January 30, 2020

3036 words 15 mins read

Paper Group ANR 202

Tropical Geometry and Piecewise-Linear Approximation of Curves and Surfaces on Weighted Lattices. X-Ray CT Reconstruction of Additively Manufactured Parts using 2.5D Deep Learning MBIR. Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness. Learning Position Evaluation Functions Used in Monte Carlo Softmax …

Tropical Geometry and Piecewise-Linear Approximation of Curves and Surfaces on Weighted Lattices


Title	Tropical Geometry and Piecewise-Linear Approximation of Curves and Surfaces on Weighted Lattices
Authors	Petros Maragos, Emmanouil Theodosis
Abstract	Tropical Geometry and Mathematical Morphology share the same max-plus and min-plus semiring arithmetic and matrix algebra. In this chapter we summarize some of their main ideas and common (geometric and algebraic) structure, generalize and extend both of them using weighted lattices and a max-$\star$ algebra with an arbitrary binary operation $\star$ that distributes over max, and outline applications to geometry, machine learning, and optimization. Further, we generalize tropical geometrical objects using weighted lattices. Finally, we provide the optimal solution of max-$\star$ equations using morphological adjunctions that are projections on weighted lattices, and apply it to optimal piecewise-linear regression for fitting max-$\star$ tropical curves and surfaces to arbitrary data that constitute polygonal or polyhedral shape approximations. This also includes an efficient algorithm for solving the convex regression problem of data fitting with max-affine functions.
Tasks
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03891v1
PDF	https://arxiv.org/pdf/1912.03891v1.pdf
PWC	https://paperswithcode.com/paper/tropical-geometry-and-piecewise-linear
Repo
Framework

X-Ray CT Reconstruction of Additively Manufactured Parts using 2.5D Deep Learning MBIR


Title	X-Ray CT Reconstruction of Additively Manufactured Parts using 2.5D Deep Learning MBIR
Authors	Amirkoushyar Ziabari, Michael Kirka, Vincent Paquit, Philip Bingham, Singanallur Venkatakrishnan
Abstract	In this paper, we present a deep learning algorithm to rapidly obtain high quality CT reconstructions for AM parts. In particular, we propose to use CAD models of the parts that are to be manufactured, introduce typical defects and simulate XCT measurements. These simulated measurements were processed using FBP (computationally simple but result in noisy images) and the MBIR technique. We then train a 2.5D deep convolutional neural network [4], deemed 2.5D Deep Learning MBIR (2.5D DL-MBIR), on these pairs of noisy and high-quality 3D volumes to learn a fast, non-linear mapping function. The 2.5D DL-MBIR reconstructs a 3D volume in a 2.5D scheme where each slice is reconstructed from multiple inputs slices of the FBP input. Given this trained system, we can take a small set of measurements on an actual part, process it using a combination of FBP followed by 2.5D DL-MBIR. Both steps can be rapidly performed using GPUs, resulting in a real-time algorithm that achieves the high-quality of MBIR as fast as standard techniques. Intuitively, since CAD models are typically available for parts to be manufactured, this provides a strong constraint “prior” which can be leveraged to improve the reconstruction.
Tasks
Published	2019-04-02
URL	https://arxiv.org/abs/1904.12585v2
PDF	https://arxiv.org/pdf/1904.12585v2.pdf
PWC	https://paperswithcode.com/paper/190412585
Repo
Framework

Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness


Title	Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness
Authors	Zhu Li, Adrian Perez-Suay, Gustau Camps-Valls, Dino Sejdinovic
Abstract	Current adoption of machine learning in industrial, societal and economical activities has raised concerns about the fairness, equity and ethics of automated decisions. Predictive models are often developed using biased datasets and thus retain or even exacerbate biases in their decisions and recommendations. Removing the sensitive covariates, such as gender or race, is insufficient to remedy this issue since the biases may be retained due to other related covariates. We present a regularization approach to this problem that trades off predictive accuracy of the learned models (with respect to biased labels) for the fairness in terms of statistical parity, i.e. independence of the decisions from the sensitive covariates. In particular, we consider a general framework of regularized empirical risk minimization over reproducing kernel Hilbert spaces and impose an additional regularizer of dependence between predictors and sensitive covariates using kernel-based measures of dependence, namely the Hilbert-Schmidt Independence Criterion (HSIC) and its normalized version. This approach leads to a closed-form solution in the case of squared loss, i.e. ridge regression. Moreover, we show that the dependence regularizer has an interpretation as modifying the corresponding Gaussian process (GP) prior. As a consequence, a GP model with a prior that encourages fairness to sensitive variables can be derived, allowing principled hyperparameter selection and studying of the relative relevance of covariates under fairness constraints. Experimental results in synthetic examples and in real problems of income and crime prediction illustrate the potential of the approach to improve fairness of automated decisions.
Tasks	Crime Prediction, Gaussian Processes
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04322v1
PDF	https://arxiv.org/pdf/1911.04322v1.pdf
PWC	https://paperswithcode.com/paper/kernel-dependence-regularizers-and-gaussian
Repo
Framework

Learning Position Evaluation Functions Used in Monte Carlo Softmax Search


Title	Learning Position Evaluation Functions Used in Monte Carlo Softmax Search
Authors	Harukazu Igarashi, Yuichi Morioka, Kazumasa Yamamoto
Abstract	This paper makes two proposals for Monte Carlo Softmax Search, which is a recently proposed method that is classified as a selective search like the Monte Carlo Tree Search. The first proposal separately defines the node-selection and backup policies to allow researchers to freely design a node-selection policy based on their searching strategies and confirms the principal variation produced by the Monte Carlo Softmax Search to that produced by a minimax search. The second proposal modifies commonly used learning methods for positional evaluation functions. In our new proposals, evaluation functions are learned by Monte Carlo sampling, which is performed with the backup policy in the search tree produced by Monte Carlo Softmax Search. The learning methods under consideration include supervised learning, reinforcement learning, regression learning, and search bootstrapping. Our sampling-based learning not only uses current positions and principal variations but also the internal nodes and important variations of a search tree. This step reduces the number of games necessary for learning. New learning rules are derived for sampling-based learning based on the Monte Carlo Softmax Search and combinations of the modified learning methods are also proposed in this paper.
Tasks
Published	2019-01-30
URL	http://arxiv.org/abs/1901.10706v1
PDF	http://arxiv.org/pdf/1901.10706v1.pdf
PWC	https://paperswithcode.com/paper/learning-position-evaluation-functions-used
Repo
Framework

DSPG: Decentralized Simultaneous Perturbations Gradient Descent Scheme


Title	DSPG: Decentralized Simultaneous Perturbations Gradient Descent Scheme
Authors	Arunselvan Ramaswamy
Abstract	Distributed descent-based methods are an essential toolset to solving optimization problems in multi-agent system scenarios. Here the agents seek to optimize a global objective function through mutual cooperation. Oftentimes, cooperation is achieved over a wireless communication network that is prone to delays and errors. There are many scenarios wherein the objective function is either non-differentiable or merely observable. In this paper, we present a cross-entropy based distributed stochastic approximation algorithm (SA) that finds a minimum of the objective, using only samples. We call this algorithm Decentralized Simultaneous Perturbation Stochastic Gradient, with Constant Sensitivity Parameters (DSPG). This algorithm is a two fold improvement over the classic Simultaneous Perturbation Stochastic Approximations (SPSA) algorithm. Specifically, DSPG allows for (i) the use of old information from other agents and (ii) easy implementation through the use simple hyper-parameter choices. We analyze the biases and variances that arise due to these two allowances. We show that the biases due to communication delays can be countered by a careful choice of algorithm hyper-parameters. The variance of the gradient estimator and its effect on the rate of convergence is studied. We present numerical results supporting our theory. Finally, we discuss an application to the stochastic consensus problem.
Tasks
Published	2019-03-17
URL	https://arxiv.org/abs/1903.07050v2
PDF	https://arxiv.org/pdf/1903.07050v2.pdf
PWC	https://paperswithcode.com/paper/dspg-decentralized-simultaneous-perturbations
Repo
Framework

Protecting the Protected Group: Circumventing Harmful Fairness


Title	Protecting the Protected Group: Circumventing Harmful Fairness
Authors	Omer Ben-Porat, Fedor Sandomirskiy, Moshe Tennenholtz
Abstract	Machine Learning (ML) algorithms shape our lives. Banks use them to determine if we are good borrowers; IT companies delegate them recruitment decisions; police apply ML for crime-prediction, and judges base their verdicts on ML. However, real-world examples show that such automated decisions tend to discriminate against protected groups. This potential discrimination generated a huge hype both in media and in the research community. Quite a few formal notions of fairness were proposed, which take a form of constraints a “fair” algorithm must satisfy. We focus on scenarios where fairness is imposed on a self-interested party (e.g., a bank that maximizes its revenue). We find that the disadvantaged protected group can be worse off after imposing a fairness constraint. We introduce a family of \textit{Welfare-Equalizing} fairness constraints that equalize per-capita welfare of protected groups, and include \textit{Demographic Parity} and \textit{Equal Opportunity} as particular cases. In this family, we characterize conditions under which the fairness constraint helps the disadvantaged group. We also characterize the structure of the optimal \textit{Welfare-Equalizing} classifier for the self-interested party, and provide an algorithm to compute it. Overall, our \textit{Welfare-Equalizing} fairness approach provides a unified framework for discussing fairness in classification in the presence of a self-interested party.
Tasks	Crime Prediction
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10546v2
PDF	https://arxiv.org/pdf/1905.10546v2.pdf
PWC	https://paperswithcode.com/paper/protecting-the-protected-group-circumventing
Repo
Framework

Iris Verification with Convolutional Neural Network and Unit-Circle Layer


Title	Iris Verification with Convolutional Neural Network and Unit-Circle Layer
Authors	Radim Spetlik, Ivan Razumenic
Abstract	We propose a novel convolutional neural network to verify a~match between two normalized images of the human iris. The network is trained end-to-end and validated on three publicly available datasets yielding state-of-the-art results against four baseline methods. The network performs better by a 10% margin to the state-of-the-art method on the CASIA.v4 dataset. In the network, we use a novel Unit-Circle Layer layer which replaces the Gabor-filtering step in a common iris-verification pipeline. We show that the layer improves the performance of the model up to 15% on previously-unseen data.
Tasks
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09472v2
PDF	https://arxiv.org/pdf/1906.09472v2.pdf
PWC	https://paperswithcode.com/paper/iris-verification-with-convolutional-neural
Repo
Framework

Deep Unknown Intent Detection with Margin Loss


Title	Deep Unknown Intent Detection with Margin Loss
Authors	Ting-En Lin, Hua Xu
Abstract	Identifying the unknown (novel) user intents that have never appeared in the training set is a challenging task in the dialogue system. In this paper, we present a two-stage method for detecting unknown intents. We use bidirectional long short-term memory (BiLSTM) network with the margin loss as the feature extractor. With margin loss, we can learn discriminative deep features by forcing the network to maximize inter-class variance and to minimize intra-class variance. Then, we feed the feature vectors to the density-based novelty detection algorithm, local outlier factor (LOF), to detect unknown intents. Experiments on two benchmark datasets show that our method can yield consistent improvements compared with the baseline methods.
Tasks	Intent Detection
Published	2019-06-02
URL	https://arxiv.org/abs/1906.00434v1
PDF	https://arxiv.org/pdf/1906.00434v1.pdf
PWC	https://paperswithcode.com/paper/190600434
Repo
Framework

Nonrigid reconstruction of 3D breast surfaces with a low-cost RGBD camera for surgical planning and aesthetic evaluation


Title	Nonrigid reconstruction of 3D breast surfaces with a low-cost RGBD camera for surgical planning and aesthetic evaluation
Authors	Rene Lacher, Francisco Vasconcelos, Norman Williams, Gerrit Rindermann, John Hipwell, David Hawkes, Danail Stoyanov
Abstract	Accounting for 26% of all new cancer cases worldwide, breast cancer remains the most common form of cancer in women. Although early breast cancer has a favourable long-term prognosis, roughly a third of patients suffer from a suboptimal aesthetic outcome despite breast conserving cancer treatment. Clinical-quality 3D modelling of the breast surface therefore assumes an increasingly important role in advancing treatment planning, prediction and evaluation of breast cosmesis. Yet, existing 3D torso scanners are expensive and either infrastructure-heavy or subject to motion artefacts. In this paper we employ a single consumer-grade RGBD camera with an ICP-based registration approach to jointly align all points from a sequence of depth images non-rigidly. Subtle body deformation due to postural sway and respiration is successfully mitigated leading to a higher geometric accuracy through regularised locally affine transformations. We present results from 6 clinical cases where our method compares well with the gold standard and outperforms a previous approach. We show that our method produces better reconstructions qualitatively by visual assessment and quantitatively by consistently obtaining lower landmark error scores and yielding more accurate breast volume estimates.
Tasks
Published	2019-01-16
URL	http://arxiv.org/abs/1901.05377v1
PDF	http://arxiv.org/pdf/1901.05377v1.pdf
PWC	https://paperswithcode.com/paper/nonrigid-reconstruction-of-3d-breast-surfaces
Repo
Framework

Self-Expressive Subspace Clustering to Recognize Motion Dynamics of a Multi-Joint Coordination for Chronic Ankle Instability


Title	Self-Expressive Subspace Clustering to Recognize Motion Dynamics of a Multi-Joint Coordination for Chronic Ankle Instability
Authors	Shaodi Qian, Sheng-Che Yen, Eric Folmar, Chun-An Chou
Abstract	Ankle sprains and instability are major public health concerns. Up to 70% of individuals do not fully recover from a single ankle sprain and eventually develop chronic ankle instability (CAI). The diagnosis of CAI has been mainly based on self-report rather than objective biomechanical measures. The goal of this study is to quantitatively recognize the motion pattern of a multi-joint coordination using biosensor data from bilateral hip, knee, and ankle joints, and further distinguish between CAI and healthy cohorts. We propose an analytic framework, where a nonlinear subspace clustering method is developed to learn the motion dynamic patterns from an inter-connected network of multiply joints. A support vector machine model is trained with a leave-one-subject-out cross validation to validate the learned measures compared to traditional statistical measures. The computational results showed >70% classification accuracy on average based on the dataset of 48 subjects (25 with CAI and 23 normal controls) examined in our designed experiment. It is found that CAI can be observed from other joints (e.g., hips) significantly, which reflects the fact that there are interactions in the multi-joint coordination system. The developed method presents a potential to support the decisions with motion patterns during diagnosis, treatment, rehabilitation of gait abnormality caused by physical injury (e.g., ankle sprains in this study) or even central nervous system disorders.
Tasks
Published	2019-01-06
URL	https://arxiv.org/abs/1901.01558v3
PDF	https://arxiv.org/pdf/1901.01558v3.pdf
PWC	https://paperswithcode.com/paper/self-expressive-subspace-clustering-to
Repo
Framework

A review of sentiment computation methods with R packages


Title	A review of sentiment computation methods with R packages
Authors	Maurizio Naldi
Abstract	Four packages in R are analyzed to carry out sentiment analysis. All packages allow to define custom dictionaries. Just one - Sentiment R - properly accounts for the presence of negators.
Tasks	Sentiment Analysis
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08319v1
PDF	http://arxiv.org/pdf/1901.08319v1.pdf
PWC	https://paperswithcode.com/paper/a-review-of-sentiment-computation-methods
Repo
Framework

Algorithms and System Architecture for Immediate Personalized News Recommendations


Title	Algorithms and System Architecture for Immediate Personalized News Recommendations
Authors	Takeshi Yoneda, Shunsuke Kozawa, Keisuke Osone, Yukinori Koide, Yosuke Abe, Yoshifumi Seki
Abstract	Personalization plays an important role in many services, just as news does. Many studies have examined news personalization algorithms, but few have considered practical environments. This paper provides algorithms and system architecture for generating immediate personalized news in a practical environment. Immediacy means changes in news trends and user interests are reflected in recommended news lists quickly. Since news trends and user interests rapidly change, immediacy is critical in news personalization applications. We develop algorithms and system architecture to realize immediacy. Our algorithms are based on collaborative filtering of user clusters and evaluate news articles using click-through rate and decay scores based on the time elapsed since the user’s last access. Existing studies have not fully discussed system architecture, so a major contribution of this paper is that we demonstrate a system architecture and realize our algorithms and a configuration example implemented on top of Amazon Web Services. We evaluate the proposed method both offline and online. The offline experiments are conducted through a real-world dataset from a commercial news delivery service, and online experiments are conducted via A/B testing on production environments. We confirm the effectiveness of our proposed method and also that our system architecture can operate in large-scale production environments.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01005v1
PDF	https://arxiv.org/pdf/1909.01005v1.pdf
PWC	https://paperswithcode.com/paper/algorithms-and-system-architecture-for
Repo
Framework

UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation


Title	UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation
Authors	Jogendra Nath Kundu, Nishank Lakkakula, R. Venkatesh Babu
Abstract	Aiming towards human-level generalization, there is a need to explore adaptable representation learning methods with greater transferability. Most existing approaches independently address task-transferability and cross-domain adaptation, resulting in limited generalization. In this paper, we propose UM-Adapt - a unified framework to effectively perform unsupervised domain adaptation for spatially-structured prediction tasks, simultaneously maintaining a balanced performance across individual tasks in a multi-task setting. To realize this, we propose two novel regularization strategies; a) Contour-based content regularization (CCR) and b) exploitation of inter-task coherency using a cross-task distillation module. Furthermore, avoiding a conventional ad-hoc domain discriminator, we re-utilize the cross-task distillation loss as output of an energy function to adversarially minimize the input domain discrepancy. Through extensive experiments, we demonstrate superior generalizability of the learned representations simultaneously for multiple tasks under domain-shifts from synthetic to natural environments. UM-Adapt yields state-of-the-art transfer learning results on ImageNet classification and comparable performance on PASCAL VOC 2007 detection task, even with a smaller backbone-net. Moreover, the resulting semi-supervised framework outperforms the current fully-supervised multi-task learning state-of-the-art on both NYUD and Cityscapes dataset.
Tasks	Domain Adaptation, Multi-Task Learning, Representation Learning, Structured Prediction, Transfer Learning, Unsupervised Domain Adaptation
Published	2019-08-11
URL	https://arxiv.org/abs/1908.03884v3
PDF	https://arxiv.org/pdf/1908.03884v3.pdf
PWC	https://paperswithcode.com/paper/um-adapt-unsupervised-multi-task-adaptation
Repo
Framework

Source Traces for Temporal Difference Learning


Title	Source Traces for Temporal Difference Learning
Authors	Silviu Pitis
Abstract	This paper motivates and develops source traces for temporal difference (TD) learning in the tabular setting. Source traces are like eligibility traces, but model potential histories rather than immediate ones. This allows TD errors to be propagated to potential causal states and leads to faster generalization. Source traces can be thought of as the model-based, backward view of successor representations (SR), and share many of the same benefits. This view, however, suggests several new ideas. First, a TD($\lambda$)-like source learning algorithm is proposed and its convergence is proven. Then, a novel algorithm for learning the source map (or SR matrix) is developed and shown to outperform the previous algorithm. Finally, various approaches to using the source/SR model are explored, and it is shown that source traces can be effectively combined with other model-based methods like Dyna and experience replay.
Tasks
Published	2019-02-08
URL	http://arxiv.org/abs/1902.02907v1
PDF	http://arxiv.org/pdf/1902.02907v1.pdf
PWC	https://paperswithcode.com/paper/source-traces-for-temporal-difference
Repo
Framework

Deep learning research landscape & roadmap in a nutshell: past, present and future – Towards deep cortical learning


Title	Deep learning research landscape & roadmap in a nutshell: past, present and future – Towards deep cortical learning
Authors	Aras R. Dargazany
Abstract	The past, present and future of deep learning is presented in this work. Given this landscape & roadmap, we predict that deep cortical learning will be the convergence of deep learning & cortical learning which builds an artificial cortical column ultimately.
Tasks
Published	2019-07-30
URL	https://arxiv.org/abs/1908.02130v1
PDF	https://arxiv.org/pdf/1908.02130v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-research-landscape-roadmap-in-a
Repo
Framework