Paper Group ANR 61
Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning. Domain Adaptation for Enterprise Email Search. Just-Enough Interaction Approach to Knee MRI Segmentation: Data from the Osteoarthritis Initiative. A survey of OpenRefine reconciliation services. Extended probabilistic Rand index and the adjustable moving …
Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning
| Title | Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning |
| Authors | Daniel Kuhn, Peyman Mohajerin Esfahani, Viet Anh Nguyen, Soroosh Shafieezadeh-Abadeh |
| Abstract | Many decision problems in science, engineering and economics are affected by uncertain parameters whose distribution is only indirectly observable through samples. The goal of data-driven decision-making is to learn a decision from finitely many training samples that will perform well on unseen test samples. This learning task is difficult even if all training and test samples are drawn from the same distribution—especially if the dimension of the uncertainty is large relative to the training sample size. Wasserstein distributionally robust optimization seeks data-driven decisions that perform well under the most adverse distribution within a certain Wasserstein distance from a nominal distribution constructed from the training samples. In this tutorial we will argue that this approach has many conceptual and computational benefits. Most prominently, the optimal decisions can often be computed by solving tractable convex optimization problems, and they enjoy rigorous out-of-sample and asymptotic consistency guarantees. We will also show that Wasserstein distributionally robust optimization has interesting ramifications for statistical learning and motivates new approaches for fundamental learning tasks such as classification, regression, maximum likelihood estimation or minimum mean square error estimation, among others. |
| Tasks | Decision Making |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08729v1 |
| https://arxiv.org/pdf/1908.08729v1.pdf | |
| PWC | https://paperswithcode.com/paper/wasserstein-distributionally-robust |
| Repo | |
| Framework | |
Domain Adaptation for Enterprise Email Search
| Title | Domain Adaptation for Enterprise Email Search |
| Authors | Brandon Tran, Maryam Karimzadehgan, Rama Kumar Pasumarthi, Michael Bendersky, Donald Metzler |
| Abstract | In the enterprise email search setting, the same search engine often powers multiple enterprises from various industries: technology, education, manufacturing, etc. However, using the same global ranking model across different enterprises may result in suboptimal search quality, due to the corpora differences and distinct information needs. On the other hand, training an individual ranking model for each enterprise may be infeasible, especially for smaller institutions with limited data. To address this data challenge, in this paper we propose a domain adaptation approach that fine-tunes the global model to each individual enterprise. In particular, we propose a novel application of the Maximum Mean Discrepancy (MMD) approach to information retrieval, which attempts to bridge the gap between the global data distribution and the data distribution for a given individual enterprise. We conduct a comprehensive set of experiments on a large-scale email search engine, and demonstrate that the MMD approach consistently improves the search quality for multiple individual domains, both in comparison to the global ranking model, as well as several competitive domain adaptation baselines including adversarial learning methods. |
| Tasks | Domain Adaptation, Information Retrieval |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.07897v1 |
| https://arxiv.org/pdf/1906.07897v1.pdf | |
| PWC | https://paperswithcode.com/paper/domain-adaptation-for-enterprise-email-search |
| Repo | |
| Framework | |
Just-Enough Interaction Approach to Knee MRI Segmentation: Data from the Osteoarthritis Initiative
| Title | Just-Enough Interaction Approach to Knee MRI Segmentation: Data from the Osteoarthritis Initiative |
| Authors | Satyananda Kashyap, Honghai Zhang, Milan Sonka |
| Abstract | State-of-the-art automated segmentation algorithms are not 100% accurate especially when segmenting difficult to interpret datasets like those with severe osteoarthritis (OA). We present a novel interactive method called just-enough interaction (JEI), which adds a fast correction step to the automated layered optimal graph segmentation of multiple objects and surfaces (LOGISMOS). After LOGISMOS segmentation in knee MRI, the JEI user interaction does not modify boundary surfaces of the bones and cartilages directly. Local costs of underlying graph nodes are modified instead and the graph is re-optimized, providing globally optimal corrected results. Significant performance improvement ($p \ll 0.001$) was observed when comparing JEI-corrected results to the automated. The algorithm was extended from 3D JEI to longitudinal multi-3D (4D) JEI allowing simultaneous visualization and interaction of multiple-time points of the same patient. |
| Tasks | |
| Published | 2019-03-10 |
| URL | http://arxiv.org/abs/1903.04027v1 |
| http://arxiv.org/pdf/1903.04027v1.pdf | |
| PWC | https://paperswithcode.com/paper/just-enough-interaction-approach-to-knee-mri |
| Repo | |
| Framework | |
A survey of OpenRefine reconciliation services
| Title | A survey of OpenRefine reconciliation services |
| Authors | Antonin Delpeuch |
| Abstract | We review the services implementing the OpenRefine reconciliation API, comparing their design to the state of the art in record linkage. Due to the design of the API, the matching scores returned by the services are of little help to guide matching decisions. This suggests possible improvements to the specifications of the API, which could improve user workflows by giving more control over the scoring mechanism to the client. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08092v2 |
| https://arxiv.org/pdf/1906.08092v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-openrefine-reconciliation |
| Repo | |
| Framework | |
Extended probabilistic Rand index and the adjustable moving window-based pixel-pair sampling method
| Title | Extended probabilistic Rand index and the adjustable moving window-based pixel-pair sampling method |
| Authors | Hisashi Shimodaira |
| Abstract | The probabilistic Rand (PR) index has the following three problems: It lacks variations in its value over images; the normalized probabilistic Rand (NPR) index to address this is theoretically unclear, and the sampling method of pixel-pairs was not proposed concretely. In this paper, we propose methods for solving these problems. First, we propose extended probabilistic Rand (EPR) index that considers not only similarity but also dissimilarity between segmentations. The EPR index provides twice as wide effective range as the PR index does. Second, we propose an adjustable moving window-based pixel-pair sampling (AWPS) method in which each pixel-pair is sampled adjustably by considering granularities of ground truth segmentations. Results of experiments show that the proposed methods work effectively and efficiently. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.07893v1 |
| https://arxiv.org/pdf/1906.07893v1.pdf | |
| PWC | https://paperswithcode.com/paper/extended-probabilistic-rand-index-and-the |
| Repo | |
| Framework | |
Prediction of Progression to Alzheimer’s disease with Deep InfoMax
| Title | Prediction of Progression to Alzheimer’s disease with Deep InfoMax |
| Authors | Alex Fedorov, R Devon Hjelm, Anees Abrol, Zening Fu, Yuhui Du, Sergey Plis, Vince D. Calhoun |
| Abstract | Arguably, unsupervised learning plays a crucial role in the majority of algorithms for processing brain imaging. A recently introduced unsupervised approach Deep InfoMax (DIM) is a promising tool for exploring brain structure in a flexible non-linear way. In this paper, we investigate the use of variants of DIM in a setting of progression to Alzheimer’s disease in comparison with supervised AlexNet and ResNet inspired convolutional neural networks. As a benchmark, we use a classification task between four groups: patients with stable, and progressive mild cognitive impairment (MCI), with Alzheimer’s disease, and healthy controls. Our dataset is comprised of 828 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Our experiments highlight encouraging evidence of the high potential utility of DIM in future neuroimaging studies. |
| Tasks | |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.10931v3 |
| http://arxiv.org/pdf/1904.10931v3.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-of-progression-to-alzheimers |
| Repo | |
| Framework | |
Provably Efficient Reinforcement Learning with Aggregated States
| Title | Provably Efficient Reinforcement Learning with Aggregated States |
| Authors | Shi Dong, Benjamin Van Roy, Zhengyuan Zhou |
| Abstract | We establish that an optimistic variant of Q-learning applied to a fixed-horizon episodic Markov decision process with an aggregated state representation incurs regret $\tilde{\mathcal{O}}(\sqrt{H^5 M K} + \epsilon HK)$, where $H$ is the horizon, $M$ is the number of aggregate states, $K$ is the number of episodes, and $\epsilon$ is the largest difference between any pair of optimal state-action values associated with a common aggregate state. Notably, this regret bound does not depend on the number of states or actions and indicates that asymptotic per-period regret is no greater than $\epsilon$, independent of horizon. To our knowledge, this is the first such result that applies to reinforcement learning with nontrivial value function approximation without any restrictions on transition probabilities. |
| Tasks | Q-Learning |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06366v2 |
| https://arxiv.org/pdf/1912.06366v2.pdf | |
| PWC | https://paperswithcode.com/paper/provably-efficient-reinforcement-learning-1 |
| Repo | |
| Framework | |
A Decoupled 3D Facial Shape Model by Adversarial Training
| Title | A Decoupled 3D Facial Shape Model by Adversarial Training |
| Authors | Victoria Fernandez Abrevaya, Adnane Boukhayma, Stefanie Wuhrer, Edmond Boyer |
| Abstract | Data-driven generative 3D face models are used to compactly encode facial shape data into meaningful parametric representations. A desirable property of these models is their ability to effectively decouple natural sources of variation, in particular identity and expression. While factorized representations have been proposed for that purpose, they are still limited in the variability they can capture and may present modeling artifacts when applied to tasks such as expression transfer. In this work, we explore a new direction with Generative Adversarial Networks and show that they contribute to better face modeling performances, especially in decoupling natural factors, while also achieving more diverse samples. To train the model we introduce a novel architecture that combines a 3D generator with a 2D discriminator that leverages conventional CNNs, where the two components are bridged by a geometry mapping layer. We further present a training scheme, based on auxiliary classifiers, to explicitly disentangle identity and expression attributes. Through quantitative and qualitative results on standard face datasets, we illustrate the benefits of our model and demonstrate that it outperforms competing state of the art methods in terms of decoupling and diversity. |
| Tasks | |
| Published | 2019-02-10 |
| URL | https://arxiv.org/abs/1902.03619v3 |
| https://arxiv.org/pdf/1902.03619v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-generative-3d-facial-model-by-adversarial |
| Repo | |
| Framework | |
Learning-Based Cost Functions for 3D and 4D Multi-Surface Multi-Object Segmentation of Knee MRI: Data from the Osteoarthritis Initiative
| Title | Learning-Based Cost Functions for 3D and 4D Multi-Surface Multi-Object Segmentation of Knee MRI: Data from the Osteoarthritis Initiative |
| Authors | Satyananda Kashyap, Honghai Zhang, Karan Rao, Milan Sonka |
| Abstract | A fully automated knee MRI segmentation method to study osteoarthritis (OA) was developed using a novel hierarchical set of random forests (RF) classifiers to learn the appearance of cartilage regions and their boundaries. A neighborhood approximation forest is used first to provide contextual feature to the second-level RF classifier that also considers local features and produces location-specific costs for the layered optimal graph image segmentation of multiple objects and surfaces (LOGISMOS) framework. Double echo steady state (DESS) MRIs used in this work originated from the Osteoarthritis Initiative (OAI) study. Trained on 34 MRIs with varying degrees of OA, the performance of the learning-based method tested on 108 MRIs showed a significant reduction in segmentation errors (\emph{p}$<$0.05) compared with the conventional gradient-based and single-stage RF-learned costs. The 3D LOGISMOS was extended to longitudinal-3D (4D) to simultaneously segment multiple follow-up visits of the same patient. As such, data from all time-points of the temporal sequence contribute information to a single optimal solution that utilizes both spatial 3D and temporal contexts. 4D LOGISMOS validation on 108 MRIs from baseline and 12 month follow-up scans of 54 patients showed a significant reduction in segmentation errors (\emph{p}$<$0.01) compared to 3D. Finally, the potential of 4D LOGISMOS was further explored on the same 54 patients using 5 annual follow-up scans demonstrating a significant improvement of measuring cartilage thickness (\emph{p}$<$0.01) compared to the sequential 3D approach. |
| Tasks | Semantic Segmentation |
| Published | 2019-03-10 |
| URL | http://arxiv.org/abs/1903.03927v1 |
| http://arxiv.org/pdf/1903.03927v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-based-cost-functions-for-3d-and-4d |
| Repo | |
| Framework | |
EasiCS: the objective and fine-grained classification method of cervical spondylosis dysfunction
| Title | EasiCS: the objective and fine-grained classification method of cervical spondylosis dysfunction |
| Authors | Nana Wang, Li Cui, Xi Huang, Yingcong Xiang, Jing Xiao, Yi Rao |
| Abstract | The precise diagnosis is of great significance in developing precise treatment plans to restore neck function and reduce the burden posed by the cervical spondylosis (CS). However, the current available neck function assessment method are subjective and coarse-grained. In this paper, based on the relationship among CS, cervical structure, cervical vertebra function, and surface electromyography (sEMG), we seek to develop a clustering algorithms on the sEMG data set collected from the clinical environment and implement the division. We proposed and developed the framework EasiCS, which consists of dimension reduction, clustering algorithm EasiSOM, spectral clustering algorithm EasiSC. The EasiCS outperform the commonly used seven algorithms overall. |
| Tasks | Dimensionality Reduction |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.05987v1 |
| https://arxiv.org/pdf/1905.05987v1.pdf | |
| PWC | https://paperswithcode.com/paper/easics-the-objective-and-fine-grained |
| Repo | |
| Framework | |
Stochastic Gradient Descent on a Tree: an Adaptive and Robust Approach to Stochastic Convex Optimization
| Title | Stochastic Gradient Descent on a Tree: an Adaptive and Robust Approach to Stochastic Convex Optimization |
| Authors | Sattar Vakili, Sudeep Salgia, Qing Zhao |
| Abstract | Online minimization of an unknown convex function over the interval $[0,1]$ is considered under first-order stochastic bandit feedback, which returns a random realization of the gradient of the function at each query point. Without knowing the distribution of the random gradients, a learning algorithm sequentially chooses query points with the objective of minimizing regret defined as the expected cumulative loss of the function values at the query points in excess to the minimum value of the function. An approach based on devising a biased random walk on an infinite-depth binary tree constructed through successive partitioning of the domain of the function is developed. Each move of the random walk is guided by a sequential test based on confidence bounds on the empirical mean constructed using the law of the iterated logarithm. With no tuning parameters, this learning algorithm is robust to heavy-tailed noise with infinite variance and adaptive to unknown function characteristics (specifically, convex, strongly convex, and nonsmooth). It achieves the corresponding optimal regret orders (up to a $\sqrt{\log T}$ or a $\log\log T$ factor) in each class of functions and offers better or matching regret orders than the classical stochastic gradient descent approach which requires the knowledge of the function characteristics for tuning the sequence of step-sizes. |
| Tasks | |
| Published | 2019-01-17 |
| URL | https://arxiv.org/abs/1901.05947v3 |
| https://arxiv.org/pdf/1901.05947v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-random-walk-approach-to-first-order |
| Repo | |
| Framework | |
Feature Extraction and Classification Based on Spatial-Spectral ConvLSTM Neural Network for Hyperspectral Images
| Title | Feature Extraction and Classification Based on Spatial-Spectral ConvLSTM Neural Network for Hyperspectral Images |
| Authors | Wen-Shuai Hu, Heng-Chao Li, Lei Pan, Wei Li, Ran Tao, Qian Du |
| Abstract | In recent years, deep learning has presented a great advance in hyperspectral image (HSI) classification. Particularly, Long Short-Term Memory (LSTM), as a special deep learning structure, has shown great ability in modeling long-term dependencies in the time dimension of video or the spectral dimension of HSIs. However, the loss of spatial information makes it quite difficult to obtain the better performance. In order to address this problem, two novel deep models are proposed to extract more discriminative spatial-spectral features by exploiting the Convolutional LSTM (ConvLSTM) for the first time. By taking the data patch in a local sliding window as the input of each memory cell band by band, the 2-D extended architecture of LSTM is considered for building the spatial-spectral ConvLSTM 2-D Neural Network (SSCL2DNN) to model long-range dependencies in the spectral domain. To take advantage of spatial and spectral information more effectively for extracting a more discriminative spatial-spectral feature representation, the spatial-spectral ConvLSTM 3-D Neural Network (SSCL3DNN) is further proposed by extending LSTM to 3-D version. The experiments, conducted on three commonly used HSI data sets, demonstrate that the proposed deep models have certain competitive advantages and can provide better classification performance than other state-of-the-art approaches. |
| Tasks | |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03577v1 |
| https://arxiv.org/pdf/1905.03577v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503577 |
| Repo | |
| Framework | |
Reducing The Search Space For Hyperparameter Optimization Using Group Sparsity
| Title | Reducing The Search Space For Hyperparameter Optimization Using Group Sparsity |
| Authors | Minsu Cho, Chinmay Hegde |
| Abstract | We propose a new algorithm for hyperparameter selection in machine learning algorithms. The algorithm is a novel modification of Harmonica, a spectral hyperparameter selection approach using sparse recovery methods. In particular, we show that a special encoding of hyperparameter space enables a natural group-sparse recovery formulation, which when coupled with HyperBand (a multi-armed bandit strategy) leads to improvement over existing hyperparameter optimization methods such as Successive Halving and Random Search. Experimental results on image datasets such as CIFAR-10 confirm the benefits of our approach. |
| Tasks | Hyperparameter Optimization |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.11095v1 |
| http://arxiv.org/pdf/1904.11095v1.pdf | |
| PWC | https://paperswithcode.com/paper/reducing-the-search-space-for-hyperparameter |
| Repo | |
| Framework | |
SoilingNet: Soiling Detection on Automotive Surround-View Cameras
| Title | SoilingNet: Soiling Detection on Automotive Surround-View Cameras |
| Authors | Michal Uricar, Pavel Krizek, Ganesh Sistu, Senthil Yogamani |
| Abstract | Cameras are an essential part of sensor suite in autonomous driving. Surround-view cameras are directly exposed to external environment and are vulnerable to get soiled. Cameras have a much higher degradation in performance due to soiling compared to other sensors. Thus it is critical to accurately detect soiling on the cameras, particularly for higher levels of autonomous driving. We created a new dataset having multiple types of soiling namely opaque and transparent. It will be released publicly as part of our WoodScape dataset \cite{yogamani2019woodscape} to encourage further research. We demonstrate high accuracy using a Convolutional Neural Network (CNN) based architecture. We also show that it can be combined with the existing object detection task in a multi-task learning framework. Finally, we make use of Generative Adversarial Networks (GANs) to generate more images for data augmentation and show that it works successfully similar to the style transfer. |
| Tasks | Autonomous Driving, Data Augmentation, Multi-Task Learning, Object Detection, Style Transfer |
| Published | 2019-05-04 |
| URL | https://arxiv.org/abs/1905.01492v2 |
| https://arxiv.org/pdf/1905.01492v2.pdf | |
| PWC | https://paperswithcode.com/paper/soilingnet-soiling-detection-on-automotive |
| Repo | |
| Framework | |
Variational Fusion for Multimodal Sentiment Analysis
| Title | Variational Fusion for Multimodal Sentiment Analysis |
| Authors | Navonil Majumder, Soujanya Poria, Gangeshwar Krishnamurthy, Niyati Chhaya, Rada Mihalcea, Alexander Gelbukh |
| Abstract | Multimodal fusion is considered a key step in multimodal tasks such as sentiment analysis, emotion detection, question answering, and others. Most of the recent work on multimodal fusion does not guarantee the fidelity of the multimodal representation with respect to the unimodal representations. In this paper, we propose a variational autoencoder-based approach for modality fusion that minimizes information loss between unimodal and multimodal representations. We empirically show that this method outperforms the state-of-the-art methods by a significant margin on several popular datasets. |
| Tasks | Multimodal Sentiment Analysis, Question Answering, Sentiment Analysis |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.06008v1 |
| https://arxiv.org/pdf/1908.06008v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-fusion-for-multimodal-sentiment |
| Repo | |
| Framework | |
