Paper Group ANR 923
Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation. Entanglement-guided architectures of machine learning by quantum tensor network. Zoom: SSD-based Vector Search for Optimizing Accuracy, Latency and Memory. The Evolution of Sex Chromosomes through the Baldwin Effect. Graphical Convergence of Subgradients in Nonconv …
Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation
Title | Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation |
Authors | Yoshikatsu Nakajima, Keisuke Tateno, Federico Tombari, Hideo Saito |
Abstract | We propose an efficient and scalable method for incrementally building a dense, semantically annotated 3D map in real-time. The proposed method assigns class probabilities to each region, not each element (e.g., surfel and voxel), of the 3D map which is built up through a robust SLAM framework and incrementally segmented with a geometric-based segmentation method. Differently from all other approaches, our method has a capability of running at over 30Hz while performing all processing components, including SLAM, segmentation, 2D recognition, and updating class probabilities of each segmentation label at every incoming frame, thanks to the high efficiency that characterizes the computationally intensive stages of our framework. By utilizing a specifically designed CNN to improve the frame-wise segmentation result, we can also achieve high accuracy. We validate our method on the NYUv2 dataset by comparing with the state of the art in terms of accuracy and computational efficiency, and by means of an analysis in terms of time and space complexity. |
Tasks | |
Published | 2018-03-07 |
URL | http://arxiv.org/abs/1803.02784v1 |
http://arxiv.org/pdf/1803.02784v1.pdf | |
PWC | https://paperswithcode.com/paper/fast-and-accurate-semantic-mapping-through |
Repo | |
Framework | |
Entanglement-guided architectures of machine learning by quantum tensor network
Title | Entanglement-guided architectures of machine learning by quantum tensor network |
Authors | Yuhan Liu, Xiao Zhang, Maciej Lewenstein, Shi-Ju Ran |
Abstract | It is a fundamental, but still elusive question whether the schemes based on quantum mechanics, in particular on quantum entanglement, can be used for classical information processing and machine learning. Even partial answer to this question would bring important insights to both fields of machine learning and quantum mechanics. In this work, we implement simple numerical experiments, related to pattern/images classification, in which we represent the classifiers by many-qubit quantum states written in the matrix product states (MPS). Classical machine learning algorithm is applied to these quantum states to learn the classical data. We explicitly show how quantum entanglement (i.e., single-site and bipartite entanglement) can emerge in such represented images. Entanglement characterizes here the importance of data, and such information are practically used to guide the architecture of MPS, and improve the efficiency. The number of needed qubits can be reduced to less than 1/10 of the original number, which is within the access of the state-of-the-art quantum computers. We expect such numerical experiments could open new paths in charactering classical machine learning algorithms, and at the same time shed lights on the generic quantum simulations/computations of machine learning tasks. |
Tasks | |
Published | 2018-03-24 |
URL | http://arxiv.org/abs/1803.09111v3 |
http://arxiv.org/pdf/1803.09111v3.pdf | |
PWC | https://paperswithcode.com/paper/entanglement-guided-architectures-of-machine |
Repo | |
Framework | |
Zoom: SSD-based Vector Search for Optimizing Accuracy, Latency and Memory
Title | Zoom: SSD-based Vector Search for Optimizing Accuracy, Latency and Memory |
Authors | Minjia Zhang, Yuxiong He |
Abstract | With the advancement of machine learning and deep learning, vector search becomes instrumental to many information retrieval systems, to search and find best matches to user queries based on their semantic similarities.These online services require the search architecture to be both effective with high accuracy and efficient with low latency and memory footprint, which existing work fails to offer. We develop, Zoom, a new vector search solution that collaboratively optimizes accuracy, latency and memory based on a multiview approach. (1) A “preview” step generates a small set of good candidates, leveraging compressed vectors in memory for reduced footprint and fast lookup. (2) A “fullview” step on SSDs reranks those candidates with their full-length vector, striking high accuracy. Our evaluation shows that, Zoom achieves an order of magnitude improvements on efficiency while attaining equal or higher accuracy, comparing with the state-of-the-art. |
Tasks | Information Retrieval |
Published | 2018-09-11 |
URL | http://arxiv.org/abs/1809.04067v1 |
http://arxiv.org/pdf/1809.04067v1.pdf | |
PWC | https://paperswithcode.com/paper/zoom-ssd-based-vector-search-for-optimizing |
Repo | |
Framework | |
The Evolution of Sex Chromosomes through the Baldwin Effect
Title | The Evolution of Sex Chromosomes through the Baldwin Effect |
Authors | Larry Bull |
Abstract | It has recently been suggested that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect. Thereafter the other associated phenomena can be explained as evolution tuning the amount and frequency of learning experienced by an organism. Using the well-known NK model of fitness landscapes it is here shown that the emergence of sex determination systems can also be explained under this view of eukaryotic evolution. |
Tasks | |
Published | 2018-08-10 |
URL | https://arxiv.org/abs/1808.03471v4 |
https://arxiv.org/pdf/1808.03471v4.pdf | |
PWC | https://paperswithcode.com/paper/the-evolution-of-sex-chromosomes-through-the |
Repo | |
Framework | |
Graphical Convergence of Subgradients in Nonconvex Optimization and Learning
Title | Graphical Convergence of Subgradients in Nonconvex Optimization and Learning |
Authors | Damek Davis, Dmitriy Drusvyatskiy |
Abstract | We investigate the stochastic optimization problem of minimizing population risk, where the loss defining the risk is assumed to be weakly convex. Compositions of Lipschitz convex functions with smooth maps are the primary examples of such losses. We analyze the estimation quality of such nonsmooth and nonconvex problems by their sample average approximations. Our main results establish dimension-dependent rates on subgradient estimation in full generality and dimension-independent rates when the loss is a generalized linear model. As an application of the developed techniques, we analyze the nonsmooth landscape of a robust nonlinear regression problem. |
Tasks | Stochastic Optimization |
Published | 2018-10-17 |
URL | http://arxiv.org/abs/1810.07590v2 |
http://arxiv.org/pdf/1810.07590v2.pdf | |
PWC | https://paperswithcode.com/paper/graphical-convergence-of-subgradients-in |
Repo | |
Framework | |
Data-dependent compression of random features for large-scale kernel approximation
Title | Data-dependent compression of random features for large-scale kernel approximation |
Authors | Raj Agrawal, Trevor Campbell, Jonathan H. Huggins, Tamara Broderick |
Abstract | Kernel methods offer the flexibility to learn complex relationships in modern, large data sets while enjoying strong theoretical guarantees on quality. Unfortunately, these methods typically require cubic running time in the data set size, a prohibitive cost in the large-data setting. Random feature maps (RFMs) and the Nystrom method both consider low-rank approximations to the kernel matrix as a potential solution. But, in order to achieve desirable theoretical guarantees, the former may require a prohibitively large number of features J+, and the latter may be prohibitively expensive for high-dimensional problems. We propose to combine the simplicity and generality of RFMs with a data-dependent feature selection scheme to achieve desirable theoretical approximation properties of Nystrom with just O(log J+) features. Our key insight is to begin with a large set of random features, then reduce them to a small number of weighted features in a data-dependent, computationally efficient way, while preserving the statistical guarantees of using the original large set of features. We demonstrate the efficacy of our method with theory and experiments–including on a data set with over 50 million observations. In particular, we show that our method achieves small kernel matrix approximation error and better test set accuracy with provably fewer random features than state-of-the-art methods. |
Tasks | Feature Selection |
Published | 2018-10-09 |
URL | http://arxiv.org/abs/1810.04249v2 |
http://arxiv.org/pdf/1810.04249v2.pdf | |
PWC | https://paperswithcode.com/paper/data-dependent-compression-of-random-features |
Repo | |
Framework | |
On the optimality of the Hedge algorithm in the stochastic regime
Title | On the optimality of the Hedge algorithm in the stochastic regime |
Authors | Jaouad Mourtada, Stéphane Gaïffas |
Abstract | In this paper, we study the behavior of the Hedge algorithm in the online stochastic setting. We prove that anytime Hedge with decreasing learning rate, which is one of the simplest algorithm for the problem of prediction with expert advice, is surprisingly both worst-case optimal and adaptive to the easier stochastic and adversarial with a gap problems. This shows that, in spite of its small, non-adaptive learning rate, Hedge possesses the same optimal regret guarantee in the stochastic case as recently introduced adaptive algorithms. Moreover, our analysis exhibits qualitative differences with other variants of the Hedge algorithm, such as the fixed-horizon version (with constant learning rate) and the one based on the so-called “doubling trick”, both of which fail to adapt to the easier stochastic setting. Finally, we discuss the limitations of anytime Hedge and the improvements provided by second-order regret bounds in the stochastic case. |
Tasks | |
Published | 2018-09-05 |
URL | https://arxiv.org/abs/1809.01382v3 |
https://arxiv.org/pdf/1809.01382v3.pdf | |
PWC | https://paperswithcode.com/paper/on-the-optimality-of-the-hedge-algorithm-in |
Repo | |
Framework | |
Interpreting Winograd Schemas Via the SP Theory of Intelligence and Its Realisation in the SP Computer Model
Title | Interpreting Winograd Schemas Via the SP Theory of Intelligence and Its Realisation in the SP Computer Model |
Authors | J Gerard Wolff |
Abstract | In ‘Winograd Schema’ (WS) sentences like “The city councilmen refused the demonstrators a permit because they feared violence” and “The city councilmen refused the demonstrators a permit because they advocated revolution”, it is easy for adults to understand what “they” refers to but can be difficult for AI systems. This paper describes how the SP System – outlined in an appendix – may solve this kind of problem of interpretation. The central idea is that a knowledge of discontinuous associations amongst linguistic features, and an ability to recognise such patterns of associations, provides a robust means of determining what a pronoun like “they” refers to. For any AI system to solve this kind of problem, it needs appropriate knowledge of relevant syntax and semantics which, ideally, it should learn for itself. Although the SP System has some strengths in unsupervised learning, its capabilities in this area are not yet good enough to learn the kind of knowledge needed to interpret WS examples, so it must be supplied with such knowledge at the outset. However, its existing strengths in unsupervised learning suggest that it has potential to learn the kind of knowledge needed for the interpretation of WS examples. In particular, it has potential to learn the kind of discontinuous association of linguistic features mentioned earlier. |
Tasks | |
Published | 2018-10-09 |
URL | http://arxiv.org/abs/1810.04554v1 |
http://arxiv.org/pdf/1810.04554v1.pdf | |
PWC | https://paperswithcode.com/paper/interpreting-winograd-schemas-via-the-sp |
Repo | |
Framework | |
Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing
Title | Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing |
Authors | A. Gomez Ramirez, C. Lara, L. Betev, D. Bilanovic, U. Kebschull, for the ALICE Collaboration |
Abstract | Grid computing systems require innovative methods and tools to identify cybersecurity incidents and perform autonomous actions i.e. without administrator intervention. They also require methods to isolate and trace job payload activity in order to protect users and find evidence of malicious behavior. We introduce an integrated approach of security monitoring via Security by Isolation with Linux Containers and Deep Learning methods for the analysis of real time data in Grid jobs running inside virtualized High-Throughput Computing infrastructure in order to detect and prevent intrusions. A dataset for malware detection in Grid computing is described. We show in addition the utilization of generative methods with Recurrent Neural Networks to improve the collected dataset. We present Arhuaco, a prototype implementation of the proposed methods. We empirically study the performance of our technique. The results show that Arhuaco outperforms other methods used in Intrusion Detection Systems for Grid Computing. The study is carried out in the ALICE Collaboration Grid, part of the Worldwide LHC Computing Grid. |
Tasks | Intrusion Detection, Malware Detection |
Published | 2018-01-12 |
URL | http://arxiv.org/abs/1801.04179v1 |
http://arxiv.org/pdf/1801.04179v1.pdf | |
PWC | https://paperswithcode.com/paper/arhuaco-deep-learning-and-isolation-based |
Repo | |
Framework | |
Practical Design Space Exploration
Title | Practical Design Space Exploration |
Authors | Luigi Nardi, David Koeplinger, Kunle Olukotun |
Abstract | Multi-objective optimization is a crucial matter in computer systems design space exploration because real-world applications often rely on a trade-off between several objectives. Derivatives are usually not available or impractical to compute and the feasibility of an experiment can not always be determined in advance. These problems are particularly difficult when the feasible region is relatively small, and it may be prohibitive to even find a feasible experiment, let alone an optimal one. We introduce a new methodology and corresponding software framework, HyperMapper 2.0, which handles multi-objective optimization, unknown feasibility constraints, and categorical/ordinal variables. This new methodology also supports injection of the user prior knowledge in the search when available. All of these features are common requirements in computer systems but rarely exposed in existing design space exploration systems. The proposed methodology follows a white-box model which is simple to understand and interpret (unlike, for example, neural networks) and can be used by the user to better understand the results of the automatic search. We apply and evaluate the new methodology to the automatic static tuning of hardware accelerators within the recently introduced Spatial programming language, with minimization of design run-time and compute logic under the constraint of the design fitting in a target field-programmable gate array chip. Our results show that HyperMapper 2.0 provides better Pareto fronts compared to state-of-the-art baselines, with better or competitive hypervolume indicator and with 8x improvement in sampling budget for most of the benchmarks explored. |
Tasks | |
Published | 2018-10-11 |
URL | https://arxiv.org/abs/1810.05236v3 |
https://arxiv.org/pdf/1810.05236v3.pdf | |
PWC | https://paperswithcode.com/paper/practical-design-space-exploration |
Repo | |
Framework | |
A Multilingual Study of Compressive Cross-Language Text Summarization
Title | A Multilingual Study of Compressive Cross-Language Text Summarization |
Authors | Elvys Linhares Pontes, Stéphane Huet, Juan-Manuel Torres-Moreno |
Abstract | Cross-Language Text Summarization (CLTS) generates summaries in a language different from the language of the source documents. Recent methods use information from both languages to generate summaries with the most informative sentences. However, these methods have performance that can vary according to languages, which can reduce the quality of summaries. In this paper, we propose a compressive framework to generate cross-language summaries. In order to analyze performance and especially stability, we tested our system and extractive baselines on a dataset available in four languages (English, French, Portuguese, and Spanish) to generate English and French summaries. An automatic evaluation showed that our method outperformed extractive state-of-art CLTS methods with better and more stable ROUGE scores for all languages. |
Tasks | Cross-Language Text Summarization, Text Summarization |
Published | 2018-10-24 |
URL | http://arxiv.org/abs/1810.10639v1 |
http://arxiv.org/pdf/1810.10639v1.pdf | |
PWC | https://paperswithcode.com/paper/a-multilingual-study-of-compressive-cross |
Repo | |
Framework | |
Pyramid Embedded Generative Adversarial Network for Automated Font Generation
Title | Pyramid Embedded Generative Adversarial Network for Automated Font Generation |
Authors | Donghui Sun, Qing Zhang, Jun Yang |
Abstract | In this paper, we investigate the Chinese font synthesis problem and propose a Pyramid Embedded Generative Adversarial Network (PEGAN) to automatically generate Chinese character images. The PEGAN consists of one generator and one discriminator. The generator is built using one encoder-decoder structure with cascaded refinement connections and mirror skip connections. The cascaded refinement connections embed a multiscale pyramid of downsampled original input into the encoder feature maps of different layers, and multi-scale feature maps from the encoder are connected to the corresponding feature maps in the decoder to make the mirror skip connections. Through combining the generative adversarial loss, pixel-wise loss, category loss and perceptual loss, the generator and discriminator can be trained alternately to synthesize character images. In order to verify the effectiveness of our proposed PEGAN, we first build one evaluation set, in which the characters are selected according to their stroke number and frequency of use, and then use both qualitative and quantitative metrics to measure the performance of our model comparing with the baseline method. The experimental results demonstrate the effectiveness of our proposed model, it shows the potential to automatically extend small font banks into complete ones. |
Tasks | |
Published | 2018-11-20 |
URL | http://arxiv.org/abs/1811.08106v1 |
http://arxiv.org/pdf/1811.08106v1.pdf | |
PWC | https://paperswithcode.com/paper/pyramid-embedded-generative-adversarial |
Repo | |
Framework | |
Summarizing User-generated Textual Content: Motivation and Methods for Fairness in Algorithmic Summaries
Title | Summarizing User-generated Textual Content: Motivation and Methods for Fairness in Algorithmic Summaries |
Authors | Abhisek Dash, Anurag Shandilya, Arindam Biswas, Kripabandhu Ghosh, Saptarshi Ghosh, Abhijnan Chakraborty |
Abstract | As the amount of user-generated textual content grows rapidly, text summarization algorithms are increasingly being used to provide users a quick overview of the information content. Traditionally, summarization algorithms have been evaluated only based on how well they match human-written summaries (e.g. as measured by ROUGE scores). In this work, we propose to evaluate summarization algorithms from a completely new perspective that is important when the user-generated data to be summarized comes from different socially salient user groups, e.g. men or women, Caucasians or African-Americans, or different political groups (Republicans or Democrats). In such cases, we check whether the generated summaries fairly represent these different social groups. Specifically, considering that an extractive summarization algorithm selects a subset of the textual units (e.g. microblogs) in the original data for inclusion in the summary, we investigate whether this selection is fair or not. Our experiments over real-world microblog datasets show that existing summarization algorithms often represent the socially salient user-groups very differently compared to their distributions in the original data. More importantly, some groups are frequently under-represented in the generated summaries, and hence get far less exposure than what they would have obtained in the original data. To reduce such adverse impacts, we propose novel fairness-preserving summarization algorithms which produce high-quality summaries while ensuring fairness among various groups. To our knowledge, this is the first attempt to produce fair text summarization, and is likely to open up an interesting research direction. |
Tasks | Text Summarization |
Published | 2018-10-22 |
URL | https://arxiv.org/abs/1810.09147v5 |
https://arxiv.org/pdf/1810.09147v5.pdf | |
PWC | https://paperswithcode.com/paper/fairness-preserving-text-summarzation |
Repo | |
Framework | |
Deep Transfer Reinforcement Learning for Text Summarization
Title | Deep Transfer Reinforcement Learning for Text Summarization |
Authors | Yaser Keneshloo, Naren Ramakrishnan, Chandan K. Reddy |
Abstract | Deep neural networks are data hungry models and thus face difficulties when attempting to train on small text datasets. Transfer learning is a potential solution but their effectiveness in the text domain is not as explored as in areas such as image analysis. In this paper, we study the problem of transfer learning for text summarization and discuss why existing state-of-the-art models fail to generalize well on other (unseen) datasets. We propose a reinforcement learning framework based on a self-critic policy gradient approach which achieves good generalization and state-of-the-art results on a variety of datasets. Through an extensive set of experiments, we also show the ability of our proposed framework to fine-tune the text summarization model using only a few training samples. To the best of our knowledge, this is the first work that studies transfer learning in text summarization and provides a generic solution that works well on unseen data. |
Tasks | Text Summarization, Transfer Learning, Transfer Reinforcement Learning |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06667v2 |
http://arxiv.org/pdf/1810.06667v2.pdf | |
PWC | https://paperswithcode.com/paper/deep-transfer-reinforcement-learning-for-text |
Repo | |
Framework | |
On The Inductive Bias of Words in Acoustics-to-Word Models
Title | On The Inductive Bias of Words in Acoustics-to-Word Models |
Authors | Hao Tang, James Glass |
Abstract | Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is also unclear how the amount of training data impacts the optimization and generalization of such models. In this work, we study the optimization and generalization of acoustics-to-word models under different amounts of training data. In addition, we study three types of inductive bias, leveraging a pronunciation dictionary, word boundary annotations, and constraints on word durations. We find that constraining word durations leads to the most improvement. Finally, we analyze the word embedding space learned by the model, and find that the space has a structure dominated by the pronunciation of words. This suggests that the contexts of words, instead of their phonetic structure, should be the future focus of inductive bias in acoustics-to-word models. |
Tasks | |
Published | 2018-10-31 |
URL | http://arxiv.org/abs/1810.13407v2 |
http://arxiv.org/pdf/1810.13407v2.pdf | |
PWC | https://paperswithcode.com/paper/on-the-inductive-bias-of-words-in-acoustics |
Repo | |
Framework | |