Paper Group ANR 753
PVNet: A LRCN Architecture for Spatio-Temporal Photovoltaic PowerForecasting from Numerical Weather Prediction. Adversarial Risk via Optimal Transport and Optimal Couplings. Training Auto-encoder-based Optimizers for Terahertz Image Reconstruction. Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder. High …
PVNet: A LRCN Architecture for Spatio-Temporal Photovoltaic PowerForecasting from Numerical Weather Prediction
| Title | PVNet: A LRCN Architecture for Spatio-Temporal Photovoltaic PowerForecasting from Numerical Weather Prediction |
| Authors | Johan Mathe, Nina Miolane, Nicolas Sebastien, Jeremie Lequeux |
| Abstract | Photovoltaic (PV) power generation has emerged as one of the lead renewable energy sources. Yet, its production is characterized by high uncertainty, being dependent on weather conditions like solar irradiance and temperature. Predicting PV production, even in the 24-hour forecast, remains a challenge and leads energy providers to left idling - often carbon emitting - plants. In this paper, we introduce a Long-Term Recurrent Convolutional Network using Numerical Weather Predictions (NWP) to predict, in turn, PV production in the 24-hour and 48-hour forecast horizons. This network architecture fully leverages both temporal and spatial weather data, sampled over the whole geographical area of interest. We train our model on an NWP dataset from the National Oceanic and Atmospheric Administration (NOAA) to predict spatially aggregated PV production in Germany. We compare its performance to the persistence model and state-of-the-art methods. |
| Tasks | |
| Published | 2019-02-04 |
| URL | https://arxiv.org/abs/1902.01453v3 |
| https://arxiv.org/pdf/1902.01453v3.pdf | |
| PWC | https://paperswithcode.com/paper/pvnet-a-lrcn-architecture-for-spatio-temporal |
| Repo | |
| Framework | |
Adversarial Risk via Optimal Transport and Optimal Couplings
| Title | Adversarial Risk via Optimal Transport and Optimal Couplings |
| Authors | Muni Sreenivas Pydi, Varun Jog |
| Abstract | The accuracy of modern machine learning algorithms deteriorates severely on adversarially manipulated test data. Optimal adversarial risk quantifies the best error rate of any classifier in the presence of adversaries, and optimal adversarial classifiers are sought that minimize adversarial risk. In this paper, we investigate the optimal adversarial risk and optimal adversarial classifiers from an optimal transport perspective. We present a new and simple approach to show that the optimal adversarial risk for binary classification with $0-1$ loss function is completely characterized by an optimal transport cost between the probability distributions of the two classes, for a suitably defined cost function. We propose a novel coupling strategy that achieves the optimal transport cost for several univariate distributions like Gaussian, uniform and triangular. Using the optimal couplings, we obtain the optimal adversarial classifiers in these settings and show how they differ from optimal classifiers in the absence of adversaries. Based on our analysis, we evaluate algorithm-independent fundamental limits on adversarial risk for CIFAR-10, MNIST, Fashion-MNIST and SVHN datasets, and Gaussian mixtures based on them. In addition to the $0-1$ loss, we also derive bounds on the deviation of optimal risk and optimal classifier in the presence of adversaries for continuous loss functions, that are based on the convexity and smoothness of the loss functions. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02794v1 |
| https://arxiv.org/pdf/1912.02794v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-risk-via-optimal-transport-and |
| Repo | |
| Framework | |
Training Auto-encoder-based Optimizers for Terahertz Image Reconstruction
| Title | Training Auto-encoder-based Optimizers for Terahertz Image Reconstruction |
| Authors | Tak Ming Wong, Matthias Kahl, Peter Haring Bolívar, Andreas Kolb, Michael Möller |
| Abstract | Terahertz (THz) sensing is a promising imaging technology for a wide variety of different applications. Extracting the interpretable and physically meaningful parameters for such applications, however, requires solving an inverse problem in which a model function determined by these parameters needs to be fitted to the measured data. Since the underlying optimization problem is nonconvex and very costly to solve, we propose learning the prediction of suitable parameters from the measured data directly. More precisely, we develop a model-based autoencoder in which the encoder network predicts suitable parameters and the decoder is fixed to a physically meaningful model function, such that we can train the encoding network in an unsupervised way. We illustrate numerically that the resulting network is more than 140 times faster than classical optimization techniques while making predictions with only slightly higher objective values. Using such predictions as starting points of local optimization techniques allows us to converge to better local minima about twice as fast as optimization without the network-based initialization. |
| Tasks | Image Reconstruction |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01377v2 |
| https://arxiv.org/pdf/1907.01377v2.pdf | |
| PWC | https://paperswithcode.com/paper/training-auto-encoder-based-optimizers-for |
| Repo | |
| Framework | |
Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder
| Title | Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder |
| Authors | Heecheol Kim, Masanori Yamada, Kosuke Miyoshi, Hiroshi Yamakawa |
| Abstract | One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions, have been studied to diminish the dimensionality of the action space with regard to the time axis. However, previous studies relied on humans defining macro actions or assumed macro actions as repetitions of the same primitive actions. We present Factorized Macro Action Reinforcement Learning (FaMARL) which autonomously learns disentangled factor representation of a sequence of actions to generate macro actions that can be directly applied to general reinforcement learning algorithms. FaMARL exhibits higher scores than other reinforcement learning algorithms on environments that require an extensive amount of search. |
| Tasks | |
| Published | 2019-03-22 |
| URL | https://arxiv.org/abs/1903.09366v2 |
| https://arxiv.org/pdf/1903.09366v2.pdf | |
| PWC | https://paperswithcode.com/paper/macro-action-reinforcement-learning-with |
| Repo | |
| Framework | |
Higher Order Function Networks for View Planning and Multi-View Reconstruction
| Title | Higher Order Function Networks for View Planning and Multi-View Reconstruction |
| Authors | Selim Engin, Eric Mitchell, Daewon Lee, Volkan Isler, Daniel D. Lee |
| Abstract | We consider the problem of planning views for a robot to acquire images of an object for visual inspection and reconstruction. In contrast to offline methods which require a 3D model of the object as input or online methods which rely on only local measurements, our method uses a neural network which encodes shape information for a large number of objects. We build on recent deep learning methods capable of generating a complete 3D reconstruction of an object from a single image. Specifically, in this work, we extend a recent method which uses Higher Order Functions (HOF) to represent the shape of the object. We present a new generalization of this method to incorporate multiple images as input and establish a connection between visibility and reconstruction quality. This relationship forms the foundation of our view planning method where we compute viewpoints to visually cover the output of the multi-view HOF network with as few images as possible. Experiments indicate that our method provides a good compromise between online and offline methods: Similar to online methods, our method does not require the true object model as input. In terms of number of views, it is much more efficient. In most cases, its performance is comparable to the optimal offline case even on object classes the network has not been trained on. |
| Tasks | 3D Reconstruction |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.02066v1 |
| https://arxiv.org/pdf/1910.02066v1.pdf | |
| PWC | https://paperswithcode.com/paper/higher-order-function-networks-for-view |
| Repo | |
| Framework | |
Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias
| Title | Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias |
| Authors | Asma Ghandeharioun, Brian Eoff, Brendan Jou, Rosalind W. Picard |
| Abstract | Supporting model interpretability for complex phenomena where annotators can legitimately disagree, such as emotion recognition, is a challenging machine learning task. In this work, we show that explicitly quantifying the uncertainty in such settings has interpretability benefits. We use a simple modification of a classical network inference using Monte Carlo dropout to give measures of epistemic and aleatoric uncertainty. We identify a significant correlation between aleatoric uncertainty and human annotator disagreement ($r\approx.3$). Additionally, we demonstrate how difficult and subjective training samples can be identified using aleatoric uncertainty and how epistemic uncertainty can reveal data bias that could result in unfair predictions. We identify the total uncertainty as a suitable surrogate for model calibration, i.e. the degree we can trust model’s predicted confidence. In addition to explainability benefits, we observe modest performance boosts from incorporating model uncertainty. |
| Tasks | Calibration, Emotion Recognition |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09285v2 |
| https://arxiv.org/pdf/1909.09285v2.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-sources-of-uncertainty-to |
| Repo | |
| Framework | |
Reproducibility of an airway tapering measurement in CT with application to bronchiectasis
| Title | Reproducibility of an airway tapering measurement in CT with application to bronchiectasis |
| Authors | Kin Quan, Ryutaro Tanno, Rebecca J. Shipley, Jeremy S. Brown, Joseph Jacob, John R. Hurst, David J. Hawkes |
| Abstract | Purpose: This paper proposes a pipeline to acquire a scalar tapering measurement from the carina to the most distal point of an individual airway visible on CT. We show the applicability of using tapering measurements on clinically acquired data by quantifying the reproducibility of the tapering measure. Methods: We generate a spline from the centreline of an airway to measure the area and arclength at contiguous intervals. The tapering measurement is the gradient of the linear regression between area in log space and arclength. The reproducibility of the measure was assessed by analysing different radiation doses, voxel sizes and reconstruction kernel on single timepoint and longitudinal CT scans and by evaluating the effct of airway bifurcations. Results: Using 74 airways from 10 CT scans, we show a statistical difference, p = 3.4 $\times$ 10$^{-4}$ in tapering between healthy airways (n = 35) and those affected by bronchiectasis (n = 39). The difference between the mean of the two populations was 0.011mm$^{-1}$ and the difference between the medians of the two populations was 0.006mm$^{-1}$. The tapering measurement retained a 95% confidence interval of $\pm$0.005mm$^{-1}$ in a simulated 25 mAs scan and retained a 95% confidence of $\pm$0.005mm$^{-1}$ on simulated CTs up to 1.5 times the original voxel size. Conclusion: We have established an estimate of the precision of the tapering measurement and estimated the effect on precision of simulated voxel size and CT scan dose. We recommend that the scanner calibration be undertaken with the phantoms as described, on the specific CT scanner, radiation dose and reconstruction algorithm that is to be used in any quantitative studies. Our code is available at https://github.com/quan14/AirwayTaperingInCT |
| Tasks | Calibration |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07454v1 |
| https://arxiv.org/pdf/1909.07454v1.pdf | |
| PWC | https://paperswithcode.com/paper/reproducibility-of-an-airway-tapering |
| Repo | |
| Framework | |
Crank up the volume: preference bias amplification in collaborative recommendation
| Title | Crank up the volume: preference bias amplification in collaborative recommendation |
| Authors | Kun Lin, Nasim Sonboli, Bamshad Mobasher, Robin Burke |
| Abstract | Recommender systems are personalized: we expect the results given to a particular user to reflect that user’s preferences. Some researchers have studied the notion of calibration, how well recommendations match users’ stated preferences, and bias disparity the extent to which mis-calibration affects different user groups. In this paper, we examine bias disparity over a range of different algorithms and for different item categories and demonstrate significant differences between model-based and memory-based algorithms. |
| Tasks | Calibration, Recommendation Systems |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06362v1 |
| https://arxiv.org/pdf/1909.06362v1.pdf | |
| PWC | https://paperswithcode.com/paper/crank-up-the-volume-preference-bias |
| Repo | |
| Framework | |
Detecting Deep Neural Network Defects with Data Flow Analysis
| Title | Detecting Deep Neural Network Defects with Data Flow Analysis |
| Authors | Jiazhen Gu, Huanlin Xu, Yangfan Zhou, Xin Wang, Hui Xu, Michael Lyu |
| Abstract | Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks. However, it is very hard to figure out whether the low precision of a DNN model is an inevitable result, or caused by defects. This paper aims at addressing this challenging problem. We find that the internal data flow footprints of a DNN model can provide insights to locate the root cause effectively. We develop DeepMorph (DNN Tomography) to analyze the root cause, which can guide a DNN developer to improve the model. |
| Tasks | Object Recognition |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02190v2 |
| https://arxiv.org/pdf/1909.02190v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-deep-neural-network-defects-with |
| Repo | |
| Framework | |
MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning
| Title | MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning |
| Authors | Bohan Wu, Iretiayo Akinola, Jacob Varley, Peter Allen |
| Abstract | Vision-based grasping systems typically adopt an open-loop execution of a planned grasp. This policy can fail due to many reasons, including ubiquitous calibration error. Recovery from a failed grasp is further complicated by visual occlusion, as the hand is usually occluding the vision sensor as it attempts another open-loop regrasp. This work presents MAT, a tactile closed-loop method capable of realizing grasps provided by a coarse initial positioning of the hand above an object. Our algorithm is a deep reinforcement learning (RL) policy optimized through the clipped surrogate objective within a maximum entropy RL framework to balance exploitation and exploration. The method utilizes tactile and proprioceptive information to act through both fine finger motions and larger regrasp movements to execute stable grasps. A novel curriculum of action motion magnitude makes learning more tractable and helps turn common failure cases into successes. Careful selection of features that exhibit small sim-to-real gaps enables this tactile grasping policy, trained purely in simulation, to transfer well to real world environments without the need for additional learning. Experimentally, this methodology improves over a vision-only grasp success rate substantially on a multi-fingered robot hand. When this methodology is used to realize grasps from coarse initial positions provided by a vision-only planner, the system is made dramatically more robust to calibration errors in the camera-robot transform. |
| Tasks | Calibration |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04787v2 |
| https://arxiv.org/pdf/1909.04787v2.pdf | |
| PWC | https://paperswithcode.com/paper/mat-multi-fingered-adaptive-tactile-grasping |
| Repo | |
| Framework | |
Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds
| Title | Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds |
| Authors | Kosuke Arase, Yusuke Mukuta, Tatsuya Harada |
| Abstract | Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots. Certain existing studies have split input point clouds into small regions such as 1m x 1m; one reason for this is that models in the studies cannot consume a large number of points because of the large space complexity. However, because such small regions occasionally include a very small number of instances belonging to the same class, an evaluation using existing metrics such as mAP is largely affected by the category recognition performance. To address these problems, we propose a new method with space complexity O(Np) such that large regions can be consumed, as well as novel metrics for tasks that are independent of the categories or size of the inputs. Our method learns a mapping from input point clouds to an embedding space, where the embeddings form clusters for each instance and distinguish instances using these clusters during testing. Our method achieves state-of-the-art performance using both existing and the proposed metrics. Moreover, we show that our new metric can evaluate the performance of a task without being affected by any other condition. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-09-27 |
| URL | https://arxiv.org/abs/1909.12655v1 |
| https://arxiv.org/pdf/1909.12655v1.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-task-and-metrics-of-instance |
| Repo | |
| Framework | |
Iteratively reweighted least squares for robust regression via SVM and ELM
| Title | Iteratively reweighted least squares for robust regression via SVM and ELM |
| Authors | Hongwei Dong, Liming Yang |
| Abstract | The measure of most robust machine learning methods is reweighted. To overcome the optimization difficulty of the implicitly reweighted robust methods (including modifying loss functions and objectives), we try to use a more direct method: explicitly iteratively reweighted method to handle noise (even heavy-tailed noise and outlier) robustness. In this paper, an explicitly iterative reweighted framework based on two kinds of kernel based regression algorithm (LS-SVR and ELM) is established, and a novel weight selection strategy is proposed at the same time. Combining the proposed weight function with the iteratively reweighted framework, we propose two models iteratively reweighted least squares support vector machine (IRLS-SVR) and iteratively reweighted extreme learning machine (IRLS-ELM) to implement robust regression. Different from the traditional explicitly reweighted robust methods, we carry out multiple reweighted operations in our work to further improve robustness. The convergence and approximability of the proposed algorithms are proved theoretically. Moreover, the robustness of the algorithm is analyzed in detail from many angles. Experiments on both artificial data and benchmark datasets confirm the validity of the proposed methods. |
| Tasks | |
| Published | 2019-03-27 |
| URL | http://arxiv.org/abs/1903.11202v1 |
| http://arxiv.org/pdf/1903.11202v1.pdf | |
| PWC | https://paperswithcode.com/paper/iteratively-reweighted-least-squares-for |
| Repo | |
| Framework | |
Calibration of a Fluid-Structure Problem with Keras
| Title | Calibration of a Fluid-Structure Problem with Keras |
| Authors | Olivier Pironneau |
| Abstract | In this short paper we report on an inverse problem issued from a physical system, namely a fluid structure problem where the parameters are the rigidity constant, the solid-fluid density ratio and the fluid viscosity. We have chosen a simple geometry so that the numerical solution of the system is easy. We compare the solution of this inverse problem by a Neural Network with a more classical solution obtained with a genetic algorithm. The Neural Network does much better. |
| Tasks | Calibration |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03708v1 |
| https://arxiv.org/pdf/1909.03708v1.pdf | |
| PWC | https://paperswithcode.com/paper/calibration-of-a-fluid-structure-problem-with |
| Repo | |
| Framework | |
Harmless interpolation of noisy data in regression
| Title | Harmless interpolation of noisy data in regression |
| Authors | Vidya Muthukumar, Kailas Vodrahalli, Vignesh Subramanian, Anant Sahai |
| Abstract | A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data is noisy and there are more parameters than data points. We investigate this overparameterized regime in linear regression, where all solutions that minimize training error interpolate the data, including noise. We characterize the fundamental generalization (mean-squared) error of any interpolating solution in the presence of noise, and show that this error decays to zero with the number of features. Thus, overparameterization can be explicitly beneficial in ensuring harmless interpolation of noise. We discuss two root causes for poor generalization that are complementary in nature – signal “bleeding” into a large number of alias features, and overfitting of noise by parsimonious feature selectors. For the sparse linear model with noise, we provide a hybrid interpolating scheme that mitigates both these issues and achieves order-optimal MSE over all possible interpolating solutions. |
| Tasks | |
| Published | 2019-03-21 |
| URL | https://arxiv.org/abs/1903.09139v2 |
| https://arxiv.org/pdf/1903.09139v2.pdf | |
| PWC | https://paperswithcode.com/paper/harmless-interpolation-of-noisy-data-in |
| Repo | |
| Framework | |
Randomized Allocation with Nonparametric Estimation for Contextual Multi-Armed Bandits with Delayed Rewards
| Title | Randomized Allocation with Nonparametric Estimation for Contextual Multi-Armed Bandits with Delayed Rewards |
| Authors | Sakshi Arya, Yuhong Yang |
| Abstract | We study a multi-armed bandit problem with covariates in a setting where there is a possible delay in observing the rewards. Under some mild assumptions on the probability distributions for the delays and using an appropriate randomization to select the arms, the proposed strategy is shown to be strongly consistent. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-02-03 |
| URL | https://arxiv.org/abs/1902.00819v3 |
| https://arxiv.org/pdf/1902.00819v3.pdf | |
| PWC | https://paperswithcode.com/paper/randomized-allocation-with-nonparametric |
| Repo | |
| Framework | |
