Paper Group ANR 994
Order Matters at Fanatics Recommending Sequentially Ordered Products by LSTM Embedded with Word2Vec. Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models. A stochastic alternating minimizing method for sparse phase retrieval. Convex Reconstruction of Structured Matrix Signals from Linear Measuremen …
Order Matters at Fanatics Recommending Sequentially Ordered Products by LSTM Embedded with Word2Vec
| Title | Order Matters at Fanatics Recommending Sequentially Ordered Products by LSTM Embedded with Word2Vec |
| Authors | Jing Pan, Weian Sheng, Santanu Dey |
| Abstract | A unique challenge for e-commerce recommendation is that customers are often interested in products that are more advanced than their already purchased products, but not reversed. The few existing recommender systems modeling unidirectional sequence output a limited number of categories or continuous variables. To model the ordered sequence, we design the first recommendation system that both embed purchased items with Word2Vec, and model the sequence with stateless LSTM RNN. The click-through rate of this recommender system in production outperforms its solely Word2Vec based predecessor. Developed in 2017, it was perhaps the first published real-world application that makes distributed predictions of a single machine trained Keras model on Spark slave nodes at a scale of more than 0.4 million columns per row. |
| Tasks | Recommendation Systems |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09818v1 |
| https://arxiv.org/pdf/1911.09818v1.pdf | |
| PWC | https://paperswithcode.com/paper/order-matters-at-fanatics-recommending |
| Repo | |
| Framework | |
Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models
| Title | Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models |
| Authors | Thai-Son Nguyen, Sebastian Stueker, Alex Waibel |
| Abstract | Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity. However, prior works have shown that modelling A2W typically encounters issues of data sparsity that prevent training such a model directly. So far, pre-training initialization is the only approach proposed to deal with this issue. In this work, we propose to build a shared neural network and optimize A2W and conventional hybrid models in a multi-task manner. Our results show that training an A2W model is much more stable with our multi-task model without pre-training initialization, and results in a significant improvement compared to a baseline model. Experiments also reveal that the performance of a hybrid acoustic model can be further improved when jointly training with a sequence-level optimization criterion such as acoustic-to-word. |
| Tasks | Multi-Task Learning, Speech Recognition |
| Published | 2019-02-02 |
| URL | https://arxiv.org/abs/1902.01951v2 |
| https://arxiv.org/pdf/1902.01951v2.pdf | |
| PWC | https://paperswithcode.com/paper/using-multi-task-learning-to-improve-the |
| Repo | |
| Framework | |
A stochastic alternating minimizing method for sparse phase retrieval
| Title | A stochastic alternating minimizing method for sparse phase retrieval |
| Authors | Jianfeng Cai, Yuling Jiao, Xiliang Lu, Juntao You |
| Abstract | Sparse phase retrieval plays an important role in many fields of applied science and thus attracts lots of attention. In this paper, we propose a \underline{sto}chastic alte\underline{r}nating \underline{m}inimizing method for \underline{sp}arse ph\underline{a}se \underline{r}etrieval (\textit{StormSpar}) algorithm which {emprically} is able to recover $n$-dimensional $s$-sparse signals from only $O(s,\mathrm{log}, n)$ number of measurements without a desired initial value required by many existing methods. In \textit{StormSpar}, the hard-thresholding pursuit (HTP) algorithm is employed to solve the sparse constraint least square sub-problems. The main competitive feature of \textit{StormSpar} is that it converges globally requiring optimal order of number of samples with random initialization. Extensive numerical experiments are given to validate the proposed algorithm. |
| Tasks | |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.05967v1 |
| https://arxiv.org/pdf/1906.05967v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-stochastic-alternating-minimizing-method |
| Repo | |
| Framework | |
Convex Reconstruction of Structured Matrix Signals from Linear Measurements (I): Theoretical Results
| Title | Convex Reconstruction of Structured Matrix Signals from Linear Measurements (I): Theoretical Results |
| Authors | Yuan Tian |
| Abstract | We investigate the problem of reconstructing n-by-n structured matrix signal X via convex programming, where each column xj is a vector of s-sparsity and all columns have the same l1-norm. The regularizer in use is matrix norm X1=maxjxj1.The contribution in this paper has two parts. The first part is about conditions for stability and robustness in signal reconstruction via solving the convex programming from noise-free or noisy measurements.We establish uniform sufficient conditions which are very close to necessary conditions and non-uniform conditions are also discussed. Similar as the traditional compressive sensing theory for reconstructing vector signals, a related RIP condition is established. In addition, stronger conditions are investigated to guarantee the reconstructed signal’s support stability, sign stability and approximation-error robustness. The second part is to establish upper and lower bounds on number of measurements for robust reconstruction in noise. We take the convex geometric approach in random measurement setting and one of the critical ingredients in this approach is to estimate the related widths bounds in case of Gaussian and non-Gaussian distributions. These bounds are explicitly controlled by signal’s structural parameters r and s which determine matrix signal’s column-wise sparsity and l1-column-flatness respectively. |
| Tasks | Compressive Sensing |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08771v4 |
| https://arxiv.org/pdf/1910.08771v4.pdf | |
| PWC | https://paperswithcode.com/paper/convex-reconstruction-of-structured-matrix |
| Repo | |
| Framework | |
Sparse Polynomial Chaos expansions using Variational Relevance Vector Machines
| Title | Sparse Polynomial Chaos expansions using Variational Relevance Vector Machines |
| Authors | Panagiotis Tsilifis, Iason Papaioannou, Daniel Straub, Fabio Nobile |
| Abstract | The challenges for non-intrusive methods for Polynomial Chaos modeling lie in the computational efficiency and accuracy under a limited number of model simulations. These challenges can be addressed by enforcing sparsity in the series representation through retaining only the most important basis terms. In this work, we present a novel sparse Bayesian learning technique for obtaining sparse Polynomial Chaos expansions which is based on a Relevance Vector Machine model and is trained using Variational Inference. The methodology shows great potential in high-dimensional data-driven settings using relatively few data points and achieves user-controlled sparse levels that are comparable to other methods such as compressive sensing. The proposed approach is illustrated on two numerical examples, a synthetic response function that is explored for validation purposes and a low-carbon steel plate with random Young’s modulus and random loading, which is modeled by stochastic finite element with 38 input random variables. |
| Tasks | Compressive Sensing |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.11029v1 |
| https://arxiv.org/pdf/1912.11029v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-polynomial-chaos-expansions-using |
| Repo | |
| Framework | |
Regularizing Neural Networks via Stochastic Branch Layers
| Title | Regularizing Neural Networks via Stochastic Branch Layers |
| Authors | Wonpyo Park, Paul Hongsuck Seo, Bohyung Han, Minsu Cho |
| Abstract | We introduce a novel stochastic regularization technique for deep neural networks, which decomposes a layer into multiple branches with different parameters and merges stochastically sampled combinations of the outputs from the branches during training. Since the factorized branches can collapse into a single branch through a linear operation, inference requires no additional complexity compared to the ordinary layers. The proposed regularization method, referred to as StochasticBranch, is applicable to any linear layers such as fully-connected or convolution layers. The proposed regularizer allows the model to explore diverse regions of the model parameter space via multiple combinations of branches to find better local minima. An extensive set of experiments shows that our method effectively regularizes networks and further improves the generalization performance when used together with other existing regularization techniques. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01467v1 |
| https://arxiv.org/pdf/1910.01467v1.pdf | |
| PWC | https://paperswithcode.com/paper/regularizing-neural-networks-via-stochastic |
| Repo | |
| Framework | |
Robust Compressive Sensing MRI Reconstruction using Generative Adversarial Networks
| Title | Robust Compressive Sensing MRI Reconstruction using Generative Adversarial Networks |
| Authors | Puneesh Deora, Bhavya Vasudeva, Saumik Bhattacharya, Pyari Mohan Pradhan |
| Abstract | Compressive sensing magnetic resonance imaging (CS-MRI) accelerates the acquisition of MR images by breaking the Nyquist sampling limit. In this work, a novel generative adversarial network (GAN) based framework for CS-MRI reconstruction is proposed. Leveraging a combination of patchGAN discriminator and structural similarity index based loss, our model focuses on preserving high frequency content as well as fine textural details in the reconstructed image. Dense and residual connections have been incorporated in a U-net based generator architecture to allow easier transfer of information as well as variable network length. We show that our algorithm outperforms state-of-the-art methods in terms of quality of reconstruction and robustness to noise. Also, the reconstruction time, which is of the order of milliseconds, makes it highly suitable for real-time clinical use. |
| Tasks | Compressive Sensing |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06067v1 |
| https://arxiv.org/pdf/1910.06067v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-compressive-sensing-mri-reconstruction |
| Repo | |
| Framework | |
What Happens on the Edge, Stays on the Edge: Toward Compressive Deep Learning
| Title | What Happens on the Edge, Stays on the Edge: Toward Compressive Deep Learning |
| Authors | Yang Li, Thomas Strohmer |
| Abstract | Machine learning at the edge offers great benefits such as increased privacy and security, low latency, and more autonomy. However, a major challenge is that many devices, in particular edge devices, have very limited memory, weak processors, and scarce energy supply. We propose a hybrid hardware-software framework that has the potential to significantly reduce the computational complexity and memory requirements of on-device machine learning. In the first step, inspired by compressive sensing, data is collected in compressed form simultaneously with the sensing process. Thus this compression happens already at the hardware level during data acquisition. But unlike in compressive sensing, this compression is achieved via a projection operator that is specifically tailored to the desired machine learning task. The second step consists of a specially designed and trained deep network. As concrete example we consider the task of image classification, although the proposed framework is more widely applicable. An additional benefit of our approach is that it can be easily combined with existing on-device techniques. Numerical simulations illustrate the viability of our method. |
| Tasks | Compressive Sensing, Image Classification |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01539v1 |
| https://arxiv.org/pdf/1909.01539v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-happens-on-the-edge-stays-on-the-edge |
| Repo | |
| Framework | |
Information-Theoretic Lower Bounds for Compressive Sensing with Generative Models
| Title | Information-Theoretic Lower Bounds for Compressive Sensing with Generative Models |
| Authors | Zhaoqiang Liu, Jonathan Scarlett |
| Abstract | It has recently been shown that for compressive sensing, significantly fewer measurements may be required if the sparsity assumption is replaced by the assumption the unknown vector lies near the range of a suitably-chosen generative model. In particular, in (Bora {\em et al.}, 2017) it was shown roughly $O(k\log L)$ random Gaussian measurements suffice for accurate recovery when the generative model is an $L$-Lipschitz function with bounded $k$-dimensional inputs, and $O(kd \log w)$ measurements suffice when the generative model is a $k$-input ReLU network with depth $d$ and width $w$. In this paper, we establish corresponding algorithm-independent lower bounds on the sample complexity using tools from minimax statistical analysis. In accordance with the above upper bounds, our results are summarized as follows: (i) We construct an $L$-Lipschitz generative model capable of generating group-sparse signals, and show that the resulting necessary number of measurements is $\Omega(k \log L)$; (ii) Using similar ideas, we construct ReLU networks with high depth and/or high depth for which the necessary number of measurements scales as $\Omega\big( kd \frac{\log w}{\log n}\big)$ (with output dimension $n$), and in some cases $\Omega(kd \log w)$. As a result, we establish that the scaling laws derived in (Bora {\em et al.}, 2017) are optimal or near-optimal in the absence of further assumptions. |
| Tasks | Compressive Sensing |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10744v2 |
| https://arxiv.org/pdf/1908.10744v2.pdf | |
| PWC | https://paperswithcode.com/paper/information-theoretic-lower-bounds-for-2 |
| Repo | |
| Framework | |
Multi-Channel Deep Networks for Block-Based Image Compressive Sensing
| Title | Multi-Channel Deep Networks for Block-Based Image Compressive Sensing |
| Authors | Siwang Zhou, Yan He, Yonghe Liu, Chengqing Li |
| Abstract | Incorporating deep neural networks in image compressive sensing (CS) receives intensive attentions recently. As deep network approaches learn the inverse mapping directly from the CS measurements, a number of models have to be trained, each of which corresponds to a sampling rate. This may potentially degrade the performance of image CS, especially when multiple sampling rates are assigned to different blocks within an image. In this paper, we develop a multi-channel deep network for block-based image CS with performance significantly exceeding the current state-of-the-art methods. The significant performance improvement of the model is attributed to block-based sampling rates allocation and model-level removal of blocking artifacts. Specifically, the image blocks with a variety of sampling rates can be reconstructed in a single model by exploiting inter-block correlation. At the same time, the initially reconstructed blocks are reassembled into a full image to remove blocking artifacts within the network by unrolling a hand-designed block-based CS algorithm. Experimental results demonstrate that the proposed method outperforms the state-of-the-art CS methods by a large margin in terms of objective metrics, PSNR, SSIM, and subjective visual quality. |
| Tasks | Compressive Sensing |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.11221v1 |
| https://arxiv.org/pdf/1908.11221v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-channel-deep-networks-for-block-based |
| Repo | |
| Framework | |
Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach
| Title | Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach |
| Authors | Igor Shalyminov, Sungjin Lee, Arash Eshghi, Oliver Lemon |
| Abstract | Learning with minimal data is one of the key challenges in the development of practical, production-ready goal-oriented dialogue systems. In a real-world enterprise setting where dialogue systems are developed rapidly and are expected to work robustly for an ever-growing variety of domains, products, and scenarios, efficient learning from a limited number of examples becomes indispensable. In this paper, we introduce a technique to achieve state-of-the-art dialogue generation performance in a few-shot setup, without using any annotated data. We do this by leveraging background knowledge from a larger, more highly represented dialogue source — namely, the MetaLWOz dataset. We evaluate our model on the Stanford Multi-Domain Dialogue Dataset, consisting of human-human goal-oriented dialogues in in-car navigation, appointment scheduling, and weather information domains. We show that our few-shot approach achieves state-of-the art results on that dataset by consistently outperforming the previous best model in terms of BLEU and Entity F1 scores, while being more data-efficient by not requiring any data annotation. |
| Tasks | Dialogue Generation, Goal-Oriented Dialogue Systems, Transfer Learning |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05854v1 |
| https://arxiv.org/pdf/1908.05854v1.pdf | |
| PWC | https://paperswithcode.com/paper/few-shot-dialogue-generation-without |
| Repo | |
| Framework | |
ISEA: Image Steganalysis using Evolutionary Algorithms
| Title | ISEA: Image Steganalysis using Evolutionary Algorithms |
| Authors | Farid Ghareh Mohammadi, Hamid R. Arabnia |
| Abstract | NP-hard problems always have been attracting scientists’ attentions, and most often seen in the emerging challenging issues. The most interesting NP-hard problems emerging in the world of data science is Curse of dimensionality (CoD). Recently, this problem has penetrated most of high technology domains like advanced image processing, particularly image steganalysis. The universal and smarter steganalysis algorithms provide a huge number of attributes, which make working with data hard to process. In large data sets, finding a pattern which governs whole data takes long time, and yet no guarantee to reach the optimal pattern. In general, the purpose of the researchers in image steganalysis stands for distinguishing stego images from cover images. In this paper, we investigated recent works on detecting stego images, particularly those algorithms that adopted evolutionary algorithms. Thus, our work is categorized as supervised learning which consider ground truth to evaluate the performance of given algorithm. The objective is to provide a comprehensive understanding of evolutionary algorithms which are attempted to solve this NP-hard problems. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.12914v1 |
| https://arxiv.org/pdf/1907.12914v1.pdf | |
| PWC | https://paperswithcode.com/paper/isea-image-steganalysis-using-evolutionary |
| Repo | |
| Framework | |
Learning Ontologies with Epistemic Reasoning: The EL Case
| Title | Learning Ontologies with Epistemic Reasoning: The EL Case |
| Authors | Ana Ozaki, Nicolas Troquard |
| Abstract | We investigate the problem of learning description logic ontologies from entailments via queries, using epistemic reasoning. We introduce a new learning model consisting of epistemic membership and example queries and show that polynomial learnability in this model coincides with polynomial learnability in Angluin’s exact learning model with membership and equivalence queries. We then instantiate our learning framework to EL and show some complexity results for an epistemic extension of EL where epistemic operators can be applied over the axioms. Finally, we transfer known results for EL ontologies and its fragments to our learning model based on epistemic reasoning. |
| Tasks | |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.03273v1 |
| http://arxiv.org/pdf/1902.03273v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-ontologies-with-epistemic-reasoning |
| Repo | |
| Framework | |
Seek and You Will Find: A New Optimized Framework for Efficient Detection of Pedestrian
| Title | Seek and You Will Find: A New Optimized Framework for Efficient Detection of Pedestrian |
| Authors | Sudip Das, Partha Sarathi Mukherjee, Ujjwal Bhattacharya |
| Abstract | Studies of object detection and localization, particularly pedestrian detection have received considerable attention in recent times due to its several prospective applications such as surveillance, driving assistance, autonomous cars, etc. Also, a significant trend of latest research studies in related problem areas is the use of sophisticated Deep Learning based approaches to improve the benchmark performance on various standard datasets. A trade-off between the speed (number of video frames processed per second) and detection accuracy has often been reported in the existing literature. In this article, we present a new but simple deep learning based strategy for pedestrian detection that improves this trade-off. Since training of similar models using publicly available sample datasets failed to improve the detection performance to some significant extent, particularly for the instances of pedestrians of smaller sizes, we have developed a new sample dataset consisting of more than 80K annotated pedestrian figures in videos recorded under varying traffic conditions. Performance of the proposed model on the test samples of the new dataset and two other existing datasets, namely Caltech Pedestrian Dataset (CPD) and CityPerson Dataset (CD) have been obtained. Our proposed system shows nearly 16% improvement over the existing state-of-the-art result. |
| Tasks | Object Detection, Pedestrian Detection |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/1912.10241v1 |
| https://arxiv.org/pdf/1912.10241v1.pdf | |
| PWC | https://paperswithcode.com/paper/seek-and-you-will-find-a-new-optimized |
| Repo | |
| Framework | |
Geometry and Symmetry in Short-and-Sparse Deconvolution
| Title | Geometry and Symmetry in Short-and-Sparse Deconvolution |
| Authors | Han-Wen Kuo, Yenson Lau, Yuqian Zhang, John Wright |
| Abstract | We study the $\textit{Short-and-Sparse (SaS) deconvolution}$ problem of recovering a short signal $\mathbf a_0$ and a sparse signal $\mathbf x_0$ from their convolution. We propose a method based on nonconvex optimization, which under certain conditions recovers the target short and sparse signals, up to a signed shift symmetry which is intrinsic to this model. This symmetry plays a central role in shaping the optimization landscape for deconvolution. We give a $\textit{regional analysis}$, which characterizes this landscape geometrically, on a union of subspaces. Our geometric characterization holds when the length-$p_0$ short signal $\mathbf a_0$ has shift coherence $\mu$, and $\mathbf x_0$ follows a random sparsity model with sparsity rate $\theta \in \Bigl[\frac{c_1}{p_0}, \frac{c_2}{p_0\sqrt\mu + \sqrt{p_0}}\Bigr]\cdot\frac{1}{\log^2p_0}$. Based on this geometry, we give a provable method that successfully solves SaS deconvolution with high probability. |
| Tasks | |
| Published | 2019-01-02 |
| URL | http://arxiv.org/abs/1901.00256v2 |
| http://arxiv.org/pdf/1901.00256v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-and-symmetry-in-short-and-sparse |
| Repo | |
| Framework | |
