Paper Group ANR 1072
Alleviating Label Switching with Optimal Transport. On Estimating Maximum Sum Rate of MIMO Systems with Successive Zero-Forcing Dirty Paper Coding and Per-antenna Power Constraint. Learning Optimal Solutions for Extremely Fast AC Optimal Power Flow. Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations. Weighted P …
Alleviating Label Switching with Optimal Transport
| Title | Alleviating Label Switching with Optimal Transport |
| Authors | Pierre Monteiller, Sebastian Claici, Edward Chien, Farzaneh Mirzazadeh, Justin Solomon, Mikhail Yurochkin |
| Abstract | Label switching is a phenomenon arising in mixture model posterior inference that prevents one from meaningfully assessing posterior statistics using standard Monte Carlo procedures. This issue arises due to invariance of the posterior under actions of a group; for example, permuting the ordering of mixture components has no effect on the likelihood. We propose a resolution to label switching that leverages machinery from optimal transport. Our algorithm efficiently computes posterior statistics in the quotient space of the symmetry group. We give conditions under which there is a meaningful solution to label switching and demonstrate advantages over alternative approaches on simulated and real data. |
| Tasks | |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.02053v2 |
| https://arxiv.org/pdf/1911.02053v2.pdf | |
| PWC | https://paperswithcode.com/paper/alleviating-label-switching-with-optimal |
| Repo | |
| Framework | |
On Estimating Maximum Sum Rate of MIMO Systems with Successive Zero-Forcing Dirty Paper Coding and Per-antenna Power Constraint
| Title | On Estimating Maximum Sum Rate of MIMO Systems with Successive Zero-Forcing Dirty Paper Coding and Per-antenna Power Constraint |
| Authors | Thuy M. Pham, Ronan Farrell, Le-Nam Tran |
| Abstract | In this paper, we study the sum rate maximization for successive zero-forcing dirty-paper coding (SZFDPC) with per-antenna power constraint (PAPC). Although SZFDPC is a low-complexity alternative to the optimal dirty paper coding (DPC), efficient algorithms to compute its sum rate are still open problems especially under practical PAPC. The existing solution to the considered problem is computationally inefficient due to employing high-complexity interior-point method. In this study, we propose two new low-complexity approaches to this important problem. More specifically, the first algorithm achieves the optimal solution by transforming the original problem in the broadcast channel into an equivalent problem in the multiple access channel, then the resulting problem is solved by alternating optimization together with successive convex approximation. We also derive a suboptimal solution based on machine learning to which simple linear regressions are applicable. The approaches are analyzed and validated extensively to demonstrate their superiors over the existing approach. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.08037v1 |
| https://arxiv.org/pdf/1905.08037v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-estimating-maximum-sum-rate-of-mimo |
| Repo | |
| Framework | |
Learning Optimal Solutions for Extremely Fast AC Optimal Power Flow
| Title | Learning Optimal Solutions for Extremely Fast AC Optimal Power Flow |
| Authors | Ahmed Zamzam, Kyri Baker |
| Abstract | In this paper, we develop an online method that leverages machine learning to obtain feasible solutions to the AC optimal power flow (OPF) problem with negligible optimality gaps on extremely fast timescales (e.g., milliseconds), bypassing solving an AC OPF altogether. This is motivated by the fact that as the power grid experiences increasing amounts of renewable power generation, controllable loads, and other inverter-interfaced devices, faster system dynamics and quicker fluctuations in the power supply are likely to occur. Currently, grid operators typically solve AC OPF every 15 minutes to determine economic generator settings while ensuring grid constraints are satisfied. Due to the computational challenges with solving this nonconvex problem, many efforts have focused on linearizing or approximating the problem in order to solve the AC OPF on faster timescales. However, many of these approximations can be fairly poor representations of the actual system state and still require solving an optimization problem, which can be time consuming for large networks. In this work, we leverage historical data to learn a mapping between the system loading and optimal generation values, enabling us to find near-optimal and feasible AC OPF solutions on extremely fast timescales without actually solving an optimization problem. |
| Tasks | |
| Published | 2019-09-27 |
| URL | https://arxiv.org/abs/1910.01213v1 |
| https://arxiv.org/pdf/1910.01213v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-optimal-solutions-for-extremely-fast |
| Repo | |
| Framework | |
Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations
| Title | Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations |
| Authors | Shigang Li, Tal Ben-Nun, Salvatore Di Girolamo, Dan Alistarh, Torsten Hoefler |
| Abstract | Load imbalance pervasively exists in distributed deep learning training systems, either caused by the inherent imbalance in learned tasks or by the system itself. Traditional synchronous Stochastic Gradient Descent (SGD) achieves good accuracy for a wide variety of tasks, but relies on global synchronization to accumulate the gradients at every training step. In this paper, we propose eager-SGD, which relaxes the global synchronization for decentralized accumulation. To implement eager-SGD, we propose to use two partial collectives: solo and majority. With solo allreduce, the faster processes contribute their gradients eagerly without waiting for the slower processes, whereas with majority allreduce, at least half of the participants must contribute gradients before continuing, all without using a central parameter server. We theoretically prove the convergence of the algorithms and describe the partial collectives in detail. Experimental results on load-imbalanced environments (CIFAR-10, ImageNet, and UCF101 datasets) show that eager-SGD achieves 1.27x speedup over the state-of-the-art synchronous SGD, without losing accuracy. |
| Tasks | |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04207v3 |
| https://arxiv.org/pdf/1908.04207v3.pdf | |
| PWC | https://paperswithcode.com/paper/taming-unbalanced-training-workloads-in-deep |
| Repo | |
| Framework | |
Weighted Point Cloud Augmentation for Neural Network Training Data Class-Imbalance
| Title | Weighted Point Cloud Augmentation for Neural Network Training Data Class-Imbalance |
| Authors | David Griffiths, Jan Boehm |
| Abstract | Recent developments in the field of deep learning for 3D data have demonstrated promising potential for end-to-end learning directly from point clouds. However, many real-world point clouds contain a large class im-balance due to the natural class im-balance observed in nature. For example, a 3D scan of an urban environment will consist mostly of road and facade, whereas other objects such as poles will be under-represented. In this paper we address this issue by employing a weighted augmentation to increase classes that contain fewer points. By mitigating the class im-balance present in the data we demonstrate that a standard PointNet++ deep neural network can achieve higher performance at inference on validation data. This was observed as an increase of F1 score of 19% and 25% on two test benchmark datasets; ScanNet and Semantic3D respectively where no class im-balance pre-processing had been performed. Our networks performed better on both highly-represented and under-represented classes, which indicates that the network is learning more robust and meaningful features when the loss function is not overly exposed to only a few classes. |
| Tasks | |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.04094v2 |
| http://arxiv.org/pdf/1904.04094v2.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-point-cloud-augmentation-for-neural |
| Repo | |
| Framework | |
Certifiably Robust Interpretation in Deep Learning
| Title | Certifiably Robust Interpretation in Deep Learning |
| Authors | Alexander Levine, Sahil Singla, Soheil Feizi |
| Abstract | Deep learning interpretation is essential to explain the reasoning behind model predictions. Understanding the robustness of interpretation methods is important especially in sensitive domains such as medical applications since interpretation results are often used in downstream tasks. Although gradient-based saliency maps are popular methods for deep learning interpretation, recent works show that they can be vulnerable to adversarial attacks. In this paper, we address this problem and provide a certifiable defense method for deep learning interpretation. We show that a sparsified version of the popular SmoothGrad method, which computes the average saliency maps over random perturbations of the input, is certifiably robust against adversarial perturbations. We obtain this result by extending recent bounds for certifiably robust smooth classifiers to the interpretation setting. Experiments on ImageNet samples validate our theory. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12105v3 |
| https://arxiv.org/pdf/1905.12105v3.pdf | |
| PWC | https://paperswithcode.com/paper/certifiably-robust-interpretation-in-deep |
| Repo | |
| Framework | |
Deep Learning based Switching Filter for Impulsive Noise Removal in Color Images
| Title | Deep Learning based Switching Filter for Impulsive Noise Removal in Color Images |
| Authors | Krystian Radlak, Lukasz Malinski, Bogdan Smolka |
| Abstract | Noise reduction is one the most important and still active research topic in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we can observe a substantial increase of interest in the application of deep learning algorithms in many computer vision problems due to its impressive capability of automatic feature extraction and classification. These methods have been also successfully applied in image denoising, significantly improving the performance, but most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering design intended for impulsive noise removal using deep learning. In the proposed method, the impulses are identified using a novel deep neural network architecture and noisy pixels are restored using the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in digital color images. |
| Tasks | Denoising, Image Denoising, Object Detection, Scene Understanding |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01721v1 |
| https://arxiv.org/pdf/1912.01721v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-switching-filter-for |
| Repo | |
| Framework | |
Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation
| Title | Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation |
| Authors | Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon |
| Abstract | In this paper, we investigate the problem of unpaired video-to-video translation. Given a video in the source domain, we aim to learn the conditional distribution of the corresponding video in the target domain, without seeing any pairs of corresponding videos. While significant progress has been made in the unpaired translation of images, directly applying these methods to an input video leads to low visual quality due to the additional time dimension. In particular, previous methods suffer from semantic inconsistency (i.e., semantic label flipping) and temporal flickering artifacts. To alleviate these issues, we propose a new framework that is composed of carefully-designed generators and discriminators, coupled with two core objective functions: 1) content preserving loss and 2) temporal consistency loss. Extensive qualitative and quantitative evaluations demonstrate the superior performance of the proposed method against previous approaches. We further apply our framework to a domain adaptation task and achieve favorable results. |
| Tasks | Domain Adaptation |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.07683v1 |
| https://arxiv.org/pdf/1908.07683v1.pdf | |
| PWC | https://paperswithcode.com/paper/190807683 |
| Repo | |
| Framework | |
Structured Prediction Helps 3D Human Motion Modelling
| Title | Structured Prediction Helps 3D Human Motion Modelling |
| Authors | Emre Aksan, Manuel Kaufmann, Otmar Hilliges |
| Abstract | Human motion prediction is a challenging and important task in many computer vision application domains. Existing work only implicitly models the spatial structure of the human skeleton. In this paper, we propose a novel approach that decomposes the prediction into individual joints by means of a structured prediction layer that explicitly models the joint dependencies. This is implemented via a hierarchy of small-sized neural networks connected analogously to the kinematic chains in the human body as well as a joint-wise decomposition in the loss function. The proposed layer is agnostic to the underlying network and can be used with existing architectures for motion modelling. Prior work typically leverages the H3.6M dataset. We show that some state-of-the-art techniques do not perform well when trained and tested on AMASS, a recently released dataset 14 times the size of H3.6M. Our experiments indicate that the proposed layer increases the performance of motion forecasting irrespective of the base network, joint-angle representation, and prediction horizon. We furthermore show that the layer also improves motion predictions qualitatively. We make code and models publicly available at https://ait.ethz.ch/projects/2019/spl. |
| Tasks | Motion Forecasting, motion prediction, Structured Prediction |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.09070v1 |
| https://arxiv.org/pdf/1910.09070v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-prediction-helps-3d-human-motion |
| Repo | |
| Framework | |
Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices
| Title | Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices |
| Authors | Manish Raghavan, Solon Barocas, Jon Kleinberg, Karen Levy |
| Abstract | There has been rapidly growing interest in the use of algorithms in hiring, especially as a means to address or mitigate bias. Yet, to date, little is known about how these methods are used in practice. How are algorithmic assessments built, validated, and examined for bias? In this work, we document and analyze the claims and practices of companies offering algorithms for employment assessment. In particular, we identify vendors of algorithmic pre-employment assessments (i.e., algorithms to screen candidates), document what they have disclosed about their development and validation procedures, and evaluate their practices, focusing particularly on efforts to detect and mitigate bias. Our analysis considers both technical and legal perspectives. Technically, we consider the various choices vendors make regarding data collection and prediction targets, and explore the risks and trade-offs that these choices pose. We also discuss how algorithmic de-biasing techniques interface with, and create challenges for, antidiscrimination law. |
| Tasks | |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09208v3 |
| https://arxiv.org/pdf/1906.09208v3.pdf | |
| PWC | https://paperswithcode.com/paper/mitigating-bias-in-algorithmic-employment |
| Repo | |
| Framework | |
Extreme Learning Tree
| Title | Extreme Learning Tree |
| Authors | Anton Akusok, Emil Eirola, Kaj-Mikael Björk, Amaury Lendasse |
| Abstract | The paper proposes a new variant of a decision tree, called an Extreme Learning Tree. It consists of an extremely random tree with non-linear data transformation, and a linear observer that provides predictions based on the leaf index where the data samples fall. The proposed method outperforms linear models on a benchmark dataset, and may be a building block for a future variant of Random Forest. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09087v1 |
| https://arxiv.org/pdf/1912.09087v1.pdf | |
| PWC | https://paperswithcode.com/paper/extreme-learning-tree |
| Repo | |
| Framework | |
Forest Representation Learning Guided by Margin Distribution
| Title | Forest Representation Learning Guided by Margin Distribution |
| Authors | Shen-Huan Lv, Liang Yang, Zhi-Hua Zhou |
| Abstract | In this paper, we reformulate the forest representation learning approach as an additive model which boosts the augmented feature instead of the prediction. We substantially improve the upper bound of generalization gap from $\mathcal{O}(\sqrt\frac{\ln m}{m})$ to $\mathcal{O}(\frac{\ln m}{m})$, while $\lambda$ - the margin ratio between the margin standard deviation and the margin mean is small enough. This tighter upper bound inspires us to optimize the margin distribution ratio $\lambda$. Therefore, we design the margin distribution reweighting approach (mdDF) to achieve small ratio $\lambda$ by boosting the augmented feature. Experiments and visualizations confirm the effectiveness of the approach in terms of performance and representation learning ability. This study offers a novel understanding of the cascaded deep forest from the margin-theory perspective and further uses the mdDF approach to guide the layer-by-layer forest representation learning. |
| Tasks | Representation Learning |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.03052v1 |
| https://arxiv.org/pdf/1905.03052v1.pdf | |
| PWC | https://paperswithcode.com/paper/forest-representation-learning-guided-by |
| Repo | |
| Framework | |
Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction
| Title | Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction |
| Authors | Ajay Jain, Sergio Casas, Renjie Liao, Yuwen Xiong, Song Feng, Sean Segal, Raquel Urtasun |
| Abstract | Self-driving vehicles plan around both static and dynamic objects, applying predictive models of behavior to estimate future locations of the objects in the environment. However, future behavior is inherently uncertain, and models of motion that produce deterministic outputs are limited to short timescales. Particularly difficult is the prediction of human behavior. In this work, we propose the discrete residual flow network (DRF-Net), a convolutional neural network for human motion prediction that captures the uncertainty inherent in long-range motion forecasting. In particular, our learned network effectively captures multimodal posteriors over future human motion by predicting and updating a discretized distribution over spatial locations. We compare our model against several strong competitors and show that our model outperforms all baselines. |
| Tasks | Motion Forecasting, motion prediction |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.08041v1 |
| https://arxiv.org/pdf/1910.08041v1.pdf | |
| PWC | https://paperswithcode.com/paper/discrete-residual-flow-for-probabilistic |
| Repo | |
| Framework | |
Learning Behavioral Representations from Wearable Sensors
| Title | Learning Behavioral Representations from Wearable Sensors |
| Authors | Nazgol Tavabi, Homa Hosseinmardi, Jennifer L. Villatte, Andrés Abeliuk, Shrikanth Narayanan, Emilio Ferrara, Kristina Lerman |
| Abstract | The ubiquity of mobile devices and wearable sensors offers unprecedented opportunities for continuous collection of multimodal physiological data. Such data enables temporal characterization of an individual’s behaviors, which can provide unique insights into her physical and psychological health. Understanding the relation between different behaviors/activities and personality traits such as stress or work performance can help build strategies to improve the work environment. Especially in workplaces like hospitals where many employees are overworked, having such policies improves the quality of patient care by prioritizing mental and physical health of their caregivers. One challenge in analyzing physiological data is extracting the underlying behavioral states from the temporal sensor signals and interpreting them. Here, we use a non-parametric Bayesian approach, to model multivariate sensor data from multiple people and discover dynamic behaviors they share. We apply this method to data collected from sensors worn by a population of workers in a large urban hospital, capturing their physiological signals, such as breathing and heart rate, and activity patterns. We show that the learned states capture behavioral differences within the population that can help cluster participants into meaningful groups and better predict their cognitive and affective states. This method offers a practical way to learn compact behavioral representations from dynamic multivariate sensor signals and provide insights into the data. |
| Tasks | |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.06959v1 |
| https://arxiv.org/pdf/1911.06959v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-behavioral-representations-from |
| Repo | |
| Framework | |
Multiple Object Tracking with Motion and Appearance Cues
| Title | Multiple Object Tracking with Motion and Appearance Cues |
| Authors | Weiqiang Li, Jiatong Mu, Guizhong Liu |
| Abstract | Due to better video quality and higher frame rate, the performance of multiple object tracking issues has been greatly improved in recent years. However, in real application scenarios, camera motion and noisy per frame detection results degrade the performance of trackers significantly. High-speed and high-quality multiple object trackers are still in urgent demand. In this paper, we propose a new multiple object tracker following the popular tracking-by-detection scheme. We tackle the camera motion problem with an optical flow network and utilize an auxiliary tracker to deal with the missing detection problem. Besides, we use both the appearance and motion information to improve the matching quality. The experimental results on the VisDrone-MOT dataset show that our approach can improve the performance of multiple object tracking significantly while achieving a high efficiency. |
| Tasks | Multiple Object Tracking, Object Tracking, Optical Flow Estimation |
| Published | 2019-09-01 |
| URL | https://arxiv.org/abs/1909.00318v1 |
| https://arxiv.org/pdf/1909.00318v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-object-tracking-with-motion-and |
| Repo | |
| Framework | |
