Paper Group ANR 634
Scalable Exact Inference in Multi-Output Gaussian Processes. Deep Reinforcement Learning for Routing a Heterogeneous Fleet of Vehicles. Day-Ahead Hourly Forecasting of Power Generation from Photovoltaic Plants. High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes. Robust Prediction when Features are Missing. Multi-Objec …
Scalable Exact Inference in Multi-Output Gaussian Processes
| Title | Scalable Exact Inference in Multi-Output Gaussian Processes |
| Authors | Wessel P. Bruinsma, Eric Perim, Will Tebbutt, J. Scott Hosking, Arno Solin, Richard E. Turner |
| Abstract | Multi-output Gaussian processes (MOGPs) leverage the flexibility and interpretability of GPs while capturing structure across outputs, which is desirable, for example, in spatio-temporal modelling. The key problem with MOGPs is the cubic computational scaling in the number of both inputs (e.g., time points or locations), n, and outputs, p. Current methods reduce this to O(n^3 m^3), where m < p is the desired degrees of freedom. This computational cost, however, is still prohibitive in many applications. To address this limitation, we present the Orthogonal Linear Mixing Model (OLMM), an MOGP in which exact inference scales linearly in m: O(n^3 m). This advance opens up a wide range of real-world tasks and can be combined with existing GP approximations in a plug-and-play way as demonstrated in the paper. Additionally, the paper organises the existing disparate literature on MOGP models into a simple taxonomy called the Mixing Model Hierarchy (MMH). |
| Tasks | Gaussian Processes |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06287v1 |
| https://arxiv.org/pdf/1911.06287v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-exact-inference-in-multi-output |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Routing a Heterogeneous Fleet of Vehicles
| Title | Deep Reinforcement Learning for Routing a Heterogeneous Fleet of Vehicles |
| Authors | Jose Manuel Vera, Andres G. Abad |
| Abstract | Motivated by the promising advances of deep-reinforcement learning (DRL) applied to cooperative multi-agent systems we propose a model and learning procedure to solve the Capacitated Multi-Vehicle Routing Problem (CMVRP) with fixed fleet size. Our learning procedure follows a centralized-training and decentralized-execution paradigm. We empirically test our model and showed its capability for producing near-optimal solutions through cooperative actions. In large instances, our model generates better solutions than other commonly used heuristics. Additionally, our model can solve arbitrary instances of the CMVRP without requiring re-training. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03341v1 |
| https://arxiv.org/pdf/1912.03341v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-routing-a |
| Repo | |
| Framework | |
Day-Ahead Hourly Forecasting of Power Generation from Photovoltaic Plants
| Title | Day-Ahead Hourly Forecasting of Power Generation from Photovoltaic Plants |
| Authors | Lorenzo Gigoni, Alessandro Betti, Emanuele Crisostomi, Alessandro Franco, Mauro Tucci, Fabrizio Bizzarri, Debora Mucci |
| Abstract | The ability to accurately forecast power generation from renewable sources is nowadays recognised as a fundamental skill to improve the operation of power systems. Despite the general interest of the power community in this topic, it is not always simple to compare different forecasting methodologies, and infer the impact of single components in providing accurate predictions. In this paper we extensively compare simple forecasting methodologies with more sophisticated ones over 32 photovoltaic plants of different size and technology over a whole year. Also, we try to evaluate the impact of weather conditions and weather forecasts on the prediction of PV power generation. |
| Tasks | |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1903.06800v1 |
| http://arxiv.org/pdf/1903.06800v1.pdf | |
| PWC | https://paperswithcode.com/paper/day-ahead-hourly-forecasting-of-power |
| Repo | |
| Framework | |
High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes
| Title | High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes |
| Authors | David Salinas, Michael Bohlke-Schneider, Laurent Callot, Roberto Medico, Jan Gasthaus |
| Abstract | Predicting the dependencies between observations from multiple time series is critical for applications such as anomaly detection, financial risk management, causal analysis, or demand forecasting. However, the computational and numerical difficulties of estimating time-varying and high-dimensional covariance matrices often limits existing methods to handling at most a few hundred dimensions or requires making strong assumptions on the dependence between series. We propose to combine an RNN-based time series model with a Gaussian copula process output model with a low-rank covariance structure to reduce the computational complexity and handle non-Gaussian marginal distributions. This permits to drastically reduce the number of parameters and consequently allows the modeling of time-varying correlations of thousands of time series. We show on several real-world datasets that our method provides significant accuracy improvements over state-of-the-art baselines and perform an ablation study analyzing the contributions of the different components of our model. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.03002v2 |
| https://arxiv.org/pdf/1910.03002v2.pdf | |
| PWC | https://paperswithcode.com/paper/high-dimensional-multivariate-forecasting |
| Repo | |
| Framework | |
Robust Prediction when Features are Missing
| Title | Robust Prediction when Features are Missing |
| Authors | Xiuming Liu, Dave Zachariah, Petre Stoica |
| Abstract | Predictors are learned using past training data containing features which may be unavailable at the time of prediction. We develop an prediction approach that is robust against unobserved outliers of the missing features, based on the optimality properties of a predictor which has access to these features. The robustness properties of the approach are demonstrated in real and synthetic data. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07226v2 |
| https://arxiv.org/pdf/1912.07226v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-prediction-when-features-are-missing |
| Repo | |
| Framework | |
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
| Title | Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification |
| Authors | Weitao Feng, Zhihao Hu, Wei Wu, Junjie Yan, Wanli Ouyang |
| Abstract | In this paper, we propose a unified Multi-Object Tracking (MOT) framework learning to make full use of long term and short term cues for handling complex cases in MOT scenes. Besides, for better association, we propose switcher-aware classification (SAC), which takes the potential identity-switch causer (switcher) into consideration. Specifically, the proposed framework includes a Single Object Tracking (SOT) sub-net to capture short term cues, a re-identification (ReID) sub-net to extract long term cues and a switcher-aware classifier to make matching decisions using extracted features from the main target and the switcher. Short term cues help to find false negatives, while long term cues avoid critical mistakes when occlusion happens, and the SAC learns to combine multiple cues in an effective way and improves robustness. The method is evaluated on the challenging MOT benchmarks and achieves the state-of-the-art results. |
| Tasks | Multi-Object Tracking, Object Tracking |
| Published | 2019-01-18 |
| URL | http://arxiv.org/abs/1901.06129v1 |
| http://arxiv.org/pdf/1901.06129v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-object-tracking-with-multiple-cues-and |
| Repo | |
| Framework | |
AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection
| Title | AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection |
| Authors | Yiping Tang, Chuang Niu, Minghao Dong, Shenghan Ren, Jimin Liang |
| Abstract | Temporal action detection is a fundamental yet challenging task in video understanding. Many of the state-of-the-art methods predict the boundaries of action instances based on predetermined anchors akin to the two-dimensional object detection detectors. However, it is hard to detect all the action instances with predetermined temporal scales because the durations of instances in untrimmed videos can vary from few seconds to several minutes. In this paper, we propose a novel action detection architecture named anchor-free one-stage temporal action detector (AFO-TAD). AFO-TAD achieves better performance for detecting action instances with arbitrary lengths and high temporal resolution, which can be attributed to two aspects. First, we design a receptive field adaption module which dynamically adjusts the receptive field for precise action detection. Second, AFO-TAD directly predicts the categories and boundaries at every temporal locations without predetermined anchors. Extensive experiments show that AFO-TAD improves the state-of-the-art performance on THUMOS’14. |
| Tasks | Action Detection, Object Detection, Video Understanding |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08250v1 |
| https://arxiv.org/pdf/1910.08250v1.pdf | |
| PWC | https://paperswithcode.com/paper/afo-tad-anchor-free-one-stage-detector-for |
| Repo | |
| Framework | |
Optimising energy and overhead for large parameter space simulations
| Title | Optimising energy and overhead for large parameter space simulations |
| Authors | Alexander J. M. Kell, Matthew Forshaw, A. Stephen McGough |
| Abstract | Many systems require optimisation over multiple objectives, where objectives are characteristics of the system such as energy consumed or increase in time to perform the work. Optimisation is performed by selecting the best' set of input parameters to elicit the desired objectives. However, the parameter search space can often be far larger than can be searched in a reasonable time. Additionally, the objectives are often mutually exclusive -- leading to a decision being made as to which objective is more important or optimising over a combination of the objectives. This work is an application of a Genetic Algorithm to identify the Pareto frontier for finding the optimal parameter sets for all combinations of objectives. A Pareto frontier can be used to identify the sets of optimal parameters for which each is the best’ for a given combination of objectives – thus allowing decisions to be made with full knowledge. We demonstrate this approach for the HTC-Sim simulation system in the case where a Reinforcement Learning scheduler is tuned for the two objectives of energy consumption and task overhead. Demonstrating that this approach can reduce the energy consumed by ~36% over previously published work without significantly increasing the overhead. |
| Tasks | |
| Published | 2019-10-06 |
| URL | https://arxiv.org/abs/1910.02516v1 |
| https://arxiv.org/pdf/1910.02516v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimising-energy-and-overhead-for-large |
| Repo | |
| Framework | |
The Limitations of Adversarial Training and the Blind-Spot Attack
| Title | The Limitations of Adversarial Training and the Blind-Spot Attack |
| Authors | Huan Zhang, Hongge Chen, Zhao Song, Duane Boning, Inderjit S. Dhillon, Cho-Jui Hsieh |
| Abstract | The adversarial training procedure proposed by Madry et al. (2018) is one of the most effective methods to defend against adversarial examples in deep neural networks (DNNs). In our paper, we shed some lights on the practicality and the hardness of adversarial training by showing that the effectiveness (robustness on test set) of adversarial training has a strong correlation with the distance between a test point and the manifold of training data embedded by the network. Test examples that are relatively far away from this manifold are more likely to be vulnerable to adversarial attacks. Consequentially, an adversarial training based defense is susceptible to a new class of attacks, the “blind-spot attack”, where the input images reside in “blind-spots” (low density regions) of the empirical distribution of training data but is still on the ground-truth data manifold. For MNIST, we found that these blind-spots can be easily found by simply scaling and shifting image pixel values. Most importantly, for large datasets with high dimensional and complex data manifold (CIFAR, ImageNet, etc), the existence of blind-spots in adversarial training makes defending on any valid test examples difficult due to the curse of dimensionality and the scarcity of training data. Additionally, we find that blind-spots also exist on provable defenses including (Wong & Kolter, 2018) and (Sinha et al., 2018) because these trainable robustness certificates can only be practically optimized on a limited set of training data. |
| Tasks | |
| Published | 2019-01-15 |
| URL | http://arxiv.org/abs/1901.04684v1 |
| http://arxiv.org/pdf/1901.04684v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-limitations-of-adversarial-training-and |
| Repo | |
| Framework | |
Deep Generative Models: Deterministic Prediction with an Application in Inverse Rendering
| Title | Deep Generative Models: Deterministic Prediction with an Application in Inverse Rendering |
| Authors | Shima Kamyab, Rasool Sabzi, Zohreh Azimifar |
| Abstract | Deep generative models are stochastic neural networks capable of learning the distribution of data so as to generate new samples. Conditional Variational Autoencoder (CVAE) is a powerful deep generative model aiming at maximizing the lower bound of training data log-likelihood. In the CVAE structure, there is appropriate regularizer, which makes it applicable for suitably constraining the solution space in solving ill-posed problems and providing high generalization power. Considering the stochastic prediction characteristic in CVAE, depending on the problem at hand, it is desirable to be able to control the uncertainty in CVAE predictions. Therefore, in this paper we analyze the impact of CVAE’s condition on the diversity of solutions given by our designed CVAE in 3D shape inverse rendering as a prediction problem. The experimental results using Modelnet10 and Shapenet datasets show the appropriate performance of our designed CVAE and verify the hypothesis: \emph{“The more informative the conditions in terms of object pose are, the less diverse the CVAE predictions are}". |
| Tasks | |
| Published | 2019-03-11 |
| URL | http://arxiv.org/abs/1903.04144v1 |
| http://arxiv.org/pdf/1903.04144v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-generative-models-deterministic |
| Repo | |
| Framework | |
Learning Restricted Regular Expressions with Interleaving
| Title | Learning Restricted Regular Expressions with Interleaving |
| Authors | Chunmei Dong, Yeting Li, Haiming Chen |
| Abstract | The advantages for the presence of an XML schema for XML documents are numerous. However, many XML documents in practice are not accompanied by a schema or by a valid schema. Relax NG is a popular and powerful schema language, which supports the unconstrained interleaving operator. Focusing on the inference of Relax NG, we propose a new subclass of regular expressions with interleaving and design a polynomial inference algorithm. Then we conducted a series of experiments based on large-scale real data and on three XML data corpora, and experimental results show that our subclass has a better practicality than previous ones, and the regular expressions inferred by our algorithm are more precise. |
| Tasks | |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1904.13164v1 |
| http://arxiv.org/pdf/1904.13164v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-restricted-regular-expressions-with |
| Repo | |
| Framework | |
Actionable Interpretability through Optimizable Counterfactual Explanations for Tree Ensembles
| Title | Actionable Interpretability through Optimizable Counterfactual Explanations for Tree Ensembles |
| Authors | Ana Lucic, Harrie Oosterhuis, Hinda Haned, Maarten de Rijke |
| Abstract | Counterfactual explanations help users understand why machine learned models make certain decisions, and more specifically, how these decisions can be changed. In this work, we frame the problem of finding counterfactual explanations – the minimal perturbation to an input such that the prediction changes – as an optimization task. Previously, optimization techniques for generating counterfactual examples could only be applied to differentiable models, or alternatively via query access to the model by estimating gradients from randomly sampled perturbations. In order to accommodate non-differentiable models such as tree ensembles, we propose using probabilistic model approximations in the optimization framework. We introduce a novel approximation technique that is effective for finding counterfactual explanations while also closely approximating the original model. Our results show that our method is able to produce counterfactual examples that are closer to the original instance in terms of Euclidean, Cosine, and Manhattan distance compared to other methods specifically designed for tree ensembles. |
| Tasks | |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12199v1 |
| https://arxiv.org/pdf/1911.12199v1.pdf | |
| PWC | https://paperswithcode.com/paper/actionable-interpretability-through |
| Repo | |
| Framework | |
Analysis of Gene Interaction Graphs as Prior Knowledge for Machine Learning Models
| Title | Analysis of Gene Interaction Graphs as Prior Knowledge for Machine Learning Models |
| Authors | Paul Bertin, Mohammad Hashir, Martin Weiss, Vincent Frappier, Theodore J. Perkins, Geneviève Boucher, Joseph Paul Cohen |
| Abstract | Gene interaction graphs aim to capture various relationships between genes and can represent decades of biology research. When trying to make predictions from genomic data, those graphs could be used to overcome the curse of dimensionality by making machine learning models sparser and more consistent with biological common knowledge. In this work, we focus on assessing how well those graphs capture dependencies seen in gene expression data to evaluate the adequacy of the prior knowledge provided by those graphs. We propose a condition graphs should satisfy to provide good prior knowledge and test it using `Single Gene Inference’ tasks. We also compare with randomly generated graphs, aiming to measure the true benefit of using biologically relevant graphs in this context, and validate our findings with five clinical tasks. We find some graphs capture relevant dependencies for most genes while being very sparse. Our analysis with random graphs finds that dependencies can be captured almost as well at random which suggests that, in terms of gene expression levels, the relevant information about the state of the cell is spread across many genes. | |
| Tasks | |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02295v2 |
| https://arxiv.org/pdf/1905.02295v2.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-gene-interaction-graphs-for |
| Repo | |
| Framework | |
L3DOC: Lifelong 3D Object Classification
| Title | L3DOC: Lifelong 3D Object Classification |
| Authors | Yuyang Liu, Yang Cong, Gan Sun |
| Abstract | 3D object classification has been widely-applied into both academic and industrial scenarios. However, most state-of-the-art algorithms are facing with a fixed 3D object classification task set, which cannot well tackle the new coming data with incremental tasks as human ourselves. Meanwhile, the performance of most state-of-the-art lifelong learning models can be deteriorated easily on previously learned classification tasks, due to the existing of unordered, large-scale, and irregular 3D geometry data. To address this challenge, in this paper, we propose a Lifelong 3D Object Classification (i.e., L3DOC) framewor, which can consecutively learn new 3D object classification tasks via imitating ‘human learning’. Specifically, the core idea of our proposed L3DOC model is to factorize PointNet in a perspective of lifelong learning, while capturing and storing the shared point-knowledge in a perspective of layer-wise tensor factorization architecture. To further transfer the task-specific knowledge from previous tasks to the new coming classification task, a memory attention mechanism is proposed to connect the current task with relevant previously tasks, which can effectively prevent catastrophic forgetting via soft-transferring previous knowledge. To our best knowledge, this is the first work about using lifelong learning to handle 3D object classification task without model fine-tuning or retraining. Furthermore, our L3DOC model can also be extended to other backbone network (e.g., PointNet++). To the end, comparisons on several point cloud datasets validate that our L3DOC model can reduce averaged 1.68~3.36 times parameters for the overall model, without sacrificing classification accuracy of each task. |
| Tasks | 3D Object Classification, 3D Object Recognition, Object Classification, Object Recognition |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06135v2 |
| https://arxiv.org/pdf/1912.06135v2.pdf | |
| PWC | https://paperswithcode.com/paper/l3dor-lifelong-3d-object-recognition |
| Repo | |
| Framework | |
Graph-Structured Visual Imitation
| Title | Graph-Structured Visual Imitation |
| Authors | Maximilian Sieb, Zhou Xian, Audrey Huang, Oliver Kroemer, Katerina Fragkiadaki |
| Abstract | We cast visual imitation as a visual correspondence problem. Our robotic agent is rewarded when its actions result in better matching of relative spatial configurations for corresponding visual entities detected in its workspace and teacher’s demonstration. We build upon recent advances in Computer Vision,such as human finger keypoint detectors, object detectors trained on-the-fly with synthetic augmentations, and point detectors supervised by viewpoint changes and learn multiple visual entity detectors for each demonstration without human annotations or robot interactions. We empirically show the proposed factorized visual representations of entities and their spatial arrangements drive successful imitation of a variety of manipulation skills within minutes, using a single demonstration and without any environment instrumentation. It is robust to background clutter and can effectively generalize across environment variations between demonstrator and imitator, greatly outperforming unstructured non-factorized full-frame CNN encodings of previous works. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05518v2 |
| https://arxiv.org/pdf/1907.05518v2.pdf | |
| PWC | https://paperswithcode.com/paper/graph-structured-visual-imitation |
| Repo | |
| Framework | |
