Paper Group ANR 414
Non-stationary Stochastic Optimization under $L_{p,q}$-Variation Measures. A Variational Approach to Shape-from-shading Under Natural Illumination. A Geometric Approach to Harmonic Color Palette Design. Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reduction. Differentially Private Dropout. Identification …
Non-stationary Stochastic Optimization under $L_{p,q}$-Variation Measures
| Title | Non-stationary Stochastic Optimization under $L_{p,q}$-Variation Measures |
| Authors | Xi Chen, Yining Wang, Yu-Xiang Wang |
| Abstract | We consider a non-stationary sequential stochastic optimization problem, in which the underlying cost functions change over time under a variation budget constraint. We propose an $L_{p,q}$-variation functional to quantify the change, which yields less variation for dynamic function sequences whose changes are constrained to short time periods or small subsets of input domain. Under the $L_{p,q}$-variation constraint, we derive both upper and matching lower regret bounds for smooth and strongly convex function sequences, which generalize previous results in Besbes et al. (2015). Furthermore, we provide an upper bound for general convex function sequences with noisy gradient feedback, which matches the optimal rate as $p\to\infty$. Our results reveal some surprising phenomena under this general variation functional, such as the curse of dimensionality of the function domain. The key technical novelties in our analysis include affinity lemmas that characterize the distance of the minimizers of two convex functions with bounded Lp difference, and a cubic spline based construction that attains matching lower bounds. |
| Tasks | Stochastic Optimization |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.03020v3 |
| http://arxiv.org/pdf/1708.03020v3.pdf | |
| PWC | https://paperswithcode.com/paper/non-stationary-stochastic-optimization-under |
| Repo | |
| Framework | |
A Variational Approach to Shape-from-shading Under Natural Illumination
| Title | A Variational Approach to Shape-from-shading Under Natural Illumination |
| Authors | Yvain Quéau, Jean Mélou, Fabien Castan, Daniel Cremers, Jean-Denis Durou |
| Abstract | A numerical solution to shape-from-shading under natural illumination is presented. It builds upon an augmented Lagrangian approach for solving a generic PDE-based shape-from-shading model which handles directional or spherical harmonic lighting, orthographic or perspective projection, and greylevel or multi-channel images. Real-world applications to shading-aware depth map denoising, refinement and completion are presented. |
| Tasks | Denoising |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10354v2 |
| http://arxiv.org/pdf/1709.10354v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-variational-approach-to-shape-from-shading |
| Repo | |
| Framework | |
A Geometric Approach to Harmonic Color Palette Design
| Title | A Geometric Approach to Harmonic Color Palette Design |
| Authors | Carlos Lara-Alvarez, Tania Reyes |
| Abstract | We address the problem of finding harmonic colors, this problem has many applications, from fashion to industrial design. In order to solve this problem we consider that colors follow normal distributions in tone (chroma and lightness) and hue. The proposed approach relies in the CIE standard for representing colors and evaluate proximity. Other approaches to this problem use a set of rules. Experimental results show that lines with specific parameters angles of inclination, and distance from the reference point are preferred over others, and that uncertain line patterns outperform non-linear patterns. |
| Tasks | |
| Published | 2017-09-04 |
| URL | http://arxiv.org/abs/1709.02252v1 |
| http://arxiv.org/pdf/1709.02252v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-geometric-approach-to-harmonic-color |
| Repo | |
| Framework | |
Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reduction
| Title | Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reduction |
| Authors | Yanwei Pang, Bo Zhou, Feiping Nie |
| Abstract | Explicitly or implicitly, most of dimensionality reduction methods need to determine which samples are neighbors and the similarity between the neighbors in the original highdimensional space. The projection matrix is then learned on the assumption that the neighborhood information (e.g., the similarity) is known and fixed prior to learning. However, it is difficult to precisely measure the intrinsic similarity of samples in high-dimensional space because of the curse of dimensionality. Consequently, the neighbors selected according to such similarity might and the projection matrix obtained according to such similarity and neighbors are not optimal in the sense of classification and generalization. To overcome the drawbacks, in this paper we propose to let the similarity and neighbors be variables and model them in low-dimensional space. Both the optimal similarity and projection matrix are obtained by minimizing a unified objective function. Nonnegative and sum-to-one constraints on the similarity are adopted. Instead of empirically setting the regularization parameter, we treat it as a variable to be optimized. It is interesting that the optimal regularization parameter is adaptive to the neighbors in low-dimensional space and has intuitive meaning. Experimental results on the YALE B, COIL-100, and MNIST datasets demonstrate the effectiveness of the proposed method. |
| Tasks | Dimensionality Reduction |
| Published | 2017-09-09 |
| URL | http://arxiv.org/abs/1709.02896v1 |
| http://arxiv.org/pdf/1709.02896v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneously-learning-neighborship-and |
| Repo | |
| Framework | |
Differentially Private Dropout
| Title | Differentially Private Dropout |
| Authors | Beyza Ermis, Ali Taylan Cemgil |
| Abstract | Large data collections required for the training of neural networks often contain sensitive information such as the medical histories of patients, and the privacy of the training data must be preserved. In this paper, we introduce a dropout technique that provides an elegant Bayesian interpretation to dropout, and show that the intrinsic noise added, with the primary goal of regularization, can be exploited to obtain a degree of differential privacy. The iterative nature of training neural networks presents a challenge for privacy-preserving estimation since multiple iterations increase the amount of noise added. We overcome this by using a relaxed notion of differential privacy, called concentrated differential privacy, which provides tighter estimates on the overall privacy loss. We demonstrate the accuracy of our privacy-preserving dropout algorithm on benchmark datasets. |
| Tasks | |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1712.01665v1 |
| http://arxiv.org/pdf/1712.01665v1.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-dropout |
| Repo | |
| Framework | |
Identification and Interpretation of Belief Structure in Dempster-Shafer Theory
| Title | Identification and Interpretation of Belief Structure in Dempster-Shafer Theory |
| Authors | Mieczysław A. Kłopotek |
| Abstract | Mathematical Theory of Evidence called also Dempster-Shafer Theory (DST) is known as a foundation for reasoning when knowledge is expressed at various levels of detail. Though much research effort has been committed to this theory since its foundation, many questions remain open. One of the most important open questions seems to be the relationship between frequencies and the Mathematical Theory of Evidence. The theory is blamed to leave frequencies outside (or aside of) its framework. The seriousness of this accusation is obvious: (1) no experiment may be run to compare the performance of DST-based models of real world processes against real world data, (2) data may not serve as foundation for construction of an appropriate belief model. In this paper we develop a frequentist interpretation of the DST bringing to fall the above argument against DST. An immediate consequence of it is the possibility to develop algorithms acquiring automatically DST belief models from data. We propose three such algorithms for various classes of belief model structures: for tree structured belief networks, for poly-tree belief networks and for general type belief networks. |
| Tasks | |
| Published | 2017-07-12 |
| URL | http://arxiv.org/abs/1707.03881v1 |
| http://arxiv.org/pdf/1707.03881v1.pdf | |
| PWC | https://paperswithcode.com/paper/identification-and-interpretation-of-belief |
| Repo | |
| Framework | |
Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis
| Title | Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis |
| Authors | Zimo Li, Yi Zhou, Shuangjiu Xiao, Chong He, Zeng Huang, Hao Li |
| Abstract | We present a real-time method for synthesizing highly complex human motions using a novel training regime we call the auto-conditioned Recurrent Neural Network (acRNN). Recently, researchers have attempted to synthesize new motion by using autoregressive techniques, but existing methods tend to freeze or diverge after a couple of seconds due to an accumulation of errors that are fed back into the network. Furthermore, such methods have only been shown to be reliable for relatively simple human motions, such as walking or running. In contrast, our approach can synthesize arbitrary motions with highly complex styles, including dances or martial arts in addition to locomotion. The acRNN is able to accomplish this by explicitly accommodating for autoregressive noise accumulation during training. Our work is the first to our knowledge that demonstrates the ability to generate over 18,000 continuous frames (300 seconds) of new complex human motion w.r.t. different styles. |
| Tasks | |
| Published | 2017-07-17 |
| URL | http://arxiv.org/abs/1707.05363v5 |
| http://arxiv.org/pdf/1707.05363v5.pdf | |
| PWC | https://paperswithcode.com/paper/auto-conditioned-recurrent-networks-for |
| Repo | |
| Framework | |
Identifying Subjective and Figurative Language in Online Dialogue
| Title | Identifying Subjective and Figurative Language in Online Dialogue |
| Authors | Stephanie M. Lukin, Luke Eisenberg, Thomas Corcoran, Marilyn A. Walker |
| Abstract | More and more of the information on the web is dialogic, from Facebook newsfeeds, to forum conversations, to comment threads on news articles. In contrast to traditional, monologic resources such as news, highly social dialogue is very frequent in social media. We aim to automatically identify sarcastic and nasty utterances in unannotated online dialogue, extending a bootstrapping method previously applied to the classification of monologic subjective sentences in Riloff and Weibe 2003. We have adapted the method to fit the sarcastic and nasty dialogic domain. Our method is as follows: 1) Explore methods for identifying sarcastic and nasty cue words and phrases in dialogues; 2) Use the learned cues to train a sarcastic (nasty) Cue-Based Classifier; 3) Learn general syntactic extraction patterns from the sarcastic (nasty) utterances and define fine-tuned sarcastic patterns to create a Pattern-Based Classifier; 4) Combine both Cue-Based and fine-tuned Pattern-Based Classifiers to maximize precision at the expense of recall and test on unannotated utterances. |
| Tasks | |
| Published | 2017-08-29 |
| URL | http://arxiv.org/abs/1708.08575v1 |
| http://arxiv.org/pdf/1708.08575v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-subjective-and-figurative |
| Repo | |
| Framework | |
Reinterpreting Importance-Weighted Autoencoders
| Title | Reinterpreting Importance-Weighted Autoencoders |
| Authors | Chris Cremer, Quaid Morris, David Duvenaud |
| Abstract | The standard interpretation of importance-weighted autoencoders is that they maximize a tighter lower bound on the marginal likelihood than the standard evidence lower bound. We give an alternate interpretation of this procedure: that it optimizes the standard variational lower bound, but using a more complex distribution. We formally derive this result, present a tighter lower bound, and visualize the implicit importance-weighted distribution. |
| Tasks | |
| Published | 2017-04-10 |
| URL | http://arxiv.org/abs/1704.02916v2 |
| http://arxiv.org/pdf/1704.02916v2.pdf | |
| PWC | https://paperswithcode.com/paper/reinterpreting-importance-weighted |
| Repo | |
| Framework | |
Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars
| Title | Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars |
| Authors | Chenfanfu Jiang, Siyuan Qi, Yixin Zhu, Siyuan Huang, Jenny Lin, Lap-Fai Yu, Demetri Terzopoulos, Song-Chun Zhu |
| Abstract | We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms. In particular, we devise a learning-based pipeline of algorithms capable of automatically generating and rendering a potentially infinite variety of indoor scenes by using a stochastic grammar, represented as an attributed Spatial And-Or Graph, in conjunction with state-of-the-art physics-based rendering. Our pipeline is capable of synthesizing scene layouts with high diversity, and it is configurable inasmuch as it enables the precise customization and control of important attributes of the generated scenes. It renders photorealistic RGB images of the generated scenes while automatically synthesizing detailed, per-pixel ground truth data, including visible surface depth and normal, object identity, and material information (detailed to object parts), as well as environments (e.g., illuminations and camera viewpoints). We demonstrate the value of our synthesized dataset, by improving performance in certain machine-learning-based scene understanding tasks–depth and surface normal prediction, semantic segmentation, reconstruction, etc.–and by providing benchmarks for and diagnostics of trained models by modifying object attributes and scene properties in a controllable manner. |
| Tasks | Scene Understanding, Semantic Segmentation |
| Published | 2017-04-01 |
| URL | http://arxiv.org/abs/1704.00112v3 |
| http://arxiv.org/pdf/1704.00112v3.pdf | |
| PWC | https://paperswithcode.com/paper/configurable-3d-scene-synthesis-and-2d-image |
| Repo | |
| Framework | |
Fast and reliable inference algorithm for hierarchical stochastic block models
| Title | Fast and reliable inference algorithm for hierarchical stochastic block models |
| Authors | Yongjin Park, Joel S. Bader |
| Abstract | Network clustering reveals the organization of a network or corresponding complex system with elements represented as vertices and interactions as edges in a (directed, weighted) graph. Although the notion of clustering can be somewhat loose, network clusters or groups are generally considered as nodes with enriched interactions and edges sharing common patterns. Statistical inference often treats groups as latent variables, with observed networks generated from latent group structure, termed a stochastic block model. Regardless of the definitions, statistical inference can be either translated to modularity maximization, which is provably an NP-complete problem. Here we present scalable and reliable algorithms that recover hierarchical stochastic block models fast and accurately. Our algorithm scales almost linearly in number of edges, and inferred models were more accurate that other scalable methods. |
| Tasks | |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.05150v1 |
| http://arxiv.org/pdf/1711.05150v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-reliable-inference-algorithm-for |
| Repo | |
| Framework | |
Active Decision Boundary Annotation with Deep Generative Models
| Title | Active Decision Boundary Annotation with Deep Generative Models |
| Authors | Miriam W. Huijser, Jan C. van Gemert |
| Abstract | This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training. Standard active learning methods ask the oracle to annotate data samples. Instead, we take a profoundly different approach: we ask for annotations of the decision boundary. We achieve this using a deep generative model to create novel instances along a 1d line. A point on the decision boundary is revealed where the instances change class. Experimentally we show on three data sets that our method can be plugged-in to other active learning schemes, that human oracles can effectively annotate points on the decision boundary, that our method is robust to annotation noise, and that decision boundary annotations improve over annotating data samples. |
| Tasks | Active Learning |
| Published | 2017-03-20 |
| URL | http://arxiv.org/abs/1703.06971v2 |
| http://arxiv.org/pdf/1703.06971v2.pdf | |
| PWC | https://paperswithcode.com/paper/active-decision-boundary-annotation-with-deep |
| Repo | |
| Framework | |
Frame Stacking and Retaining for Recurrent Neural Network Acoustic Model
| Title | Frame Stacking and Retaining for Recurrent Neural Network Acoustic Model |
| Authors | Xu Tian, Jun Zhang, Zejun Ma, Yi He, Juan Wei |
| Abstract | Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural network based on context-dependent state acoustic model, if the decoder is unchanged. In this paper, we propose a novel frame retaining method which is applied in decoding. The system which combined frame retaining with frame stacking could reduces the time consumption of both training and decoding. Long short-term memory (LSTM) recurrent neural networks (RNNs) using it achieve almost linear training speedup and reduces relative 41% real time factor (RTF). At the same time, recognition performance is no degradation or improves sightly on Shenma voice search dataset in Mandarin. |
| Tasks | |
| Published | 2017-05-17 |
| URL | http://arxiv.org/abs/1705.05992v1 |
| http://arxiv.org/pdf/1705.05992v1.pdf | |
| PWC | https://paperswithcode.com/paper/frame-stacking-and-retaining-for-recurrent |
| Repo | |
| Framework | |
Fundamental Matrix Estimation: A Study of Error Criteria
| Title | Fundamental Matrix Estimation: A Study of Error Criteria |
| Authors | Mohammed E. Fathy, Ashraf S. Hussein, Mohammed F. Tolba |
| Abstract | The fundamental matrix (FM) describes the geometric relations that exist between two images of the same scene. Different error criteria are used for estimating FMs from an input set of correspondences. In this paper, the accuracy and efficiency aspects of the different error criteria were studied. We mathematically and experimentally proved that the most popular error criterion, the symmetric epipolar distance, is biased. It was also shown that despite the similarity between the algebraic expressions of the symmetric epipolar distance and Sampson distance, they have different accuracy properties. In addition, a new error criterion, Kanatani distance, was proposed and was proved to be the most effective for use during the outlier removal phase from accuracy and efficiency perspectives. To thoroughly test the accuracy of the different error criteria, we proposed a randomized algorithm for Reprojection Error-based Correspondence Generation (RE-CG). As input, RE-CG takes an FM and a desired reprojection error value $d$. As output, RE-CG generates a random correspondence having that error value. Mathematical analysis of this algorithm revealed that the success probability for any given trial is 1 - (2/3)^2 at best and is 1 - (6/7)^2 at worst while experiments demonstrated that the algorithm often succeeds after only one trial. |
| Tasks | |
| Published | 2017-06-24 |
| URL | http://arxiv.org/abs/1706.07886v1 |
| http://arxiv.org/pdf/1706.07886v1.pdf | |
| PWC | https://paperswithcode.com/paper/fundamental-matrix-estimation-a-study-of |
| Repo | |
| Framework | |
Generating Sentence Planning Variations for Story Telling
| Title | Generating Sentence Planning Variations for Story Telling |
| Authors | Stephanie M. Lukin, Lena I. Reed, Marilyn A. Walker |
| Abstract | There has been a recent explosion in applications for dialogue interaction ranging from direction-giving and tourist information to interactive story systems. Yet the natural language generation (NLG) component for many of these systems remains largely handcrafted. This limitation greatly restricts the range of applications; it also means that it is impossible to take advantage of recent work in expressive and statistical language generation that can dynamically and automatically produce a large number of variations of given content. We propose that a solution to this problem lies in new methods for developing language generation resources. We describe the ES-Translator, a computational language generator that has previously been applied only to fables, and quantitatively evaluate the domain independence of the EST by applying it to personal narratives from weblogs. We then take advantage of recent work on language generation to create a parameterized sentence planner for story generation that provides aggregation operations, variations in discourse and in point of view. Finally, we present a user evaluation of different personal narrative retellings. |
| Tasks | Text Generation |
| Published | 2017-08-29 |
| URL | http://arxiv.org/abs/1708.08580v1 |
| http://arxiv.org/pdf/1708.08580v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-sentence-planning-variations-for |
| Repo | |
| Framework | |
