Paper Group ANR 199
Classifying Options for Deep Reinforcement Learning. Inductive supervised quantum learning. Coherence Pursuit: Fast, Simple, and Robust Principal Component Analysis. Determination of Pedestrian Flow Performance Based on Video Tracking and Microscopic Simulations. Polyhedron Volume-Ratio-based Classification for Image Recognition. Charagram: Embeddi …
Classifying Options for Deep Reinforcement Learning
| Title | Classifying Options for Deep Reinforcement Learning |
| Authors | Kai Arulkumaran, Nat Dilokthanakul, Murray Shanahan, Anil Anthony Bharath |
| Abstract | In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different “option heads” on the policy network, and a supervisory network for choosing between the different options. We utilise our setup to investigate the effects of architectural constraints in subtasks with positive and negative transfer, across a range of network capacities. We empirically show that our augmented DQN has lower sample complexity when simultaneously learning subtasks with negative transfer, without degrading performance when learning subtasks with positive transfer. |
| Tasks | Hierarchical Reinforcement Learning |
| Published | 2016-04-27 |
| URL | http://arxiv.org/abs/1604.08153v3 |
| http://arxiv.org/pdf/1604.08153v3.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-options-for-deep-reinforcement |
| Repo | |
| Framework | |
Inductive supervised quantum learning
| Title | Inductive supervised quantum learning |
| Authors | Alex Monràs, Gael Sentís, Peter Wittek |
| Abstract | In supervised learning, an inductive learning algorithm extracts general rules from observed training instances, then the rules are applied to test instances. We show that this splitting of training and application arises naturally, in the classical setting, from a simple independence requirement with a physical interpretation of being non-signalling. Thus, two seemingly different definitions of inductive learning happen to coincide. This follows from the properties of classical information that break down in the quantum setup. We prove a quantum de Finetti theorem for quantum channels, which shows that in the quantum case, the equivalence holds in the asymptotic setting, that is, for large number of test instances. This reveals a natural analogy between classical learning protocols and their quantum counterparts, justifying a similar treatment, and allowing to inquire about standard elements in computational learning theory, such as structural risk minimization and sample complexity. |
| Tasks | |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07541v2 |
| http://arxiv.org/pdf/1605.07541v2.pdf | |
| PWC | https://paperswithcode.com/paper/inductive-supervised-quantum-learning |
| Repo | |
| Framework | |
Coherence Pursuit: Fast, Simple, and Robust Principal Component Analysis
| Title | Coherence Pursuit: Fast, Simple, and Robust Principal Component Analysis |
| Authors | Mostafa Rahmani, George Atia |
| Abstract | This paper presents a remarkably simple, yet powerful, algorithm termed Coherence Pursuit (CoP) to robust Principal Component Analysis (PCA). As inliers lie in a low dimensional subspace and are mostly correlated, an inlier is likely to have strong mutual coherence with a large number of data points. By contrast, outliers either do not admit low dimensional structures or form small clusters. In either case, an outlier is unlikely to bear strong resemblance to a large number of data points. Given that, CoP sets an outlier apart from an inlier by comparing their coherence with the rest of the data points. The mutual coherences are computed by forming the Gram matrix of the normalized data points. Subsequently, the sought subspace is recovered from the span of the subset of the data points that exhibit strong coherence with the rest of the data. As CoP only involves one simple matrix multiplication, it is significantly faster than the state-of-the-art robust PCA algorithms. We derive analytical performance guarantees for CoP under different models for the distributions of inliers and outliers in both noise-free and noisy settings. CoP is the first robust PCA algorithm that is simultaneously non-iterative, provably robust to both unstructured and structured outliers, and can tolerate a large number of unstructured outliers. |
| Tasks | |
| Published | 2016-09-15 |
| URL | http://arxiv.org/abs/1609.04789v3 |
| http://arxiv.org/pdf/1609.04789v3.pdf | |
| PWC | https://paperswithcode.com/paper/coherence-pursuit-fast-simple-and-robust-1 |
| Repo | |
| Framework | |
Determination of Pedestrian Flow Performance Based on Video Tracking and Microscopic Simulations
| Title | Determination of Pedestrian Flow Performance Based on Video Tracking and Microscopic Simulations |
| Authors | Kardi Teknomo, Yasushi Takeyama, Hajime Inamura |
| Abstract | One of the objectives of understanding pedestrian behavior is to predict the effect of proposed changes in the design or evaluation of pedestrian facilities. We want to know the impact to the user of the facilities, as the design of the facilities change. That impact was traditionally evaluated by level of service standards. Another design criterion to measure the impact of design change is measured by the pedestrian flow performance index. This paper describes the determination of pedestrian flow performance based video tracking or any microscopic pedestrian simulation models. Most of pedestrian researches have been done on a macroscopic level, which is an aggregation of all pedestrian movement in pedestrian areas into flow, average speed and area module. Macroscopic level, however, does not consider the interaction between pedestrians. It is also not well suited for prediction of pedestrian flow performance in pedestrian areas or in buildings with some obstruction, that reduces the effective width of the walkways. On the other hand, the microscopic level has a more general usage and considers detail in the design. More efficient pedestrian flow can even be reached with less space. Those results have rejected the linearity assumption of space and flow in the macroscopic level. |
| Tasks | |
| Published | 2016-09-08 |
| URL | http://arxiv.org/abs/1609.02243v1 |
| http://arxiv.org/pdf/1609.02243v1.pdf | |
| PWC | https://paperswithcode.com/paper/determination-of-pedestrian-flow-performance |
| Repo | |
| Framework | |
Polyhedron Volume-Ratio-based Classification for Image Recognition
| Title | Polyhedron Volume-Ratio-based Classification for Image Recognition |
| Authors | Qingxiang Feng, Jeng-Shyang Pan, Jar-Ferr Yang, Yang-Ting Chou |
| Abstract | In this paper, a novel method, called polyhedron volume ratio classification (PVRC) is proposed for image recognition |
| Tasks | |
| Published | 2016-01-26 |
| URL | http://arxiv.org/abs/1601.07021v1 |
| http://arxiv.org/pdf/1601.07021v1.pdf | |
| PWC | https://paperswithcode.com/paper/polyhedron-volume-ratio-based-classification |
| Repo | |
| Framework | |
Charagram: Embedding Words and Sentences via Character n-grams
| Title | Charagram: Embedding Words and Sentences via Character n-grams |
| Authors | John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu |
| Abstract | We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear transformation to yield a low-dimensional embedding. We use three tasks for evaluation: word similarity, sentence similarity, and part-of-speech tagging. We demonstrate that Charagram embeddings outperform more complex architectures based on character-level recurrent and convolutional neural networks, achieving new state-of-the-art performance on several similarity tasks. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2016-07-10 |
| URL | http://arxiv.org/abs/1607.02789v1 |
| http://arxiv.org/pdf/1607.02789v1.pdf | |
| PWC | https://paperswithcode.com/paper/charagram-embedding-words-and-sentences-via |
| Repo | |
| Framework | |
Quantitative Analyses of Chinese Poetry of Tang and Song Dynasties: Using Changing Colors and Innovative Terms as Examples
| Title | Quantitative Analyses of Chinese Poetry of Tang and Song Dynasties: Using Changing Colors and Innovative Terms as Examples |
| Authors | Chao-Lin Liu |
| Abstract | Tang (618-907 AD) and Song (960-1279) dynasties are two very important periods in the development of Chinese literary. The most influential forms of the poetry in Tang and Song were Shi and Ci, respectively. Tang Shi and Song Ci established crucial foundations of the Chinese literature, and their influences in both literary works and daily lives of the Chinese communities last until today. We can analyze and compare the Complete Tang Shi and the Complete Song Ci from various viewpoints. In this presentation, we report our findings about the differences in their vocabularies. Interesting new words that started to appear in Song Ci and continue to be used in modern Chinese were identified. Colors are an important ingredient of the imagery in poetry, and we discuss the most frequent color words that appeared in Tang Shi and Song Ci. |
| Tasks | |
| Published | 2016-08-28 |
| URL | http://arxiv.org/abs/1608.07852v1 |
| http://arxiv.org/pdf/1608.07852v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantitative-analyses-of-chinese-poetry-of |
| Repo | |
| Framework | |
Hardware for Machine Learning: Challenges and Opportunities
| Title | Hardware for Machine Learning: Challenges and Opportunities |
| Authors | Vivienne Sze, Yu-Hsin Chen, Joel Emer, Amr Suleiman, Zhengdong Zhang |
| Abstract | Machine learning plays a critical role in extracting meaningful information out of the zetabytes of sensor data collected every day. For some applications, the goal is to analyze and understand the data to identify trends (e.g., surveillance, portable/wearable electronics); in other applications, the goal is to take immediate action based the data (e.g., robotics/drones, self-driving cars, smart Internet of Things). For many of these applications, local embedded processing near the sensor is preferred over the cloud due to privacy or latency concerns, or limitations in the communication bandwidth. However, at the sensor there are often stringent constraints on energy consumption and cost in addition to throughput and accuracy requirements. Furthermore, flexibility is often required such that the processing can be adapted for different applications or environments (e.g., update the weights and model in the classifier). In many applications, machine learning often involves transforming the input data into a higher dimensional space, which, along with programmable weights, increases data movement and consequently energy consumption. In this paper, we will discuss how these challenges can be addressed at various levels of hardware design ranging from architecture, hardware-friendly algorithms, mixed-signal circuits, and advanced technologies (including memories and sensors). |
| Tasks | Self-Driving Cars |
| Published | 2016-12-22 |
| URL | http://arxiv.org/abs/1612.07625v5 |
| http://arxiv.org/pdf/1612.07625v5.pdf | |
| PWC | https://paperswithcode.com/paper/hardware-for-machine-learning-challenges-and |
| Repo | |
| Framework | |
Guided Policy Search as Approximate Mirror Descent
| Title | Guided Policy Search as Approximate Mirror Descent |
| Authors | William Montgomery, Sergey Levine |
| Abstract | Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised learning to train the policy to mimic a “teacher” algorithm, such as a trajectory optimizer or a trajectory-centric reinforcement learning method. Guided policy search methods provide asymptotic local convergence guarantees by construction, but it is not clear how much the policy improves within a small, finite number of iterations. We show that guided policy search algorithms can be interpreted as an approximate variant of mirror descent, where the projection onto the constraint manifold is not exact. We derive a new guided policy search algorithm that is simpler and provides appealing improvement and convergence guarantees in simplified convex and linear settings, and show that in the more general nonlinear setting, the error in the projection step can be bounded. We provide empirical results on several simulated robotic navigation and manipulation tasks that show that our method is stable and achieves similar or better performance when compared to prior guided policy search methods, with a simpler formulation and fewer hyperparameters. |
| Tasks | |
| Published | 2016-07-15 |
| URL | http://arxiv.org/abs/1607.04614v1 |
| http://arxiv.org/pdf/1607.04614v1.pdf | |
| PWC | https://paperswithcode.com/paper/guided-policy-search-as-approximate-mirror |
| Repo | |
| Framework | |
Learning Social Affordance for Human-Robot Interaction
| Title | Learning Social Affordance for Human-Robot Interaction |
| Authors | Tianmin Shu, M. S. Ryoo, Song-Chun Zhu |
| Abstract | In this paper, we present an approach for robot learning of social affordance from human activity videos. We consider the problem in the context of human-robot interaction: Our approach learns structural representations of human-human (and human-object-human) interactions, describing how body-parts of each agent move with respect to each other and what spatial relations they should maintain to complete each sub-event (i.e., sub-goal). This enables the robot to infer its own movement in reaction to the human body motion, allowing it to naturally replicate such interactions. We introduce the representation of social affordance and propose a generative model for its weakly supervised learning from human demonstration videos. Our approach discovers critical steps (i.e., latent sub-events) in an interaction and the typical motion associated with them, learning what body-parts should be involved and how. The experimental results demonstrate that our Markov Chain Monte Carlo (MCMC) based learning algorithm automatically discovers semantically meaningful interactive affordance from RGB-D videos, which allows us to generate appropriate full body motion for an agent. |
| Tasks | |
| Published | 2016-04-13 |
| URL | http://arxiv.org/abs/1604.03692v2 |
| http://arxiv.org/pdf/1604.03692v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-social-affordance-for-human-robot |
| Repo | |
| Framework | |
Long-Term Image Boundary Prediction
| Title | Long-Term Image Boundary Prediction |
| Authors | Apratim Bhattacharyya, Mateusz Malinowski, Bernt Schiele, Mario Fritz |
| Abstract | Boundary estimation in images and videos has been a very active topic of research, and organizing visual information into boundaries and segments is believed to be a corner stone of visual perception. While prior work has focused on estimating boundaries for observed frames, our work aims at predicting boundaries of future unobserved frames. This requires our model to learn about the fate of boundaries and corresponding motion patterns – including a notion of “intuitive physics”. We experiment on natural video sequences along with synthetic sequences with deterministic physics-based and agent-based motions. While not being our primary goal, we also show that fusion of RGB and boundary prediction leads to improved RGB predictions. |
| Tasks | |
| Published | 2016-11-27 |
| URL | http://arxiv.org/abs/1611.08841v2 |
| http://arxiv.org/pdf/1611.08841v2.pdf | |
| PWC | https://paperswithcode.com/paper/long-term-image-boundary-prediction |
| Repo | |
| Framework | |
Swift: Compiled Inference for Probabilistic Programming Languages
| Title | Swift: Compiled Inference for Probabilistic Programming Languages |
| Authors | Yi Wu, Lei Li, Stuart Russell, Rastislav Bodik |
| Abstract | A probabilistic program defines a probability measure over its semantic structures. One common goal of probabilistic programming languages (PPLs) is to compute posterior probabilities for arbitrary models and queries, given observed evidence, using a generic inference engine. Most PPL inference engines—even the compiled ones—incur significant runtime interpretation overhead, especially for contingent and open-universe models. This paper describes Swift, a compiler for the BLOG PPL. Swift-generated code incorporates optimizations that eliminate interpretation overhead, maintain dynamic dependencies efficiently, and handle memory management for possible worlds of varying sizes. Experiments comparing Swift with other PPL engines on a variety of inference problems demonstrate speedups ranging from 12x to 326x. |
| Tasks | Probabilistic Programming |
| Published | 2016-06-30 |
| URL | http://arxiv.org/abs/1606.09242v1 |
| http://arxiv.org/pdf/1606.09242v1.pdf | |
| PWC | https://paperswithcode.com/paper/swift-compiled-inference-for-probabilistic |
| Repo | |
| Framework | |
Spreadsheet Probabilistic Programming
| Title | Spreadsheet Probabilistic Programming |
| Authors | Mike Wu, Yura Perov, Frank Wood, Hongseok Yang |
| Abstract | Spreadsheet workbook contents are simple programs. Because of this, probabilistic programming techniques can be used to perform Bayesian inversion of spreadsheet computations. What is more, existing execution engines in spreadsheet applications such as Microsoft Excel can be made to do this using only built-in functionality. We demonstrate this by developing a native Excel implementation of both a particle Markov Chain Monte Carlo variant and black-box variational inference for spreadsheet probabilistic programming. The resulting engine performs probabilistically coherent inference over spreadsheet computations, notably including spreadsheets that include user-defined black-box functions. Spreadsheet engines that choose to integrate the functionality we describe in this paper will give their users the ability to both easily develop probabilistic models and maintain them over time by including actuals via a simple user-interface mechanism. For spreadsheet end-users this would mean having access to efficient and probabilistically coherent probabilistic modeling and inference for use in all kinds of decision making under uncertainty. |
| Tasks | Decision Making, Decision Making Under Uncertainty, Probabilistic Programming |
| Published | 2016-06-14 |
| URL | http://arxiv.org/abs/1606.04216v1 |
| http://arxiv.org/pdf/1606.04216v1.pdf | |
| PWC | https://paperswithcode.com/paper/spreadsheet-probabilistic-programming |
| Repo | |
| Framework | |
Applications of Probabilistic Programming (Master’s thesis, 2015)
| Title | Applications of Probabilistic Programming (Master’s thesis, 2015) |
| Authors | Yura N Perov |
| Abstract | This thesis describes work on two applications of probabilistic programming: the learning of probabilistic program code given specifications, in particular program code of one-dimensional samplers; and the facilitation of sequential Monte Carlo inference with help of data-driven proposals. The latter is presented with experimental results on a linear Gaussian model and a non-parametric dependent Dirichlet process mixture of objects model for object recognition and tracking. In Chapter 1 we provide a brief introduction to probabilistic programming. In Chapter 3 we present an approach to automatic discovery of samplers in the form of probabilistic programs. We formulate a Bayesian approach to this problem by specifying a grammar-based prior over probabilistic program code. We use an approximate Bayesian computation method to learn the programs, whose executions generate samples that statistically match observed data or analytical characteristics of distributions of interest. In our experiments we leverage different probabilistic programming systems to perform Markov chain Monte Carlo sampling over the space of programs. Experimental results have demonstrated that, using the proposed methodology, we can learn approximate and even some exact samplers. Finally, we show that our results are competitive with regard to genetic programming methods. In Chapter 3, we describe a way to facilitate sequential Monte Carlo inference in probabilistic programming using data-driven proposals. In particular, we develop a distance-based proposal for the non-parametric dependent Dirichlet process mixture of objects model. We implement this approach in the probabilistic programming system Anglican, and show that for that model data-driven proposals provide significant performance improvements. We also explore the possibility of using neural networks to improve data-driven proposals. |
| Tasks | Object Recognition, Probabilistic Programming |
| Published | 2016-05-31 |
| URL | http://arxiv.org/abs/1606.00075v1 |
| http://arxiv.org/pdf/1606.00075v1.pdf | |
| PWC | https://paperswithcode.com/paper/applications-of-probabilistic-programming |
| Repo | |
| Framework | |
Multi-view metric learning for multi-instance image classification
| Title | Multi-view metric learning for multi-instance image classification |
| Authors | Dewei Li, Yingjie Tian |
| Abstract | It is critical and meaningful to make image classification since it can help human in image retrieval and recognition, object detection, etc. In this paper, three-sides efforts are made to accomplish the task. First, visual features with bag-of-words representation, not single vector, are extracted to characterize the image. To improve the performance, the idea of multi-view learning is implemented and three kinds of features are provided, each one corresponds to a single view. The information from three views is complementary to each other, which can be unified together. Then a new distance function is designed for bags by computing the weighted sum of the distances between instances. The technique of metric learning is explored to construct a data-dependent distance metric to measure the relationships between instances, meanwhile between bags and images, more accurately. Last, a novel approach, called MVML, is proposed, which optimizes the joint probability that every image is similar with its nearest image. MVML learns multiple distance metrics, each one models a single view, to unifies the information from multiple views. The method can be solved by alternate optimization iteratively. Gradient ascent and positive semi-definite projection are utilized in the iterations. Distance comparisons verified that the new bag distance function is prior to previous functions. In model evaluation, numerical experiments show that MVML with multiple views performs better than single view condition, which demonstrates that our model can assemble the complementary information efficiently and measure the distance between images more precisely. Experiments on influence of parameters and instance number validate the consistency of the method. |
| Tasks | Image Classification, Image Retrieval, Metric Learning, MULTI-VIEW LEARNING, Object Detection |
| Published | 2016-10-21 |
| URL | http://arxiv.org/abs/1610.06671v1 |
| http://arxiv.org/pdf/1610.06671v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-metric-learning-for-multi-instance |
| Repo | |
| Framework | |
