, the proportional-integral-derivative (PID) control is typically used due to its simplicity and overall performance. We use Safe Contextual Bayesian Optimization to optimize the PID parameters without human intervention. We reduce costs by 32% compared to the current PID controller setting while assuring safety and comfort to people in the room. The results of this work have an immediate impact on the room control loop performances and its related commissioning costs. Furthermore, this successful attempt paves the way for further use at different levels of HVAC systems, with promising energy, operational, and commissioning costs savings, and it is a practical demonstration of the positive effects that Artificial Intelligence can have on environmental sustainability.
Tasks
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12086v1
PDF	https://arxiv.org/pdf/1906.12086v1.pdf
PWC	https://paperswithcode.com/paper/safe-contextual-bayesian-optimization-for
Repo
Framework

Audio-Visual Kinship Verification


Title	Audio-Visual Kinship Verification
Authors	Xiaoting Wu, Eric Granger, Xiaoyi Feng
Abstract	Visual kinship verification entails confirming whether or not two individuals in a given pair of images or videos share a hypothesized kin relation. As a generalized face verification task, visual kinship verification is particularly difficult with low-quality found Internet data. Due to uncontrolled variations in background, pose, facial expression, blur, illumination and occlusion, state-of-the-art methods fail to provide high level of recognition accuracy. As with many other visual recognition tasks, kinship verification may benefit from combining visual and audio signals. However, voice-based kinship verification has received very little prior attention. We hypothesize that the human voice contains kin-related cues that are complementary to visual cues. In this paper, we address, for the first time, the use of audio-visual information from face and voice modalities to perform kinship verification. We first propose a new multi-modal kinship dataset, called TALking KINship (TALKIN), that contains several pairs of Internet-quality video sequences. Using TALKIN, we then study the utility of various kinship verification methods including traditional local feature based methods, statistical methods and more recent deep learning approaches. Then, early and late fusion methods are evaluated on the TALKIN dataset for the study of kinship verification with both face and voice modalities. Finally, we propose a deep Siamese fusion network with contrastive loss for multi-modal fusion of kinship relations. Extensive experiments on the TALKIN dataset indicate that by combining face and voice modalities, the proposed Siamese network can provide a significantly higher level of accuracy compared to baseline uni-modal and multi-modal fusion techniques. Experimental results also indicate that audio (vocal) information is complementary (to facial information) and useful for kinship verification.
Tasks	Face Verification
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10096v1
PDF	https://arxiv.org/pdf/1906.10096v1.pdf
PWC	https://paperswithcode.com/paper/audio-visual-kinship-verification
Repo
Framework

Web data mining for public health purposes


Title	Web data mining for public health purposes
Authors	Niels Dalum Hansen
Abstract	For a long time, public health events, such as disease incidence or vaccination activity, have been monitored to keep track of the health status of the population, allowing to evaluate the effect of public health initiatives and to decide where resources for improving public health are best spent. This thesis investigates the use of web data mining for public health monitoring, and makes contributions in the following two areas: New approaches for predicting public health events from web mined data, and novel applications of web mined data for public health monitoring.
Tasks
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00829v1
PDF	https://arxiv.org/pdf/1905.00829v1.pdf
PWC	https://paperswithcode.com/paper/web-data-mining-for-public-health-purposes
Repo
Framework

Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning


Title	Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning
Authors	Wenjie Shi, Shiji Song, Cheng Wu
Abstract	Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot scale to tasks with very high state and action dimensionality such as 3D humanoid locomotion. Besides, the optimality of desired Boltzmann policy set for non-optimal soft value function is not persuasive enough. In this paper, we first derive soft policy gradient based on entropy regularized expected reward objective for RL with continuous actions. Then, we present an off-policy actor-critic, model-free maximum entropy deep RL algorithm called deep soft policy gradient (DSPG) by combining soft policy gradient with soft Bellman equation. To ensure stable learning while eliminating the need of two separate critics for soft value functions, we leverage double sampling approach to making the soft Bellman equation tractable. The experimental results demonstrate that our method outperforms in performance over off-policy prior methods.
Tasks
Published	2019-09-07
URL	https://arxiv.org/abs/1909.03198v1
PDF	https://arxiv.org/pdf/1909.03198v1.pdf
PWC	https://paperswithcode.com/paper/soft-policy-gradient-method-for-maximum
Repo
Framework

EM-like Learning Chaotic Dynamics from Noisy and Partial Observations


Title	EM-like Learning Chaotic Dynamics from Noisy and Partial Observations
Authors	Duong Nguyen, Said Ouala, Lucas Drumetz, Ronan Fablet
Abstract	The identification of the governing equations of chaotic dynamical systems from data has recently emerged as a hot topic. While the seminal work by Brunton et al. reported proof-of-concepts for idealized observation setting for fully-observed systems, {\em i.e.} large signal-to-noise ratios and high-frequency sampling of all system variables, we here address the learning of data-driven representations of chaotic dynamics for partially-observed systems, including significant noise patterns and possibly lower and irregular sampling setting. Instead of considering training losses based on short-term prediction error like state-of-the-art learning-based schemes, we adopt a Bayesian formulation and state this issue as a data assimilation problem with unknown model parameters. To solve for the joint inference of the hidden dynamics and of model parameters, we combine neural-network representations and state-of-the-art assimilation schemes. Using iterative Expectation-Maximization (EM)-like procedures, the key feature of the proposed inference schemes is the derivation of the posterior of the hidden dynamics. Using a neural-network-based Ordinary Differential Equation (ODE) representation of these dynamics, we investigate two strategies: their combination to Ensemble Kalman Smoothers and Long Short-Term Memory (LSTM)-based variational approximations of the posterior. Through numerical experiments on the Lorenz-63 system with different noise and time sampling settings, we demonstrate the ability of the proposed schemes to recover and reproduce the hidden chaotic dynamics, including their Lyapunov characteristic exponents, when classic machine learning approaches fail.
Tasks
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10335v1
PDF	http://arxiv.org/pdf/1903.10335v1.pdf
PWC	https://paperswithcode.com/paper/em-like-learning-chaotic-dynamics-from-noisy
Repo
Framework

Statistical EL is ExpTime-complete


Title	Statistical EL is ExpTime-complete
Authors	Bartosz Bednarczyk
Abstract	We show that consistency of Statistical EL knowledge bases, as defined by Penaloza and Potyka in SUM 2017 [4] is ExpTime-hard. Together with the existing ExpTime upper bound by Baader in FroCos 2017 [1], the result leads to the ExpTime-completeness of the mentioned logic. Our proof goes via a reduction from consistency of EL extended with an atomic negation, which is known to be equivalent to the well-known ExpTime-complete description logic ALC.
Tasks
Published	2019-11-02
URL	https://arxiv.org/abs/1911.00696v1
PDF	https://arxiv.org/pdf/1911.00696v1.pdf
PWC	https://paperswithcode.com/paper/statistical-el-is-exptime-complete
Repo
Framework

Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches


Title	Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches
Authors	Hosnieh Sattar, Katharina Krombholz, Gerard Pons-Moll, Mario Fritz
Abstract	Modern approaches to pose and body shape estimation have recently achieved strong performance even under challenging real-world conditions. Even from a single image of a clothed person, a realistic looking body shape can be inferred that captures a users’ weight group and body shape type well. This opens up a whole spectrum of applications – in particular in fashion – where virtual try-on and recommendation systems can make use of these new and automatized cues. However, a realistic depiction of the undressed body is regarded highly private and therefore might not be consented by most people. Hence, we ask if the automatic extraction of such information can be effectively evaded. While adversarial perturbations have been shown to be effective for manipulating the output of machine learning models – in particular, end-to-end deep learning approaches – state of the art shape estimation methods are composed of multiple stages. We perform the first investigation of different strategies that can be used to effectively manipulate the automatic shape estimation while preserving the overall appearance of the original image.
Tasks	Recommendation Systems
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11503v1
PDF	https://arxiv.org/pdf/1905.11503v1.pdf
PWC	https://paperswithcode.com/paper/shape-evasion-preventing-body-shape-inference
Repo
Framework

An Analytical Lidar Sensor Model Based on Ray Path Information


Title	An Analytical Lidar Sensor Model Based on Ray Path Information
Authors	Alexander Schaefer, Lukas Luft, Wolfram Burgard
Abstract	Two core competencies of a mobile robot are to build a map of the environment and to estimate its own pose on the basis of this map and incoming sensor readings. To account for the uncertainties in this process, one typically employs probabilistic state estimation approaches combined with a model of the specific sensor. Over the past years, lidar sensors have become a popular choice for mapping and localization. However, many common lidar models perform poorly in unstructured, unpredictable environments, they lack a consistent physical model for both mapping and localization, and they do not exploit all the information the sensor provides, e.g. out-of-range measurements. In this paper, we introduce a consistent physical model that can be applied to mapping as well as to localization. It naturally deals with unstructured environments and makes use of both out-of-range measurements and information about the ray path. The approach can be seen as a generalization of the well-established reflection model, but in addition to counting ray reflections and traversals in a specific map cell, it considers the distances that all rays travel inside this cell. We prove that the resulting map maximizes the data likelihood and demonstrate that our model outperforms state-of-the-art sensor models in extensive real-world experiments.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10469v1
PDF	https://arxiv.org/pdf/1910.10469v1.pdf
PWC	https://paperswithcode.com/paper/an-analytical-lidar-sensor-model-based-on-ray
Repo
Framework

Walking the Tightrope: An Investigation of the Convolutional Autoencoder Bottleneck


Title	Walking the Tightrope: An Investigation of the Convolutional Autoencoder Bottleneck
Authors	Ilja Manakov, Markus Rohm, Volker Tresp
Abstract	In this paper, we present an in-depth investigation of the convolutional autoencoder (CAE) bottleneck. Autoencoders (AE), and especially their convolutional variants, play a vital role in the current deep learning toolbox. Researchers and practitioners employ CAEs for a variety of tasks, ranging from outlier detection and compression to transfer and representation learning. Despite their widespread adoption, we have limited insight into how the bottleneck shape impacts the emergent properties of the CAE. We demonstrate that increased height and width of the bottleneck drastically improves generalization, which in turn leads to better performance of the latent codes in downstream transfer learning tasks. The number of channels in the bottleneck, on the other hand, is secondary in importance. Furthermore, we show empirically that, contrary to popular belief, CAEs do not learn to copy their input, even when the bottleneck has the same number of neurons as there are pixels in the input. Copying does not occur, despite training the CAE for 1,000 epochs on a tiny ($\approx$ 600 images) dataset. We believe that the findings in this paper are directly applicable and will lead to improvements in models that rely on CAEs.
Tasks	Outlier Detection, Representation Learning, Transfer Learning
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07460v1
PDF	https://arxiv.org/pdf/1911.07460v1.pdf
PWC	https://paperswithcode.com/paper/walking-the-tightrope-an-investigation-of-the-1
Repo
Framework

Improving the Robustness of Capsule Networks to Image Affine Transformations


Title	Improving the Robustness of Capsule Networks to Image Affine Transformations
Authors	Jindong Gu, Volker Tresp
Abstract	Convolutional neural networks (CNNs) achieve translational invariance by using pooling operations. However, the operations do not preserve the spatial relationships in the learned representations. Hence, CNNs cannot extrapolate to various geometric transformations of inputs. Recently, Capsule Networks (CapsNets) have been proposed to tackle this problem. In CapsNets, each entity is represented by a vector and routed to high-level entity representations by a dynamic routing algorithm. CapsNets have been shown to be more robust than CNNs to affine transformations of inputs. However, there is still a huge gap between their performance on transformed inputs compared to untransformed versions. In this work, we first revisit the routing procedure by (un)rolling its forward and backward passes. Our investigation reveals that the routing procedure contributes neither to the generalization ability nor to the affine robustness of the CapsNets. Furthermore, we explore the limitations of capsule transformations and propose affine CapsNets (Aff-CapsNets), which are more robust to affine transformations. On our benchmark task, where models are trained on the MNIST dataset and tested on the AffNIST dataset, our Aff-CapsNets improve the benchmark performance by a large margin (from 79% to 93.21%), without using any routing mechanism.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07968v3
PDF	https://arxiv.org/pdf/1911.07968v3.pdf
PWC	https://paperswithcode.com/paper/improving-the-robustness-of-capsule-networks
Repo
Framework

Generalized Sparse Additive Models


Title	Generalized Sparse Additive Models
Authors	Asad Haris, Noah Simon, Ali Shojaie
Abstract	We present a unified framework for estimation and analysis of generalized additive models in high dimensions. The framework defines a large class of penalized regression estimators, encompassing many existing methods. An efficient computational algorithm for this class is presented that easily scales to thousands of observations and features. We prove minimax optimal convergence bounds for this class under a weak compatibility condition. In addition, we characterize the rate of convergence when this compatibility condition is not met. Finally, we also show that the optimal penalty parameters for structure and sparsity penalties in our framework are linked, allowing cross-validation to be conducted over only a single tuning parameter. We complement our theoretical results with empirical studies comparing some existing methods within this framework.
Tasks
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04641v1
PDF	http://arxiv.org/pdf/1903.04641v1.pdf
PWC	https://paperswithcode.com/paper/generalized-sparse-additive-models
Repo
Framework

Projection-Based 2.5D U-net Architecture for Fast Volumetric Segmentation


Title	Projection-Based 2.5D U-net Architecture for Fast Volumetric Segmentation
Authors	Christoph Angermann, Markus Haltmeier, Ruth Steiger, Sergiy Pereverzyev Jr, Elke Gizewski
Abstract	Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and require long training time. To overcome this issue, we introduce a network structure for volumetric data without 3D convolutional layers. The main idea is to include maximum intensity projections from different directions to transform the volumetric data to a sequence of images, where each image contains information of the full data. We then apply 2D convolutions to these projection images and lift them again to volumetric data using a trainable reconstruction algorithm.The proposed network architecture has less storage requirements than network structures using 3D convolutions. For a tested binary segmentation task, it even shows better performance than the 3D U-net and can be trained much faster.
Tasks
Published	2019-02-01
URL	https://arxiv.org/abs/1902.00347v2
PDF	https://arxiv.org/pdf/1902.00347v2.pdf
PWC	https://paperswithcode.com/paper/projection-based-25d-u-net-architecture-for
Repo
Framework

Combinatorial Sleeping Bandits with Fairness Constraints


Title	Combinatorial Sleeping Bandits with Fairness Constraints
Authors	Fengjiao Li, Jia Liu, Bo Ji
Abstract	The multi-armed bandit (MAB) model has been widely adopted for studying many practical optimization problems (network resource allocation, ad placement, crowdsourcing, etc.) with unknown parameters. The goal of the player here is to maximize the cumulative reward in the face of uncertainty. However, the basic MAB model neglects several important factors of the system in many real-world applications, where multiple arms can be simultaneously played and an arm could sometimes be “sleeping”. Besides, ensuring fairness is also a key design concern in practice. To that end, we propose a new Combinatorial Sleeping MAB model with Fairness constraints, called CSMAB-F, aiming to address the aforementioned crucial modeling issues. The objective is now to maximize the reward while satisfying the fairness requirement of a minimum selection fraction for each individual arm. To tackle this new problem, we extend an online learning algorithm, UCB, to deal with a critical tradeoff between exploitation and exploration and employ the virtual queue technique to properly handle the fairness constraints. By carefully integrating these two techniques, we develop a new algorithm, called Learning with Fairness Guarantee (LFG), for the CSMAB-F problem. Further, we rigorously prove that not only LFG is feasibility-optimal, but it also has a time-average regret upper bounded by $\frac{N}{2\eta}+\frac{\beta_1\sqrt{mNT\log{T}}+\beta_2 N}{T}$, where N is the total number of arms, m is the maximum number of arms that can be simultaneously played, T is the time horizon, $\beta_1$ and $\beta_2$ are constants, and $\eta$ is a design parameter that we can tune. Finally, we perform extensive simulations to corroborate the effectiveness of the proposed algorithm. Interestingly, the simulation results reveal an important tradeoff between the regret and the speed of convergence to a point satisfying the fairness constraints.
Tasks
Published	2019-01-15
URL	https://arxiv.org/abs/1901.04891v3
PDF	https://arxiv.org/pdf/1901.04891v3.pdf
PWC	https://paperswithcode.com/paper/combinatorial-sleeping-bandits-with-fairness
Repo
Framework

A data-driven approach for discovering heat load patterns in district heating


Title	A data-driven approach for discovering heat load patterns in district heating
Authors	Ece Calikus, Slawomir Nowaczyk, Anita Sant’Anna, Henrik Gadd, Sven Werner
Abstract	Understanding the heat usage of customers is crucial for effective district heating operations and management. Unfortunately, existing knowledge about customers and their heat load behaviors is quite scarce. Most previous studies are limited to small-scale analyses that are not representative enough to understand the behavior of the overall network. In this work, we propose a data-driven approach that enables large-scale automatic analysis of heat load patterns in district heating networks without requiring prior knowledge. Our method clusters the customer profiles into different groups, extracts their representative patterns, and detects unusual customers whose profiles deviate significantly from the rest of their group. Using our approach, we present the first large-scale, comprehensive analysis of the heat load patterns by conducting a case study on many buildings in six different customer categories connected to two district heating networks in the south of Sweden. The 1222 buildings had a total floor space of 3.4 million square meters and used 1540 TJ heat during 2016. The results show that the proposed method has a high potential to be deployed and used in practice to analyze and understand customers’ heat-use habits.
Tasks
Published	2019-01-14
URL	https://arxiv.org/abs/1901.04863v3
PDF	https://arxiv.org/pdf/1901.04863v3.pdf
PWC	https://paperswithcode.com/paper/a-data-driven-approach-for-discovery-of-heat
Repo
Framework

calibDB: enabling web based computer vision through on-the-fly camera calibration


Title	calibDB: enabling web based computer vision through on-the-fly camera calibration
Authors	Pavel Rojtberg, Felix Gorschlüter
Abstract	For many computer vision applications, the availability of camera calibration data is crucial as overall quality heavily depends on it. While calibration data is available on some devices through Augmented Reality (AR) frameworks like ARCore and ARKit, for most cameras this information is not available. Therefore, we propose a web based calibration service that not only aggregates calibration data, but also allows calibrating new cameras on-the-fly. We build upon a novel camera calibration framework that enables even novice users to perform a precise camera calibration in about 2 minutes. This allows general deployment of computer vision algorithms on the web, which was previously not possible due to lack of calibration data.
Tasks	Calibration
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04100v2
PDF	https://arxiv.org/pdf/1907.04100v2.pdf
PWC	https://paperswithcode.com/paper/calibdb-enabling-web-based-computer-vision
Repo
Framework