Paper Group ANR 1266
Curve Fitting from Probabilistic Emissions and Applications to Dynamic Item Response Theory. From Predictions to Prescriptions in Multistage Optimization Problems. Model-based annotation of coreference. Almawave-SLU: A new dataset for SLU in Italian. Learned Semantic Multi-Sensor Depth Map Fusion. Notes on Margin Training and Margin p-Values for De …
Curve Fitting from Probabilistic Emissions and Applications to Dynamic Item Response Theory
| Title | Curve Fitting from Probabilistic Emissions and Applications to Dynamic Item Response Theory |
| Authors | Ajay Shanker Tripathi, Benjamin W. Domingue |
| Abstract | Item response theory (IRT) models are widely used in psychometrics and educational measurement, being deployed in many high stakes tests such as the GRE aptitude test. IRT has largely focused on estimation of a single latent trait (e.g. ability) that remains static through the collection of item responses. However, in contemporary settings where item responses are being continuously collected, such as Massive Open Online Courses (MOOCs), interest will naturally be on the dynamics of ability, thus complicating usage of traditional IRT models. We propose DynAEsti, an augmentation of the traditional IRT Expectation Maximization algorithm that allows ability to be a continuously varying curve over time. In the process, we develop CurvFiFE, a novel non-parametric continuous-time technique that handles the curve-fitting/regression problem extended to address more general probabilistic emissions (as opposed to simply noisy data points). Furthermore, to accomplish this, we develop a novel technique called grafting, which can successfully approximate distributions represented by graphical models when other popular techniques like Loopy Belief Propogation (LBP) and Variational Inference (VI) fail. The performance of DynAEsti is evaluated through simulation, where we achieve results comparable to the optimal of what is observed in the static ability scenario. Finally, DynAEsti is applied to a longitudinal performance dataset (80-years of competitive golf at the 18-hole Masters Tournament) to demonstrate its ability to recover key properties of human performance and the heterogeneous characteristics of the different holes. Python code for CurvFiFE and DynAEsti is publicly available at github.com/chausies/DynAEstiAndCurvFiFE. This is the full version of our ICDM 2019 paper. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03586v1 |
| https://arxiv.org/pdf/1909.03586v1.pdf | |
| PWC | https://paperswithcode.com/paper/curve-fitting-from-probabilistic-emissions |
| Repo | |
| Framework | |
From Predictions to Prescriptions in Multistage Optimization Problems
| Title | From Predictions to Prescriptions in Multistage Optimization Problems |
| Authors | Dimitris Bertsimas, Christopher McCord |
| Abstract | In this paper, we introduce a framework for solving finite-horizon multistage optimization problems under uncertainty in the presence of auxiliary data. We assume the joint distribution of the uncertain quantities is unknown, but noisy observations, along with observations of auxiliary covariates, are available. We utilize effective predictive methods from machine learning (ML), including $k$-nearest neighbors regression ($k$NN), classification and regression trees (CART), and random forests (RF), to develop specific methods that are applicable to a wide variety of problems. We demonstrate that our solution methods are asymptotically optimal under mild conditions. Additionally, we establish finite sample guarantees for the optimality of our method with $k$NN weight functions. Finally, we demonstrate the practicality of our approach with computational examples. We see a significant decrease in cost by taking into account the auxiliary data in the multistage setting. |
| Tasks | |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.11637v1 |
| http://arxiv.org/pdf/1904.11637v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-predictions-to-prescriptions-in |
| Repo | |
| Framework | |
Model-based annotation of coreference
| Title | Model-based annotation of coreference |
| Authors | Rahul Aralikatte, Anders Søgaard |
| Abstract | Humans do not make inferences over texts, but over models of what texts are about. When annotators are asked to annotate coreferent spans of text, it is therefore a somewhat unnatural task. This paper presents an alternative in which we preprocess documents, linking entities to a knowledge base, and turn the coreference annotation task – in our case limited to pronouns – into an annotation task where annotators are asked to assign pronouns to entities. Model-based annotation is shown to lead to faster annotation and higher inter-annotator agreement, and we argue that it also opens up for an alternative approach to coreference resolution. We present two new coreference benchmark datasets, for English Wikipedia and English teacher-student dialogues, and evaluate state-of-the-art coreference resolvers on them. |
| Tasks | Coreference Resolution |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10724v3 |
| https://arxiv.org/pdf/1906.10724v3.pdf | |
| PWC | https://paperswithcode.com/paper/model-based-annotation-of-coreference |
| Repo | |
| Framework | |
Almawave-SLU: A new dataset for SLU in Italian
| Title | Almawave-SLU: A new dataset for SLU in Italian |
| Authors | Valentina Bellomaria, Giuseppe Castellucci, Andrea Favalli, Raniero Romagnoli |
| Abstract | The widespread use of conversational and question answering systems made it necessary to improve the performances of speaker intent detection and understanding of related semantic slots, i.e., Spoken Language Understanding (SLU). Often, these tasks are approached with supervised learning methods, which needs considerable labeled datasets. This paper presents the first Italian dataset for SLU. It is derived through a semi-automatic procedure and is used as a benchmark of various open source and commercial systems. |
| Tasks | Intent Detection, Question Answering, Spoken Language Understanding |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07526v1 |
| https://arxiv.org/pdf/1907.07526v1.pdf | |
| PWC | https://paperswithcode.com/paper/almawave-slu-a-new-dataset-for-slu-in-italian |
| Repo | |
| Framework | |
Learned Semantic Multi-Sensor Depth Map Fusion
| Title | Learned Semantic Multi-Sensor Depth Map Fusion |
| Authors | Denys Rozumnyi, Ian Cherabier, Marc Pollefeys, Martin R. Oswald |
| Abstract | Volumetric depth map fusion based on truncated signed distance functions has become a standard method and is used in many 3D reconstruction pipelines. In this paper, we are generalizing this classic method in multiple ways: 1) Semantics: Semantic information enriches the scene representation and is incorporated into the fusion process. 2) Multi-Sensor: Depth information can originate from different sensors or algorithms with very different noise and outlier statistics which are considered during data fusion. 3) Scene denoising and completion: Sensors can fail to recover depth for certain materials and light conditions, or data is missing due to occlusions. Our method denoises the geometry, closes holes and computes a watertight surface for every semantic class. 4) Learning: We propose a neural network reconstruction method that unifies all these properties within a single powerful framework. Our method learns sensor or algorithm properties jointly with semantic depth fusion and scene completion and can also be used as an expert system, e.g. to unify the strengths of various photometric stereo algorithms. Our approach is the first to unify all these properties. Experimental evaluations on both synthetic and real data sets demonstrate clear improvements. |
| Tasks | 3D Reconstruction, Denoising |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00703v1 |
| https://arxiv.org/pdf/1909.00703v1.pdf | |
| PWC | https://paperswithcode.com/paper/learned-semantic-multi-sensor-depth-map |
| Repo | |
| Framework | |
Notes on Margin Training and Margin p-Values for Deep Neural Network Classifiers
| Title | Notes on Margin Training and Margin p-Values for Deep Neural Network Classifiers |
| Authors | George Kesidis, David J. Miller, Zhen Xiang |
| Abstract | We provide a new local class-purity theorem for Lipschitz continuous DNN classifiers. In addition, we discuss how to achieve classification margin for training samples. Finally, we describe how to compute margin p-values for test samples. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.08032v2 |
| https://arxiv.org/pdf/1910.08032v2.pdf | |
| PWC | https://paperswithcode.com/paper/notes-on-lipschitz-margin-lipschitz-margin |
| Repo | |
| Framework | |
A Survey on Deep Learning based Brain Computer Interface: Recent Advances and New Frontiers
| Title | A Survey on Deep Learning based Brain Computer Interface: Recent Advances and New Frontiers |
| Authors | Xiang Zhang, Lina Yao, Xianzhi Wang, Jessica Monaghan, David Mcalpine, Yu Zhang |
| Abstract | Brain-Computer Interface (BCI) bridges the human’s neural world and the outer physical world by decoding individuals’ brain signals into commands recognizable by computer devices. Deep learning has lifted the performance of brain-computer interface systems significantly in recent years. In this article, we systematically investigate brain signal types for BCI and related deep learning concepts for brain signal analysis. We then present a comprehensive survey of deep learning techniques used for BCI, by summarizing over 230 contributions most published in the past five years. Finally, we discuss the applied areas, opening challenges, and future directions for deep learning-based BCI. |
| Tasks | |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.04149v4 |
| https://arxiv.org/pdf/1905.04149v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-deep-learning-based-brain |
| Repo | |
| Framework | |
Discrete Laplace Operator Estimation for Dynamic 3D Reconstruction
| Title | Discrete Laplace Operator Estimation for Dynamic 3D Reconstruction |
| Authors | Xiangyu Xu, Enrique Dunn |
| Abstract | We present a general paradigm for dynamic 3D reconstruction from multiple independent and uncontrolled image sources having arbitrary temporal sampling density and distribution. Our graph-theoretic formulation models the Spatio-temporal relationships among our observations in terms of the joint estimation of their 3D geometry and its discrete Laplace operator. Towards this end, we define a tri-convex optimization framework that leverages the geometric properties and dependencies found among a Euclideanshape-space and the discrete Laplace operator describing its local and global topology. We present a reconstructability analysis, experiments on motion capture data and multi-view image datasets, as well as explore applications to geometry-based event segmentation and data association. |
| Tasks | 3D Reconstruction, Motion Capture |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11044v1 |
| https://arxiv.org/pdf/1908.11044v1.pdf | |
| PWC | https://paperswithcode.com/paper/discrete-laplace-operator-estimation-for |
| Repo | |
| Framework | |
Accurate inference of crowdsourcing properties when using efficient allocation strategies
| Title | Accurate inference of crowdsourcing properties when using efficient allocation strategies |
| Authors | Abigail Hotaling, James P. Bagrow |
| Abstract | Allocation strategies improve the efficiency of crowdsourcing by decreasing the work needed to complete individual tasks accurately. However, these algorithms introduce bias by preferentially allocating workers onto easy tasks, leading to sets of completed tasks that are no longer representative of all tasks. This bias challenges inference of problem-wide properties such as typical task difficulty or crowd properties such as worker completion times, important information that goes beyond the crowd responses themselves. Here we study inference about problem properties when using an allocation algorithm to improve crowd efficiency. We introduce Decision-Explicit Probability Sampling (DEPS), a method to perform inference of problem properties while accounting for the potential bias introduced by an allocation strategy. Experiments on real and synthetic crowdsourcing data show that DEPS outperforms baseline inference methods while still leveraging the efficiency gains of the allocation method. The ability to perform accurate inference of general properties when using non-representative data allows crowdsourcers to extract more knowledge out of a given crowdsourced dataset. |
| Tasks | |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.03104v1 |
| http://arxiv.org/pdf/1903.03104v1.pdf | |
| PWC | https://paperswithcode.com/paper/accurate-inference-of-crowdsourcing |
| Repo | |
| Framework | |
Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks
| Title | Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks |
| Authors | Victor Schmidt, Alexandra Luccioni, S. Karthik Mukkavilli, Narmada Balasooriya, Kris Sankaran, Jennifer Chayes, Yoshua Bengio |
| Abstract | We present a project that aims to generate images that depict accurate, vivid, and personalized outcomes of climate change using Cycle-Consistent Adversarial Networks (CycleGANs). By training our CycleGAN model on street-view images of houses before and after extreme weather events (e.g. floods, forest fires, etc.), we learn a mapping that can then be applied to images of locations that have not yet experienced these events. This visual transformation is paired with climate model predictions to assess likelihood and type of climate-related events in the long term (50 years) in order to bring the future closer in the viewers mind. The eventual goal of our project is to enable individuals to make more informed choices about their climate future by creating a more visceral understanding of the effects of climate change, while maintaining scientific credibility by drawing on climate model projections. |
| Tasks | |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.03709v1 |
| https://arxiv.org/pdf/1905.03709v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503709 |
| Repo | |
| Framework | |
DirectPET: Full Size Neural Network PET Reconstruction from Sinogram Data
| Title | DirectPET: Full Size Neural Network PET Reconstruction from Sinogram Data |
| Authors | William Whiteley, Wing K. Luk, Jens Gregor |
| Abstract | Purpose: Neural network image reconstruction directly from measurement data is a relatively new field of research, that until now has been limited to producing small single-slice images (e.g., 1x128x128). This paper proposes a novel and more efficient network design for Positron Emission Tomography called DirectPET which is capable of reconstructing multi-slice image volumes (i.e., 16x400x400) from sinograms. Approach: Large-scale direct neural network reconstruction is accomplished by addressing the associated memory space challenge through the introduction of a specially designed Radon inversion layer. Using patient data, we compare the proposed method to the benchmark Ordered Subsets Expectation Maximization (OSEM) algorithm using signal-to-noise ratio, bias, mean absolute error and structural similarity measures. In addition, line profiles and full-width half-maximum measurements are provided for a sample of lesions. Results: DirectPET is shown capable of producing images that are quantitatively and qualitatively similar to the OSEM target images in a fraction of the time. We also report on an experiment where DirectPET is trained to map low count raw data to normal count target images demonstrating the method’s ability to maintain image quality under a low dose scenario. Conclusion: The ability of DirectPET to quickly reconstruct high-quality, multi-slice image volumes suggests potential clinical viability of the method. However, design parameters and performance boundaries need to be fully established before adoption can be considered. |
| Tasks | 3D Reconstruction, Image Reconstruction |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.07516v4 |
| https://arxiv.org/pdf/1908.07516v4.pdf | |
| PWC | https://paperswithcode.com/paper/190807516 |
| Repo | |
| Framework | |
Jointly Aligning Millions of Images with Deep Penalised Reconstruction Congealing
| Title | Jointly Aligning Millions of Images with Deep Penalised Reconstruction Congealing |
| Authors | Roberto Annunziata, Christos Sagonas, Jacques Cali |
| Abstract | Extrapolating fine-grained pixel-level correspondences in a fully unsupervised manner from a large set of misaligned images can benefit several computer vision and graphics problems, e.g. co-segmentation, super-resolution, image edit propagation, structure-from-motion, and 3D reconstruction. Several joint image alignment and congealing techniques have been proposed to tackle this problem, but robustness to initialisation, ability to scale to large datasets, and alignment accuracy seem to hamper their wide applicability. To overcome these limitations, we propose an unsupervised joint alignment method leveraging a densely fused spatial transformer network to estimate the warping parameters for each image and a low-capacity auto-encoder whose reconstruction error is used as an auxiliary measure of joint alignment. Experimental results on digits from multiple versions of MNIST (i.e., original, perturbed, affNIST and infiMNIST) and faces from LFW, show that our approach is capable of aligning millions of images with high accuracy and robustness to different levels and types of perturbation. Moreover, qualitative and quantitative results suggest that the proposed method outperforms state-of-the-art approaches both in terms of alignment quality and robustness to initialisation. |
| Tasks | 3D Reconstruction, Super-Resolution |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04130v2 |
| https://arxiv.org/pdf/1908.04130v2.pdf | |
| PWC | https://paperswithcode.com/paper/jointly-aligning-millions-of-images-with-deep |
| Repo | |
| Framework | |
Deep, spatially coherent Occupancy Maps based on Radar Measurements
| Title | Deep, spatially coherent Occupancy Maps based on Radar Measurements |
| Authors | Daniel Bauer, Lars Kuhnert, Lutz Eckstein |
| Abstract | One essential step to realize modern driver assistance technology is the accurate knowledge about the location of static objects in the environment. In this work, we use artificial neural networks to predict the occupation state of a whole scene in an end-to-end manner. This stands in contrast to the traditional approach of accumulating each detection’s influence on the occupancy state and allows to learn spatial priors which can be used to interpolate the environment’s occupancy state. We show that these priors make our method suitable to predict dense occupancy estimations from sparse, highly uncertain inputs, as given by automotive radars, even for complex urban scenarios. Furthermore, we demonstrate that these estimations can be used for large-scale mapping applications. |
| Tasks | |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1903.12467v1 |
| http://arxiv.org/pdf/1903.12467v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-spatially-coherent-occupancy-maps-based |
| Repo | |
| Framework | |
Coherent Optical Communications Enhanced by Machine Intelligence
| Title | Coherent Optical Communications Enhanced by Machine Intelligence |
| Authors | Sanjaya Lohani, Ryan T. Glasser |
| Abstract | Uncertainty in discriminating between different received coherent signals is integral to the operation of many free-space optical communications protocols, and is often difficult when the receiver measures a weak signal. Here we design an optical communications scheme that uses balanced homodyne detection in combination with an unsupervised generative machine learning and convolutional neural network (CNN) system, and demonstrate its efficacy in a realistic simulated coherent quadrature phase shift keyed (QPSK) communications system. Additionally, we program the neural network system at the transmitter such that it autonomously learns to correct for the noise associated with a weak QPSK signal, which is shared with the network state of the receiver prior to the implementation of the communications. We find that the scheme significantly reduces the overall error probability of the communications system, achieving the classical optimal limit. This communications design is straightforward to build, implement, and scale. We anticipate that these results will allow for a significant enhancement of current classical and quantum coherent optical communications technologies. |
| Tasks | |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02525v2 |
| https://arxiv.org/pdf/1909.02525v2.pdf | |
| PWC | https://paperswithcode.com/paper/coherent-optical-communications-enhanced-by |
| Repo | |
| Framework | |
On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points
| Title | On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points |
| Authors | Chi Jin, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, Michael I. Jordan |
| Abstract | Gradient descent (GD) and stochastic gradient descent (SGD) are the workhorses of large-scale machine learning. While classical theory focused on analyzing the performance of these methods in convex optimization problems, the most notable successes in machine learning have involved nonconvex optimization, and a gap has arisen between theory and practice. Indeed, traditional analyses of GD and SGD show that both algorithms converge to stationary points efficiently. But these analyses do not take into account the possibility of converging to saddle points. More recent theory has shown that GD and SGD can avoid saddle points, but the dependence on dimension in these analyses is polynomial. For modern machine learning, where the dimension can be in the millions, such dependence would be catastrophic. We analyze perturbed versions of GD and SGD and show that they are truly efficient—their dimension dependence is only polylogarithmic. Indeed, these algorithms converge to second-order stationary points in essentially the same time as they take to converge to classical first-order stationary points. |
| Tasks | |
| Published | 2019-02-13 |
| URL | https://arxiv.org/abs/1902.04811v2 |
| https://arxiv.org/pdf/1902.04811v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-gradient-descent-escapes-saddle |
| Repo | |
| Framework | |
