Paper Group NAWR 6
Predicting epileptic seizures using nonnegative matrix factorization. Abstractive Text Summarization Based on Deep Learning and Semantic Content Generalization. DHSGAN: An End to End Dehazing Network for Fog and Smoke. Tree Communication Models for Sentiment Analysis. Zero-shot Word Sense Disambiguation using Sense Definition Embeddings. Classifica …
Predicting epileptic seizures using nonnegative matrix factorization
| Title | Predicting epileptic seizures using nonnegative matrix factorization |
| Authors | Olivera Stojanović, Gordon Pipa |
| Abstract | This paper presents a procedure for the patient-specific prediction of epileptic seizures. To this end, a combination of nonnegative matrix factorization (NMF) and smooth basis functions with robust regression is applied to power spectra of intracranial electroencephalographic (iEEG) signals. The resulting time and frequency components capture the dominant information from power spectra, while removing outliers and noise. This makes it possible to detect structure in preictal states, which is used for classification. Linear support vector machines (SVM) with L1 regularization are used to select and weigh the contributions from different number of not equally informative channels among patients. Due to class imbalance in data, synthetic minority over-sampling technique (SMOTE) is applied. The resulting method yields a computationally and conceptually simple, interpretable model of EEG signals of preictal and interictal states, which shows a good performance for the task of seizure prediction. |
| Tasks | EEG, Epilepsy Prediction, Seizure prediction |
| Published | 2019-06-25 |
| URL | https://www.medrxiv.org/content/10.1101/19000430v1 |
| https://www.medrxiv.org/content/medrxiv/early/2019/06/25/19000430.full.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-epileptic-seizures-using |
| Repo | https://github.com/ostojanovic/seizure_prediction |
| Framework | none |
Abstractive Text Summarization Based on Deep Learning and Semantic Content Generalization
| Title | Abstractive Text Summarization Based on Deep Learning and Semantic Content Generalization |
| Authors | Panagiotis Kouris, Alex, Georgios ridis, Andreas Stafylopatis |
| Abstract | This work proposes a novel framework for enhancing abstractive text summarization based on the combination of deep learning techniques along with semantic data transformations. Initially, a theoretical model for semantic-based text generalization is introduced and used in conjunction with a deep encoder-decoder architecture in order to produce a summary in generalized form. Subsequently, a methodology is proposed which transforms the aforementioned generalized summary into human-readable form, retaining at the same time important informational aspects of the original text and addressing the problem of out-of-vocabulary or rare words. The overall approach is evaluated on two popular datasets with encouraging results. |
| Tasks | Abstractive Text Summarization, Text Summarization |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1501/ |
| https://www.aclweb.org/anthology/P19-1501 | |
| PWC | https://paperswithcode.com/paper/abstractive-text-summarization-based-on-deep |
| Repo | https://github.com/pkouris/abtextsum |
| Framework | tf |
DHSGAN: An End to End Dehazing Network for Fog and Smoke
| Title | DHSGAN: An End to End Dehazing Network for Fog and Smoke |
| Authors | Ramavtar Malav, Ayoung Kim, Soumya Ranjan Sahoo, Gaurav Pandey |
| Abstract | In this paper we propose a novel end-to-end convolution dehazing architecture, called De-Haze and Smoke GAN (DHSGAN). The model is trained under a generative adversarial network framework to effectively learn the underlying distribution of clean images for the generation of realistic haze-free images. We train the model on a dataset that is synthesized to include image degradation scenarios from varied conditions of fog, haze, and smoke in both indoor and outdoor settings. Experimental results on both synthetic and natural degraded images demonstrate that our method shows significant robustness over different haze conditions in comparison to the state-of-the-art methods. A group of studies are conducted to evaluate the effectiveness of each module of the proposed method. |
| Tasks | Image Dehazing, Image Enhancement, Single Image Dehazing |
| Published | 2019-05-26 |
| URL | https://link.springer.com/chapter/10.1007/978-3-030-20873-8_38 |
| https://drive.google.com/file/d/1uoy5JAfXSfCjd0VtJoQEu_6dT8Z9V-DO/view?usp=sharing | |
| PWC | https://paperswithcode.com/paper/dhsgan-an-end-to-end-dehazing-network-for-fog |
| Repo | https://github.com/rmalav15/DHSGAN |
| Framework | tf |
Tree Communication Models for Sentiment Analysis
| Title | Tree Communication Models for Sentiment Analysis |
| Authors | Yuan Zhang, Yue Zhang |
| Abstract | Tree-LSTMs have been used for tree-based sentiment analysis over Stanford Sentiment Treebank, which allows the sentiment signals over hierarchical phrase structures to be calculated simultaneously. However, traditional tree-LSTMs capture only the bottom-up dependencies between constituents. In this paper, we propose a tree communication model using graph convolutional neural network and graph recurrent neural network, which allows rich information exchange between phrases constituent tree. Experiments show that our model outperforms existing work on bidirectional tree-LSTMs in both accuracy and efficiency, providing more consistent predictions on phrase-level sentiments. |
| Tasks | Sentiment Analysis |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1342/ |
| https://www.aclweb.org/anthology/P19-1342 | |
| PWC | https://paperswithcode.com/paper/tree-communication-models-for-sentiment |
| Repo | https://github.com/fred2008/TCMSA |
| Framework | tf |
Zero-shot Word Sense Disambiguation using Sense Definition Embeddings
| Title | Zero-shot Word Sense Disambiguation using Sense Definition Embeddings |
| Authors | Sawan Kumar, Sharmistha Jat, Karan Saxena, Partha Talukdar |
| Abstract | Word Sense Disambiguation (WSD) is a long-standing but open problem in Natural Language Processing (NLP). WSD corpora are typically small in size, owing to an expensive annotation process. Current supervised WSD methods treat senses as discrete labels and also resort to predicting the Most-Frequent-Sense (MFS) for words unseen during training. This leads to poor performance on rare and unseen senses. To overcome this challenge, we propose Extended WSD Incorporating Sense Embeddings (EWISE), a supervised model to perform WSD by predicting over a continuous sense embedding space as opposed to a discrete label space. This allows EWISE to generalize over both seen and unseen senses, thus achieving generalized zero-shot learning. To obtain target sense embeddings, EWISE utilizes sense definitions. EWISE learns a novel sentence encoder for sense definitions by using WordNet relations and also ConvE, a recently proposed knowledge graph embedding method. We also compare EWISE against other sentence encoders pretrained on large corpora to generate definition embeddings. EWISE achieves new state-of-the-art WSD performance. |
| Tasks | Graph Embedding, Knowledge Graph Embedding, Word Sense Disambiguation, Zero-Shot Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1568/ |
| https://www.aclweb.org/anthology/P19-1568 | |
| PWC | https://paperswithcode.com/paper/zero-shot-word-sense-disambiguation-using |
| Repo | https://github.com/malllabiisc/EWISE |
| Framework | pytorch |
Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components
| Title | Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components |
| Authors | Sascha Saralajew, Lars Holdijk, Maike Rees, Ebubekir Asan, Thomas Villmann |
| Abstract | Abstract Neural networks are state-of-the-art classification approaches but are generally difficult to interpret. This issue can be partly alleviated by constructing a precise decision process within the neural network. In this work, a network architecture, denoted as Classification-By-Components network (CBC), is proposed. It is restricted to follow an intuitive reasoning based decision process inspired by Biederman’s recognition-by-components theory from cognitive psychology. The network is trained to learn and detect generic components that characterize objects. In parallel, a class-wise reasoning strategy based on these components is learned to solve the classification problem. In contrast to other work on reasoning, we propose three different types of reasoning: positive, negative, and indefinite. These three types together form a probability space to provide a probabilistic classifier. The decomposition of objects into generic components combined with the probabilistic reasoning provides by design a clear interpretation of the classification decision process. The evaluation of the approach on MNIST shows that CBCs are viable classifiers. Additionally, we demonstrate that the inherent interpretability offers a profound understanding of the classification behavior such that we can explain the success of an adversarial attack. The method’s scalability is successfully tested using the ImageNet dataset. |
| Tasks | Adversarial Attack |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8546-classification-by-components-probabilistic-modeling-of-reasoning-over-a-set-of-components |
| http://papers.nips.cc/paper/8546-classification-by-components-probabilistic-modeling-of-reasoning-over-a-set-of-components.pdf | |
| PWC | https://paperswithcode.com/paper/classification-by-components-probabilistic |
| Repo | https://github.com/saralajew/cbc_networks |
| Framework | tf |
A Skeleton-bridged Deep Learning Approach for Generating Meshesof Complex Topologies from Single RGB Image
| Title | A Skeleton-bridged Deep Learning Approach for Generating Meshesof Complex Topologies from Single RGB Image |
| Authors | Jiapeng Tang, Xiaoguang Han, Junyi Pan, Kui Jia, Xin Tong |
| Abstract | This paper focuses on the challenging task of learning 3D object surface reconstructions from single RGB images. Existing methods achieve varying degrees of success by using different geometric representations. However, they all have their own drawbacks, and cannot well reconstruct those surfaces of complex topologies. To this end, we propose in this paper a skeleton-bridged, stage-wise learning approach to address the challenge. Our use of skeleton is due to its nice property of topology preservation, while being of lower complexity to learn. To learn skeleton from an input image, we design a deep architecture whose decoder is based on a novel design of parallel streams respectively for synthesis of curve- and surface-like skeleton points. We use different shape representations of point cloud, volume, and mesh in our stage-wise learning, in order to take their respective advantages. We also propose multi-stage use of the input image to correct prediction errors that are possibly accumulated in each stage. We conduct intensive experiments to investigate the efficacy of our proposed approach. Qualitative and quantitative results on representative object categories of both simple and complex topologies demonstrate the superiority of our approach over existing ones. We will make our ShapeNet-Skeleton dataset publicly available. |
| Tasks | |
| Published | 2019-04-10 |
| URL | https://arxiv.org/abs/1903.04704 |
| https://arxiv.org/pdf/1903.04704.pdf | |
| PWC | https://paperswithcode.com/paper/a-skeleton-bridged-deep-learning-approach-for-2 |
| Repo | https://github.com/tangjiapeng/SkeletonBridgeRecon |
| Framework | pytorch |
Tight Dimensionality Reduction for Sketching Low Degree Polynomial Kernels
| Title | Tight Dimensionality Reduction for Sketching Low Degree Polynomial Kernels |
| Authors | Michela Meister, Tamas Sarlos, David Woodruff |
| Abstract | We revisit the classic randomized sketch of a tensor product of $q$ vectors $x_i\in\mathbb{R}^n$. The $i$-th coordinate $(Sx)i$ of the sketch is equal to $\prod{j = 1}^q \langle u^{i, j}, x^j \rangle / \sqrt{m}$, where $u^{i,j}$ are independent random sign vectors. Kar and Karnick (JMLR, 2012) show that if the sketching dimension $m = \Omega(\epsilon^{-2} C_{\Omega}^2 \log (1/\delta))$, where $C_{\Omega}$ is a certain property of the point set $\Omega$ one wants to sketch, then with probability $1-\delta$, $\Sx_2 = (1\pm \epsilon)\x_2$ for all $x\in\Omega$. However, in their analysis $C_{\Omega}^2$ can be as large as $\Theta(n^{2q})$, even for a set $\Omega$ of $O(1)$ vectors $x$. We give a new analysis of this sketch, providing nearly optimal bounds. Namely, we show an upper bound of $m = \Theta \left (\epsilon^{-2} \log(n/\delta) + \epsilon^{-1} \log^q(n/\delta) \right ),$ which by composing with CountSketch, can be improved to $\Theta(\epsilon^{-2}\log(1/(\delta \epsilon)) + \epsilon^{-1} \log^q (1/(\delta \epsilon))$. For the important case of $q = 2$ and $\delta = 1/\poly(n)$, this shows that $m = \Theta(\epsilon^{-2} \log(n) + \epsilon^{-1} \log^2(n))$, demonstrating that the $\epsilon^{-2}$ and $\log^2(n)$ terms do not multiply each other. We also show a nearly matching lower bound of $m = \Omega(\eps^{-2} \log(1/(\delta)) + \eps^{-1} \log^q(1/(\delta)))$. In a number of applications, one has $\Omega = \poly(n)$ and in this case our bounds are optimal up to a constant factor. This is the first high probability sketch for tensor products that has optimal sketch size and can be implemented in $m \cdot \sum_{i=1}^q \textrm{nnz}(x_i)$ time, where $\textrm{nnz}(x_i)$ is the number of non-zero entries of $x_i$. Lastly, we empirically compare our sketch to other sketches for tensor products, and give a novel application to compressing neural networks. |
| Tasks | Dimensionality Reduction |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9144-tight-dimensionality-reduction-for-sketching-low-degree-polynomial-kernels |
| http://papers.nips.cc/paper/9144-tight-dimensionality-reduction-for-sketching-low-degree-polynomial-kernels.pdf | |
| PWC | https://paperswithcode.com/paper/tight-dimensionality-reduction-for-sketching |
| Repo | https://github.com/google-research/google-research |
| Framework | tf |
A Dynamic Speaker Model for Conversational Interactions
| Title | A Dynamic Speaker Model for Conversational Interactions |
| Authors | Hao Cheng, Hao Fang, Mari Ostendorf |
| Abstract | Individual differences in speakers are reflected in their language use as well as in their interests and opinions. Characterizing these differences can be useful in human-computer interaction, as well as analysis of human-human conversations. In this work, we introduce a neural model for learning a dynamically updated speaker embedding in a conversational context. Initial model training is unsupervised, using context-sensitive language generation as an objective, with the context being the conversation history. Further fine-tuning can leverage task-dependent supervised training. The learned neural representation of speakers is shown to be useful for content ranking in a socialbot and dialog act prediction in human-human conversations. |
| Tasks | Text Generation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1284/ |
| https://www.aclweb.org/anthology/N19-1284 | |
| PWC | https://paperswithcode.com/paper/a-dynamic-speaker-model-for-conversational |
| Repo | https://github.com/hao-cheng/dynamic_speaker_model |
| Framework | none |
Cross-Modal Learning with Adversarial Samples
| Title | Cross-Modal Learning with Adversarial Samples |
| Authors | Chao Li, Shangqian Gao, Cheng Deng, De Xie, Wei Liu |
| Abstract | With the rapid developments of deep neural networks, numerous deep cross-modal analysis methods have been presented and are being applied in widespread real-world applications, including healthcare and safety-critical environments. However, the recent studies on robustness and stability of deep neural networks show that a microscopic modification, known as adversarial sample, which is even imperceptible to humans, can easily fool a well-performed deep neural network and brings a new obstacle to deep cross-modal correlation exploring. In this paper, we propose a novel Cross-Modal correlation Learning with Adversarial samples, namely CMLA, which for the first time presents the existence of adversarial samples in cross-modal data. Moreover, we provide a simple yet effective adversarial sample learning method, where inter- and intra- modality similarity regularizations across different modalities are simultaneously integrated into the learning of adversarial samples. Finally, our proposed CMLA is demonstrated to be highly effective in cross-modal hashing based retrieval. Extensive experiments on two cross-modal benchmark datasets show that the adversarial examples produced by our CMLA are efficient in fooling a target deep cross-modal hashing network. On the other hand, such adversarial examples can significantly strengthen the robustness of the target network by conducting an adversarial training. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9262-cross-modal-learning-with-adversarial-samples |
| http://papers.nips.cc/paper/9262-cross-modal-learning-with-adversarial-samples.pdf | |
| PWC | https://paperswithcode.com/paper/cross-modal-learning-with-adversarial-samples |
| Repo | https://github.com/ChaoLi1991/CMLA |
| Framework | tf |
SEDTWik: Segmentation-based Event Detection from Tweets Using Wikipedia
| Title | SEDTWik: Segmentation-based Event Detection from Tweets Using Wikipedia |
| Authors | Keval Morabia, Neti Lalita Bhanu Murthy, Aruna Malapati, Surender Samant |
| Abstract | Event Detection has been one of the research areas in Text Mining that has attracted attention during this decade due to the widespread availability of social media data specifically twitter data. Twitter has become a major source for information about real-world events because of the use of hashtags and the small word limit of Twitter that ensures concise presentation of events. Previous works on event detection from tweets are either applicable to detect localized events or breaking news only or miss out on many important events. This paper presents the problems associated with event detection from tweets and a tweet-segmentation based system for event detection called SEDTWik, an extension to a previous work, that is able to detect newsworthy events occurring at different locations of the world from a wide range of categories. The main idea is to split each tweet and hash-tag into segments, extract bursty segments, cluster them, and summarize them. We evaluated our results on the well-known Events2012 corpus and achieved state-of-the-art results. Keywords: Event detection, Twitter, Social Media, Microblogging, Tweet segmentation, Text Mining, Wikipedia, Hashtag. |
| Tasks | Twitter Event Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-3011/ |
| https://www.aclweb.org/anthology/N19-3011 | |
| PWC | https://paperswithcode.com/paper/sedtwik-segmentation-based-event-detection |
| Repo | https://github.com/kevalmorabia97/SEDTWik-Event-Detection-from-Tweets |
| Framework | none |
UNI-EM: An Environment for Deep Neural Network-Based Automated Segmentation of Neuronal Electron Microscopic Images
| Title | UNI-EM: An Environment for Deep Neural Network-Based Automated Segmentation of Neuronal Electron Microscopic Images |
| Authors | Hidetoshi Urakubo, Torsten Bullmann, Yoshiyuki Kubota, Shigeyuki Oba, Shin Ishii |
| Abstract | Recently, there has been a rapid expansion in the field of micro-connectomics, which targets the three-dimensional (3D) reconstruction of neuronal networks from a stack of two-dimensional (2D) electron microscopic (EM) images. The spatial scale of the 3D reconstruction grows rapidly owing to deep neural networks (DNNs) that enable automated image segmentation. Several research teams have developed their own software pipelines for DNN-based segmentation. However, the complexity of such pipelines makes their use difficult even for computer experts and impossible for non-experts. In this study, we developed a new software program, called UNI-EM, that enables 2D- and 3D-DNN-based segmentation for non-computer experts. UNI-EM is a software collection for DNN-based EM image segmentation, including ground truth generation, training, inference, postprocessing, proofreading, and visualization. UNI-EM comes with a set of 2D DNNs, i.e., U-Net, ResNet, HighwayNet, and DenseNet. We further wrapped flood-filling networks (FFNs) as a representative 3D DNN-based neuron segmentation algorithm. The 2D- and 3D-DNNs are known to show state-of-the-art level segmentation performance. We then provided two-example workflows: mitochondria segmentation using a 2D DNN as well as neuron segmentation using FFNs. Following these example workflows, users can benefit from DNN-based segmentation without any knowledge of Python programming or DNN frameworks. |
| Tasks | 3D Reconstruction, Electron Microscopy Image Segmentation, Semantic Segmentation |
| Published | 2019-04-12 |
| URL | https://doi.org/10.1101/607366 |
| https://www.biorxiv.org/content/biorxiv/early/2019/04/12/607366.full-text.pdf | |
| PWC | https://paperswithcode.com/paper/uni-em-an-environment-for-deep-neural-network |
| Repo | https://github.com/urakubo/UNI-EM |
| Framework | tf |
Prior Guided Dropout for Robust Visual Localization in Dynamic Environments
| Title | Prior Guided Dropout for Robust Visual Localization in Dynamic Environments |
| Authors | Zhaoyang Huang, Yan Xu, Jianping Shi, Xiaowei Zhou, Hujun Bao, Guofeng Zhang |
| Abstract | Camera localization from monocular images has been a long-standing problem, but its robustness in dynamic environments is still not adequately addressed. Compared with classic geometric approaches, modern CNN-based methods (e.g. PoseNet) have manifested the reliability against illumination or viewpoint variations, but they still have the following limitations. First, foreground moving objects are not explicitly handled, which results in poor performance and instability in dynamic environments. Second, the output for each image is a point estimate without uncertainty quantification. In this paper, we propose a framework which can be generally applied to existing CNN-based pose regressors to improve their robustness in dynamic environments. The key idea is a prior guided dropout module coupled with a self-attention module which can guide CNNs to ignore foreground objects during both training and inference. Additionally, the dropout module enables the pose regressor to output multiple hypotheses from which the uncertainty of pose estimates can be quantified and leveraged in the following uncertainty-aware pose-graph optimization to improve the robustness further. We achieve an average accuracy of 9.98m/3.63deg on RobotCar dataset, which outperforms the state-of-the-art method by 62.97%/47.08%. The source code of our implementation is available at https://github.com/zju3dv/RVL-dynamic. |
| Tasks | Camera Localization, Visual Localization |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Huang_Prior_Guided_Dropout_for_Robust_Visual_Localization_in_Dynamic_Environments_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Huang_Prior_Guided_Dropout_for_Robust_Visual_Localization_in_Dynamic_Environments_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/prior-guided-dropout-for-robust-visual |
| Repo | https://github.com/zju3dv/RVL-Dynamic |
| Framework | none |
A First-Order Algorithmic Framework for Distributionally Robust Logistic Regression
| Title | A First-Order Algorithmic Framework for Distributionally Robust Logistic Regression |
| Authors | Jiajin Li, Sen Huang, Anthony Man-Cho So |
| Abstract | Wasserstein distance-based distributionally robust optimization (DRO) has received much attention lately due to its ability to provide a robustness interpretation of various learning models. Moreover, many of the DRO problems that arise in the learning context admits exact convex reformulations and hence can be tackled by off-the-shelf solvers. Nevertheless, the use of such solvers severely limits the applicability of DRO in large-scale learning problems, as they often rely on general purpose interior-point algorithms. On the other hand, there are very few works that attempt to develop fast iterative methods to solve these DRO problems, which typically possess complicated structures. In this paper, we take a first step towards resolving the above difficulty by developing a first-order algorithmic framework for tackling a class of Wasserstein distance-based distributionally robust logistic regression (DRLR) problem. Specifically, we propose a novel linearized proximal ADMM to solve the DRLR problem, whose objective is convex but consists of a smooth term plus two non-separable non-smooth terms. We prove that our method enjoys a sublinear convergence rate. Furthermore, we conduct three different experiments to show its superb performance on both synthetic and real-world datasets. In particular, our method can achieve the same accuracy up to 800+ times faster than the standard off-the-shelf solver. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8649-a-first-order-algorithmic-framework-for-distributionally-robust-logistic-regression |
| http://papers.nips.cc/paper/8649-a-first-order-algorithmic-framework-for-distributionally-robust-logistic-regression.pdf | |
| PWC | https://paperswithcode.com/paper/a-first-order-algorithmic-framework-for-1 |
| Repo | https://github.com/gerrili1996/DRLR_NIPS2019_exp |
| Framework | none |
Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models
| Title | Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models |
| Authors | Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Lenka Zdeborová |
| Abstract | Gradient-based algorithms are effective for many machine learning tasks, but despite ample recent effort and some progress, it often remains unclear why they work in practice in optimising high-dimensional non-convex functions and why they find good minima instead of being trapped in spurious ones.Here we present a quantitative theory explaining this behaviour in a spiked matrix-tensor model.Our framework is based on the Kac-Rice analysis of stationary points and a closed-form analysis of gradient-flow originating from statistical physics. We show that there is a well defined region of parameters where the gradient-flow algorithm finds a good global minimum despite the presence of exponentially many spurious local minima. We show that this is achieved by surfing on saddles that have strong negative direction towards the global minima, a phenomenon that is connected to a BBP-type threshold in the Hessian describing the critical points of the landscapes. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9073-who-is-afraid-of-big-bad-minima-analysis-of-gradient-flow-in-spiked-matrix-tensor-models |
| http://papers.nips.cc/paper/9073-who-is-afraid-of-big-bad-minima-analysis-of-gradient-flow-in-spiked-matrix-tensor-models.pdf | |
| PWC | https://paperswithcode.com/paper/who-is-afraid-of-big-bad-minima-analysis-of-1 |
| Repo | https://github.com/sphinxteam/spiked_matrix-tensor_T0 |
| Framework | none |
