May 6, 2019

3112 words 15 mins read

Paper Group ANR 418

Embodiment of Learning in Electro-Optical Signal Processors. StuffNet: Using ‘Stuff’ to Improve Object Detection. Online Multi-view Clustering with Incomplete Views. Prediction of future hospital admissions - what is the tradeoff between specificity and accuracy?. Reinforcement Learning algorithms for regret minimization in structured Markov Decisi …

Embodiment of Learning in Electro-Optical Signal Processors


Title	Embodiment of Learning in Electro-Optical Signal Processors
Authors	Michiel Hermans, Piotr Antonik, Marc Haelterman, Serge Massar
Abstract	Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular it has recently been demonstrated, using the artificial intelligence algorithm known as reservoir computing, that photonic implementations of such systems solve complex tasks such as speech recognition. Here we show how the backpropagation algorithm can be physically implemented on the same electro-optical delay-coupled architecture used for computation with only minor changes to the original design. We find that, compared when the backpropagation algorithm is not used, the error rate of the resulting computing device, evaluated on three benchmark tasks, decreases considerably. This demonstrates that electro-optical analog computers can embody a large part of their own training process, allowing them to be applied to new, more difficult tasks.
Tasks	Speech Recognition
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06269v2
PDF	http://arxiv.org/pdf/1610.06269v2.pdf
PWC	https://paperswithcode.com/paper/embodiment-of-learning-in-electro-optical
Repo
Framework

StuffNet: Using ‘Stuff’ to Improve Object Detection


Title	StuffNet: Using ‘Stuff’ to Improve Object Detection
Authors	Samarth Brahmbhatt, Henrik I. Christensen, James Hays
Abstract	We propose a Convolutional Neural Network (CNN) based algorithm - StuffNet - for object detection. In addition to the standard convolutional features trained for region proposal and object detection [31], StuffNet uses convolutional features trained for segmentation of objects and ‘stuff’ (amorphous categories such as ground and water). Through experiments on Pascal VOC 2010, we show the importance of features learnt from stuff segmentation for improving object detection performance. StuffNet improves performance from 18.8% mAP to 23.9% mAP for small objects. We also devise a method to train StuffNet on datasets that do not have stuff segmentation labels. Through experiments on Pascal VOC 2007 and 2012, we demonstrate the effectiveness of this method and show that StuffNet also significantly improves object detection performance on such datasets.
Tasks	Object Detection
Published	2016-10-19
URL	http://arxiv.org/abs/1610.05861v2
PDF	http://arxiv.org/pdf/1610.05861v2.pdf
PWC	https://paperswithcode.com/paper/stuffnet-using-stuff-to-improve-object
Repo
Framework

Online Multi-view Clustering with Incomplete Views


Title	Online Multi-view Clustering with Incomplete Views
Authors	Weixiang Shao, Lifang He, Chun-Ta Lu, Philip S. Yu
Abstract	In the era of big data, it is common to have data with multiple modalities or coming from multiple sources, known as “multi-view data”. Multi-view clustering provides a natural way to generate clusters from such data. Since different views share some consistency and complementary information, previous works on multi-view clustering mainly focus on how to combine various numbers of views to improve clustering performance. However, in reality, each view may be incomplete, i.e., instances missing in the view. Furthermore, the size of data could be extremely huge. It is unrealistic to apply multi-view clustering in large real-world applications without considering the incompleteness of views and the memory requirement. None of previous works have addressed all these challenges simultaneously. In this paper, we propose an online multi-view clustering algorithm, OMVC, which deals with large-scale incomplete views. We model the multi-view clustering problem as a joint weighted nonnegative matrix factorization problem and process the multi-view data chunk by chunk to reduce the memory requirement. OMVC learns the latent feature matrices for all the views and pushes them towards a consensus. We further increase the robustness of the learned latent feature matrices in OMVC via lasso regularization. To minimize the influence of incompleteness, dynamic weight setting is introduced to give lower weights to the incoming missing instances in different views. More importantly, to reduce the computational time, we incorporate a faster projected gradient descent by utilizing the Hessian matrices in OMVC. Extensive experiments conducted on four real data demonstrate the effectiveness of the proposed OMVC method.
Tasks
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00481v2
PDF	http://arxiv.org/pdf/1611.00481v2.pdf
PWC	https://paperswithcode.com/paper/online-multi-view-clustering-with-incomplete
Repo
Framework

Prediction of future hospital admissions - what is the tradeoff between specificity and accuracy?


Title	Prediction of future hospital admissions - what is the tradeoff between specificity and accuracy?
Authors	Ieva Vasiljeva, Ognjen Arandjelovic
Abstract	Large amounts of electronic medical records collected by hospitals across the developed world offer unprecedented possibilities for knowledge discovery using computer based data mining and machine learning. Notwithstanding significant research efforts, the use of this data in the prediction of disease development has largely been disappointing. In this paper we examine in detail a recently proposed method which has in preliminary experiments demonstrated highly promising results on real-world data. We scrutinize the authors’ claims that the proposed model is scalable and investigate whether the tradeoff between prediction specificity (i.e. the ability of the model to predict a wide number of different ailments) and accuracy (i.e. the ability of the model to make the correct prediction) is practically viable. Our experiments conducted on a data corpus of nearly 3,000,000 admissions support the authors’ expectations and demonstrate that the high prediction accuracy is maintained well even when the number of admission types explicitly included in the model is increased to account for 98% of all admissions in the corpus. Thus several promising directions for future work are highlighted.
Tasks
Published	2016-02-27
URL	http://arxiv.org/abs/1607.07817v1
PDF	http://arxiv.org/pdf/1607.07817v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-future-hospital-admissions-what
Repo
Framework

Reinforcement Learning algorithms for regret minimization in structured Markov Decision Processes


Title	Reinforcement Learning algorithms for regret minimization in structured Markov Decision Processes
Authors	K J Prabuchandran, Tejas Bodas, Theja Tulabandhula
Abstract	A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation research and optimal control, the optimal policy of the underlying Markov Decision Process (MDP) is characterized by a known structure. The current state of the art algorithms do not utilize this known structure of the optimal policy while minimizing regret. In this work, we develop new RL algorithms that exploit the structure of the optimal policy to minimize regret. Numerical experiments on MDPs with structured optimal policies show that our algorithms have better performance, are easy to implement, have a smaller run-time and require less number of random number generations.
Tasks
Published	2016-08-17
URL	http://arxiv.org/abs/1608.04929v1
PDF	http://arxiv.org/pdf/1608.04929v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-algorithms-for-regret
Repo
Framework

A heuristic scheme for the Cooperative Team Orienteering Problem with Time Windows


Title	A heuristic scheme for the Cooperative Team Orienteering Problem with Time Windows
Authors	Iman Roozbeh, Melih Ozlen, John W. Hearne
Abstract	The Cooperative Orienteering Problem with Time Windows (COPTW)is a class of problems with some important applications and yet has received relatively little attention. In the COPTW a certain number of team members are required to collect the associated reward from each customer simultaneously and cooperatively. This requirement to have one or more team members simultaneously available at a vertex to collect the reward, poses a challenging OR task. Exact methods are not able to handle large scale instances of the COPTW and no heuristic schemes have been developed for this problem so far. In this paper, a new modification to the classical Clarke and Wright saving heuristic is proposed to handle this problem. A new benchmark set generated by adding the resource requirement attribute to the existing benchmarks. The heuristic algorithm followed by boosting operators achieves optimal solutions for 64.5% of instances for which the optimal results are known. The proposed solution approach attains an optimality gap of 2.61% for the same instances and solves benchmarks with realistic size within short computational times.
Tasks
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05485v1
PDF	http://arxiv.org/pdf/1608.05485v1.pdf
PWC	https://paperswithcode.com/paper/a-heuristic-scheme-for-the-cooperative-team
Repo
Framework

Cost-Sensitive Reference Pair Encoding for Multi-Label Learning


Title	Cost-Sensitive Reference Pair Encoding for Multi-Label Learning
Authors	Yao-Yuan Yang, Kuan-Hao Huang, Chih-Wei Chang, Hsuan-Tien Lin
Abstract	Label space expansion for multi-label classification (MLC) is a methodology that encodes the original label vectors to higher dimensional codes before training and decodes the predicted codes back to the label vectors during testing. The methodology has been demonstrated to improve the performance of MLC algorithms when coupled with off-the-shelf error-correcting codes for encoding and decoding. Nevertheless, such a coding scheme can be complicated to implement, and cannot easily satisfy a common application need of cost-sensitive MLC—adapting to different evaluation criteria of interest. In this work, we show that a simpler coding scheme based on the concept of a reference pair of label vectors achieves cost-sensitivity more naturally. In particular, our proposed cost-sensitive reference pair encoding (CSRPE) algorithm contains cluster-based encoding, weight-based training and voting-based decoding steps, all utilizing the cost information. Furthermore, we leverage the cost information embedded in the code space of CSRPE to propose a novel active learning algorithm for cost-sensitive MLC. Extensive experimental results verify that CSRPE performs better than state-of-the-art algorithms across different MLC criteria. The results also demonstrate that the CSRPE-backed active learning algorithm is superior to existing algorithms for active MLC, and further justify the usefulness of CSRPE.
Tasks	Active Learning, Multi-Label Classification, Multi-Label Learning
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09461v3
PDF	http://arxiv.org/pdf/1611.09461v3.pdf
PWC	https://paperswithcode.com/paper/cost-sensitive-reference-pair-encoding-for
Repo
Framework

A Programming Language With a POMDP Inside


Title	A Programming Language With a POMDP Inside
Authors	Christopher H. Lin, Mausam, Daniel S. Weld
Abstract	We present POAPS, a novel planning system for defining Partially Observable Markov Decision Processes (POMDPs) that abstracts away from POMDP details for the benefit of non-expert practitioners. POAPS includes an expressive adaptive programming language based on Lisp that has constructs for choice points that can be dynamically optimized. Non-experts can use our language to write adaptive programs that have partially observable components without needing to specify belief/hidden states or reason about probabilities. POAPS is also a compiler that defines and performs the transformation of any program written in our language into a POMDP with control knowledge. We demonstrate the generality and power of POAPS in the rapidly growing domain of human computation by describing its expressiveness and simplicity by writing several POAPS programs for common crowdsourcing tasks.
Tasks
Published	2016-08-31
URL	http://arxiv.org/abs/1608.08724v1
PDF	http://arxiv.org/pdf/1608.08724v1.pdf
PWC	https://paperswithcode.com/paper/a-programming-language-with-a-pomdp-inside
Repo
Framework

Adaptive ADMM with Spectral Penalty Parameter Selection


Title	Adaptive ADMM with Spectral Penalty Parameter Selection
Authors	Zheng Xu, Mario A. T. Figueiredo, Tom Goldstein
Abstract	The alternating direction method of multipliers (ADMM) is a versatile tool for solving a wide range of constrained optimization problems, with differentiable or non-differentiable objective functions. Unfortunately, its performance is highly sensitive to a penalty parameter, which makes ADMM often unreliable and hard to automate for a non-expert user. We tackle this weakness of ADMM by proposing a method to adaptively tune the penalty parameters to achieve fast convergence. The resulting adaptive ADMM (AADMM) algorithm, inspired by the successful Barzilai-Borwein spectral method for gradient descent, yields fast convergence and relative insensitivity to the initial stepsize and problem scaling.
Tasks
Published	2016-05-24
URL	http://arxiv.org/abs/1605.07246v5
PDF	http://arxiv.org/pdf/1605.07246v5.pdf
PWC	https://paperswithcode.com/paper/adaptive-admm-with-spectral-penalty-parameter
Repo
Framework

A general multiblock method for structured variable selection


Title	A general multiblock method for structured variable selection
Authors	Tommy Löfstedt, Fouad Hadj-Selem, Vincent Guillemot, Cathy Philippe, Nicolas Raymond, Edouard Duchesney, Vincent Frouin, Arthur Tenenhaus
Abstract	Regularised canonical correlation analysis was recently extended to more than two sets of variables by the multiblock method Regularised generalised canonical correlation analysis (RGCCA). Further, Sparse GCCA (SGCCA) was proposed to address the issue of variable selection. However, for technical reasons, the variable selection offered by SGCCA was restricted to a covariance link between the blocks (i.e., with $\tau=1$). One of the main contributions of this paper is to go beyond the covariance link and to propose an extension of SGCCA for the full RGCCA model (i.e., with $\tau\in[0, 1]$). In addition, we propose an extension of SGCCA that exploits structural relationships between variables within blocks. Specifically, we propose an algorithm that allows structured and sparsity-inducing penalties to be included in the RGCCA optimisation problem. The proposed multiblock method is illustrated on a real three-block high-grade glioma data set, where the aim is to predict the location of the brain tumours, and on a simulated data set, where the aim is to illustrate the method’s ability to reconstruct the true underlying weight vectors.
Tasks
Published	2016-10-29
URL	http://arxiv.org/abs/1610.09490v1
PDF	http://arxiv.org/pdf/1610.09490v1.pdf
PWC	https://paperswithcode.com/paper/a-general-multiblock-method-for-structured
Repo
Framework

Inferring Restaurant Styles by Mining Crowd Sourced Photos from User-Review Websites


Title	Inferring Restaurant Styles by Mining Crowd Sourced Photos from User-Review Websites
Authors	Haofu Liao, Yucheng Li, Tianran Hu, Jiebo Luo
Abstract	When looking for a restaurant online, user uploaded photos often give people an immediate and tangible impression about a restaurant. Due to their informativeness, such user contributed photos are leveraged by restaurant review websites to provide their users an intuitive and effective search experience. In this paper, we present a novel approach to inferring restaurant types or styles (ambiance, dish styles, suitability for different occasions) from user uploaded photos on user-review websites. To that end, we first collect a novel restaurant photo dataset associating the user contributed photos with the restaurant styles from TripAdvior. We then propose a deep multi-instance multi-label learning (MIML) framework to deal with the unique problem setting of the restaurant style classification task. We employ a two-step bootstrap strategy to train a multi-label convolutional neural network (CNN). The multi-label CNN is then used to compute the confidence scores of restaurant styles for all the images associated with a restaurant. The computed confidence scores are further used to train a final binary classifier for each restaurant style tag. Upon training, the styles of a restaurant can be profiled by analyzing restaurant photos with the trained multi-label CNN and SVM models. Experimental evaluation has demonstrated that our crowd sourcing-based approach can effectively infer the restaurant style when there are a sufficient number of user uploaded photos for a given restaurant.
Tasks	Multi-Label Learning
Published	2016-11-19
URL	http://arxiv.org/abs/1611.06301v1
PDF	http://arxiv.org/pdf/1611.06301v1.pdf
PWC	https://paperswithcode.com/paper/inferring-restaurant-styles-by-mining-crowd
Repo
Framework

Deep Variational Inference Without Pixel-Wise Reconstruction


Title	Deep Variational Inference Without Pixel-Wise Reconstruction
Authors	Siddharth Agrawal, Ambedkar Dukkipati
Abstract	Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the approximations to the posterior flexible and accurate, leading to tremendous progress. However, there have been limited efforts to replace pixel-wise reconstruction, which have known shortcomings. In this work, we use real-valued non-volume preserving transformations (real NVP) to exactly compute the conditional likelihood of the data given the latent distribution. We show that a simple VAE with this form of reconstruction is competitive with complicated VAE structures, on image modeling tasks. As part of our model, we develop powerful conditional coupling layers that enable real NVP to learn with fewer intermediate layers.
Tasks
Published	2016-11-16
URL	http://arxiv.org/abs/1611.05209v1
PDF	http://arxiv.org/pdf/1611.05209v1.pdf
PWC	https://paperswithcode.com/paper/deep-variational-inference-without-pixel-wise
Repo
Framework

Multi-Label Learning with Provable Guarantee


Title	Multi-Label Learning with Provable Guarantee
Authors	Sayantan Dasgupta
Abstract	Here we study the problem of learning labels for large text corpora where each text can be assigned a variable number of labels. The problem might seem trivial when the label dimensionality is small and can be easily solved using a series of one-vs-all classifiers. However, as the label dimensionality increases to several thousand, the parameter space becomes extremely large, and it is no longer possible to use the one-vs-all technique. Here we propose a model based on the factorization of higher order moments of the words in the corpora, as well as the cross moment between the labels and the words for multi-label prediction. Our model provides guaranteed convergence bounds on the estimated parameters. Further, our model takes only three passes through the training dataset to extract the parameters, resulting in a highly scalable algorithm that can train on GB’s of data consisting of millions of documents with hundreds of thousands of labels using a nominal resource of a single processor with 16GB RAM. Our model achieves 10x-15x order of speed-up on large-scale datasets while producing competitive performance in comparison with existing benchmark algorithms.
Tasks	Multi-Label Learning
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03426v4
PDF	http://arxiv.org/pdf/1609.03426v4.pdf
PWC	https://paperswithcode.com/paper/multi-label-learning-with-provable-guarantee
Repo
Framework

Channel Selection Algorithm for Cognitive Radio Networks with Heavy-Tailed Idle Times


Title	Channel Selection Algorithm for Cognitive Radio Networks with Heavy-Tailed Idle Times
Authors	S. Senthilmurugan, Junaid Ansari, Petri Mähönen, T. G. Venkatesh, Marina Petrova
Abstract	We consider a multichannel Cognitive Radio Network (CRN), where secondary users sequentially sense channels for opportunistic spectrum access. In this scenario, the Channel Selection Algorithm (CSA) allows secondary users to find a vacant channel with the minimal number of channel switches. Most of the existing CSA literature assumes exponential ON-OFF time distribution for primary users (PU) channel occupancy pattern. This exponential assumption might be helpful to get performance bounds; but not useful to evaluate the performance of CSA under realistic conditions. An in-depth analysis of independent spectrum measurement traces reveals that wireless channels have typically heavy-tailed PU OFF times. In this paper, we propose an extension to the Predictive CSA framework and its generalization for heavy tailed PU OFF time distribution, which represents realistic scenarios. In particular, we calculate the probability of channel being idle for hyper-exponential OFF times to use in CSA. We implement our proposed CSA framework in a wireless test-bed and comprehensively evaluate its performance by recreating the realistic PU channel occupancy patterns. The proposed CSA shows significant reduction in channel switches and energy consumption as compared to Predictive CSA which always assumes exponential PU ON-OFF times.Through our work, we show the impact of the PU channel occupancy pattern on the performance of CSA in multichannel CRN.
Tasks
Published	2016-07-15
URL	http://arxiv.org/abs/1607.04450v1
PDF	http://arxiv.org/pdf/1607.04450v1.pdf
PWC	https://paperswithcode.com/paper/channel-selection-algorithm-for-cognitive
Repo
Framework

Infinite-Label Learning with Semantic Output Codes


Title	Infinite-Label Learning with Semantic Output Codes
Authors	Yang Zhang, Rupam Acharyya, Ji Liu, Boqing Gong
Abstract	We develop a new statistical machine learning paradigm, named infinite-label learning, to annotate a data point with more than one relevant labels from a candidate set, which pools both the finite labels observed at training and a potentially infinite number of previously unseen labels. The infinite-label learning fundamentally expands the scope of conventional multi-label learning, and better models the practical requirements in various real-world applications, such as image tagging, ads-query association, and article categorization. However, how can we learn a labeling function that is capable of assigning to a data point the labels omitted from the training set? To answer the question, we seek some clues from the recent work on zero-shot learning, where the key is to represent a class/label by a vector of semantic codes, as opposed to treating them as atomic labels. We validate the infinite-label learning by a PAC bound in theory and some empirical studies on both synthetic and real data.
Tasks	Multi-Label Learning, Zero-Shot Learning
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06608v3
PDF	http://arxiv.org/pdf/1608.06608v3.pdf
PWC	https://paperswithcode.com/paper/infinite-label-learning-with-semantic-output
Repo
Framework