Paper Group ANR 827
Towards Generalizing Sensorimotor Control Across Weather Conditions. Proximal Reliability Optimization for Reinforcement Learning. Balancing Accuracy and Diversity in Recommendations using Matrix Completion Framework. Influenza Modeling Based on Massive Feature Engineering and International Flow Deconvolution. Kernel density estimation based sampli …
Towards Generalizing Sensorimotor Control Across Weather Conditions
| Title | Towards Generalizing Sensorimotor Control Across Weather Conditions |
| Authors | Qadeer Khan, Patrick Wenzel, Daniel Cremers, Laura Leal-Taixé |
| Abstract | The ability of deep learning models to generalize well across different scenarios depends primarily on the quality and quantity of annotated data. Labeling large amounts of data for all possible scenarios that a model may encounter would not be feasible; if even possible. We propose a framework to deal with limited labeled training data and demonstrate it on the application of vision-based vehicle control. We show how limited steering angle data available for only one condition can be transferred to multiple different weather scenarios. This is done by leveraging unlabeled images in a teacher-student learning paradigm complemented with an image-to-image translation network. The translation network transfers the images to a new domain, whereas the teacher provides soft supervised targets to train the student on this domain. Furthermore, we demonstrate how utilization of auxiliary networks can reduce the size of a model at inference time, without affecting the accuracy. The experiments show that our approach generalizes well across multiple different weather conditions using only ground truth labels from one domain. |
| Tasks | Image-to-Image Translation |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.11025v1 |
| https://arxiv.org/pdf/1907.11025v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-generalizing-sensorimotor-control |
| Repo | |
| Framework | |
Proximal Reliability Optimization for Reinforcement Learning
| Title | Proximal Reliability Optimization for Reinforcement Learning |
| Authors | Narendra Patwardhan, Zequn Wang |
| Abstract | Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on absolute or deterministic reward as a metric for optimization process renders reinforcement learning highly susceptible to changes in problem dynamics. We introduce a novel framework that effectively quantizes the uncertainty of the design space and induces robustness in controllers by switching to a reliability-based optimization routine. The data efficiency of the method is maintained to match reward based optimization methods by employing a model-based approach. We prove the stability of learned neuro-controllers in both static and dynamic environments on classical reinforcement learning tasks such as Cart Pole balancing and Inverted Pendulum. |
| Tasks | |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.01127v1 |
| https://arxiv.org/pdf/1906.01127v1.pdf | |
| PWC | https://paperswithcode.com/paper/proximal-reliability-optimization-for |
| Repo | |
| Framework | |
Balancing Accuracy and Diversity in Recommendations using Matrix Completion Framework
| Title | Balancing Accuracy and Diversity in Recommendations using Matrix Completion Framework |
| Authors | Anupriya Gogna, Angshul Majumdar |
| Abstract | Design of recommender systems aimed at achieving high prediction accuracy is a widely researched area. However, several studies have suggested the need for diversified recommendations, with acceptable level of accuracy, to avoid monotony and improve customers experience. However, increasing diversity comes with an associated reduction in recommendation accuracy; thereby necessitating an optimum tradeoff between the two. In this work, we attempt to achieve accuracy vs diversity balance, by exploiting available ratings and item metadata, through a single, joint optimization model built over the matrix completion framework. Most existing works, unlike our formulation, propose a 2 stage model, a heuristic item ranking scheme on top of an existing collaborative filtering technique. Experimental evaluation on a movie recommender system indicates that our model achieves higher diversity for a given drop in accuracy as compared to existing state of the art techniques. |
| Tasks | Matrix Completion, Recommendation Systems |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/2001.04349v1 |
| https://arxiv.org/pdf/2001.04349v1.pdf | |
| PWC | https://paperswithcode.com/paper/balancing-accuracy-and-diversity-in |
| Repo | |
| Framework | |
Influenza Modeling Based on Massive Feature Engineering and International Flow Deconvolution
| Title | Influenza Modeling Based on Massive Feature Engineering and International Flow Deconvolution |
| Authors | Ziming Liu, Yixuan Wang, Zizhao Han, Dian Wu |
| Abstract | In this article, we focus on the analysis of the potential factors driving the spread of influenza, and possible policies to mitigate the adverse effects of the disease. To be precise, we first invoke discrete Fourier transform (DFT) to conclude a yearly periodic regional structure in the influenza activity, thus safely restricting ourselves to the analysis of the yearly influenza behavior. Then we collect a massive number of possible region-wise indicators contributing to the influenza mortality, such as consumption, immunization, sanitation, water quality, and other indicators from external data, with $1170$ dimensions in total. We extract significant features from the high dimensional indicators using a combination of data analysis techniques, including matrix completion, support vector machines (SVM), autoencoders, and principal component analysis (PCA). Furthermore, we model the international flow of migration and trade as a convolution on regional influenza activity, and solve the deconvolution problem as higher-order perturbations to the linear regression, thus separating regional and international factors related to the influenza mortality. Finally, both the original model and the perturbed model are tested on regional examples, as validations of our models. Pertaining to the policy, we make a proposal based on the connectivity data along with the previously extracted significant features to alleviate the impact of influenza, as well as efficiently propagate and carry out the policies. We conclude that environmental features and economic features are of significance to the influenza mortality. The model can be easily adapted to model other types of infectious diseases. |
| Tasks | Feature Engineering, Matrix Completion |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.02989v1 |
| https://arxiv.org/pdf/1912.02989v1.pdf | |
| PWC | https://paperswithcode.com/paper/influenza-modeling-based-on-massive-feature |
| Repo | |
| Framework | |
Kernel density estimation based sampling for imbalanced class distribution
| Title | Kernel density estimation based sampling for imbalanced class distribution |
| Authors | Firuz Kamalov |
| Abstract | Imbalanced response variable distribution is a common occurrence in data science. In fields such as fraud detection, medical diagnostics, system intrusion detection and many others where abnormal behavior is rarely observed the data under study often features disproportionate target class distribution. One common way to combat class imbalance is through resampling the minority class to achieve a more balanced distribution. In this paper, we investigate the performance of the sampling method based on kernel density estimation (KDE). We believe that KDE offers a more natural way of generating new instances of minority class that is less prone to overfitting than other standard sampling techniques. It is based on a well established theory of nonparametric statistical estimation. Numerical experiments show that KDE can outperform other sampling techniques on a range of real life datasets as measured by F1-score and G-mean. The results remain consistent across a number of classification algorithms used in the experiments. Furthermore, the proposed method outperforms the benchmark methods irregardless of the class distribution ratio. We conclude, based on the solid theoretical foundation and strong experimental results, that the proposed method would be a valuable tool in problems involving imbalanced class distribution. |
| Tasks | Density Estimation, Fraud Detection, Intrusion Detection |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.07842v2 |
| https://arxiv.org/pdf/1910.07842v2.pdf | |
| PWC | https://paperswithcode.com/paper/kde-sampling-for-imbalanced-class |
| Repo | |
| Framework | |
Inertial nonconvex alternating minimizations for the image deblurring
| Title | Inertial nonconvex alternating minimizations for the image deblurring |
| Authors | Tao Sun, Roberto Barrio, Marcos Rodriguez, Hao Jiang |
| Abstract | In image processing, Total Variation (TV) regularization models are commonly used to recover blurred images. One of the most efficient and popular methods to solve the convex TV problem is the Alternating Direction Method of Multipliers (ADMM) algorithm, recently extended using the inertial proximal point method. Although all the classical studies focus on only a convex formulation, recent articles are paying increasing attention to the nonconvex methodology due to its good numerical performance and properties. In this paper, we propose to extend the classical formulation with a novel nonconvex Alternating Direction Method of Multipliers with the Inertial technique (IADMM). Under certain assumptions on the parameters, we prove the convergence of the algorithm with the help of the Kurdyka-{\L}ojasiewicz property. We also present numerical simulations on classical TV image reconstruction problems to illustrate the efficiency of the new algorithm and its behavior compared with the well established ADMM method. |
| Tasks | Deblurring, Image Reconstruction |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.12945v1 |
| https://arxiv.org/pdf/1907.12945v1.pdf | |
| PWC | https://paperswithcode.com/paper/inertial-nonconvex-alternating-minimizations |
| Repo | |
| Framework | |
Inverse-Transform AutoEncoder for Anomaly Detection
| Title | Inverse-Transform AutoEncoder for Anomaly Detection |
| Authors | Chaoqing Huang, Jinkun Cao, Fei Ye, Maosen Li, Ya Zhang, Cewu Lu |
| Abstract | Reconstruction-based methods have recently shown great promise for anomaly detection. We here propose a new transform-based framework for anomaly detection. A selected set of transformations based on human priors is used to erase certain targeted information from input data. An inverse-transform autoencoder is trained with the normal data only to embed corresponding erased information during the restoration of the original data. The normal and anomalous data are thus expected to be differentiable based on restoration errors. Extensive experiments have demonstrated that the proposed method significantly outperforms several state-of-the-arts on multiple benchmark datasets, especially on ImageNet, increasing the AUROC of the top-performing baseline by 10.1%. We also evaluate our method on a real-world anomaly detection dataset MVTec AD and a video anomaly detection dataset ShanghaiTech to validate the effectiveness of the method in real-world environments. |
| Tasks | Anomaly Detection |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10676v1 |
| https://arxiv.org/pdf/1911.10676v1.pdf | |
| PWC | https://paperswithcode.com/paper/inverse-transform-autoencoder-for-anomaly |
| Repo | |
| Framework | |
Early Classification for Agricultural Monitoring from Satellite Time Series
| Title | Early Classification for Agricultural Monitoring from Satellite Time Series |
| Authors | Marc Rußwurm, Romain Tavenard, Sébastien Lefèvre, Marco Körner |
| Abstract | In this work, we introduce a recently developed early classification mechanism to satellite-based agricultural monitoring. It augments existing classification models by an additional stopping probability based on the previously seen information. This mechanism is end-to-end trainable and derives its stopping decision solely from the observed satellite data. We show results on field parcels in central Europe where sufficient ground truth data is available for an empiric evaluation of the results with local phenological information obtained from authorities. We observe that the recurrent neural network outfitted with this early classification mechanism was able to distinguish the many of the crop types before the end of the vegetative period. Further, we associated these stopping times with evaluated ground truth information and saw that the times of classification were related to characteristic events of the observed plants’ phenology. |
| Tasks | Time Series |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10283v1 |
| https://arxiv.org/pdf/1908.10283v1.pdf | |
| PWC | https://paperswithcode.com/paper/early-classification-for-agricultural |
| Repo | |
| Framework | |
Blind Deblurring using Deep Learning: A Survey
| Title | Blind Deblurring using Deep Learning: A Survey |
| Authors | Siddhant Sahu, Manoj Kumar Lenka, Pankaj Kumar Sa |
| Abstract | We inspect all the deep learning based solutions and provide holistic understanding of various architectures that have evolved over the past few years to solve blind deblurring. The introductory work used deep learning to estimate some features of the blur kernel and then moved onto predicting the blur kernel entirely, which converts the problem into non-blind deblurring. The recent state of the art techniques are end to end, i.e., they don’t estimate the blur kernel rather try to estimate the latent sharp image directly from the blurred image. The benchmarking PSNR and SSIM values on standard datasets of GOPRO and Kohler using various architectures are also provided. |
| Tasks | Deblurring |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.10128v1 |
| https://arxiv.org/pdf/1907.10128v1.pdf | |
| PWC | https://paperswithcode.com/paper/blind-deblurring-using-deep-learning-a-survey |
| Repo | |
| Framework | |
A Case for Backward Compatibility for Human-AI Teams
| Title | A Case for Backward Compatibility for Human-AI Teams |
| Authors | Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, Eric Horvitz |
| Abstract | AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI’s inferences. A successful partnership requires that the human develops insights into the performance of the AI system, including its failures. We study the influence of updates to an AI system in this setting. While updates can increase the AI’s predictive performance, they may also lead to changes that are at odds with the user’s prior experiences and confidence in the AI’s inferences, hurting therefore the overall team performance. We introduce the notion of the compatibility of an AI update with prior user experience and present methods for studying the role of compatibility in human-AI teams. Empirical results on three high-stakes domains show that current machine learning algorithms do not produce compatible updates. We propose a re-training objective to improve the compatibility of an update by penalizing new errors. The objective offers full leverage of the performance/compatibility tradeoff, enabling more compatible yet accurate updates. |
| Tasks | Decision Making |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01148v1 |
| https://arxiv.org/pdf/1906.01148v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-case-for-backward-compatibility-for-human |
| Repo | |
| Framework | |
Dynamically Composing Domain-Data Selection with Clean-Data Selection by “Co-Curricular Learning” for Neural Machine Translation
| Title | Dynamically Composing Domain-Data Selection with Clean-Data Selection by “Co-Curricular Learning” for Neural Machine Translation |
| Authors | Wei Wang, Isaac Caswell, Ciprian Chelba |
| Abstract | Noise and domain are important aspects of data quality for neural machine translation. Existing research focus separately on domain-data selection, clean-data selection, or their static combination, leaving the dynamic interaction across them not explicitly examined. This paper introduces a “co-curricular learning” method to compose dynamic domain-data selection with dynamic clean-data selection, for transfer learning across both capabilities. We apply an EM-style optimization procedure to further refine the “co-curriculum”. Experiment results and analysis with two domains demonstrate the effectiveness of the method and the properties of data scheduled by the co-curriculum. |
| Tasks | Machine Translation, Transfer Learning |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.01130v1 |
| https://arxiv.org/pdf/1906.01130v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamically-composing-domain-data-selection |
| Repo | |
| Framework | |
Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
| Title | Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations |
| Authors | Rui Zhang, Caitlin Westerfield, Sungrok Shim, Garrett Bingham, Alexander Fabbri, Neha Verma, William Hu, Dragomir Radev |
| Abstract | In this paper, we propose to boost low-resource cross-lingual document retrieval performance with deep bilingual query-document representations. We match queries and documents in both source and target languages with four components, each of which is implemented as a term interaction-based deep neural network with cross-lingual word embeddings as input. By including query likelihood scores as extra features, our model effectively learns to rerank the retrieved documents by using a small number of relevance labels for low-resource language pairs. Due to the shared cross-lingual word embedding space, the model can also be directly applied to another language pair without any training label. Experimental results on the MATERIAL dataset show that our model outperforms the competitive translation-based baselines on English-Swahili, English-Tagalog, and English-Somali cross-lingual information retrieval tasks. |
| Tasks | Information Retrieval, Word Embeddings |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03492v1 |
| https://arxiv.org/pdf/1906.03492v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-low-resource-cross-lingual-document |
| Repo | |
| Framework | |
Novel Uncertainty Framework for Deep Learning Ensembles
| Title | Novel Uncertainty Framework for Deep Learning Ensembles |
| Authors | Tal Kachman, Michal Moshkovitz, Michal Rosen-Zvi |
| Abstract | Deep neural networks have become the default choice for many of the machine learning tasks such as classification and regression. Dropout, a method commonly used to improve the convergence of deep neural networks, generates an ensemble of thinned networks with extensive weight sharing. Recent studies that dropout can be viewed as an approximate variational inference in Gaussian processes, and used as a practical tool to obtain uncertainty estimates of the network. We propose a novel statistical mechanics based framework to dropout and use this framework to propose a new generic algorithm that focuses on estimates of the variance of the loss as measured by the ensemble of thinned networks. Our approach can be applied to a wide range of deep neural network architectures and machine learning tasks. In classification, this algorithm allows the generation of a don’t-know answer to be generated, which can increase the reliability of the classifier. Empirically we demonstrate state-of-the-art AUC results on publicly available benchmarks. |
| Tasks | Gaussian Processes |
| Published | 2019-04-09 |
| URL | http://arxiv.org/abs/1904.04917v1 |
| http://arxiv.org/pdf/1904.04917v1.pdf | |
| PWC | https://paperswithcode.com/paper/novel-uncertainty-framework-for-deep-learning |
| Repo | |
| Framework | |
Robust Deep Gaussian Processes
| Title | Robust Deep Gaussian Processes |
| Authors | Jeremias Knoblauch |
| Abstract | This report provides an in-depth overview over the implications and novelty Generalized Variational Inference (GVI) (Knoblauch et al., 2019) brings to Deep Gaussian Processes (DGPs) (Damianou & Lawrence, 2013). Specifically, robustness to model misspecification as well as principled alternatives for uncertainty quantification are motivated with an information-geometric view. These modifications have clear interpretations and can be implemented in less than 100 lines of Python code. Most importantly, the corresponding empirical results show that DGPs can greatly benefit from the presented enhancements. |
| Tasks | Gaussian Processes |
| Published | 2019-04-04 |
| URL | https://arxiv.org/abs/1904.02303v2 |
| https://arxiv.org/pdf/1904.02303v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-deep-gaussian-processes |
| Repo | |
| Framework | |
Quantifying the Effects of the 2008 Recession using the Zillow Dataset
| Title | Quantifying the Effects of the 2008 Recession using the Zillow Dataset |
| Authors | Arunav Gupta, Lucas Nguyen, Camille Dunning, Ka Ming Chan |
| Abstract | This report explores the use of Zillow’s housing metrics dataset to investigate the effects of the 2008 US subprime mortgage crisis on various US locales. We begin by exploring the causes of the recession and the metrics available to us in the dataset. We settle on using the Zillow Home Value Index (ZHVI) because it is seasonally adjusted and able to account for a variety of inventory factors. Then, we explore three methodologies for quantifying recession impact: (a) Principal Components Analysis, (b) Area Under Baseline, and (c) ARIMA modeling and Confidence Intervals. While PCA does not yield useable results, we ended up with six cities from both AUB and ARIMA analysis, the top 3 “losers” and “gainers” of the 2008 recession, as determined by each analysis. This gave us 12 cities in total. Finally, we tested the robustness of our analysis against three “common knowledge” metrics for the recession: geographic clustering, population trends, and unemployment rate. While we did find some overlap between the results of our analysis and geographic clustering, there was no positive regression outcome from comparing our methodologies to population trends and the unemployment rate. |
| Tasks | |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.11341v1 |
| https://arxiv.org/pdf/1912.11341v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantifying-the-effects-of-the-2008-recession |
| Repo | |
| Framework | |
