Paper Group ANR 11
On- and Off-Policy Monotonic Policy Improvement. Rate-optimal Meta Learning of Classification Error. Siamese Neural Networks for One-shot detection of Railway Track Switches. A Convex Framework for Fair Regression. Classification and Representation via Separable Subspaces: Performance Limits and Algorithms. Finding Algebraic Structure of Care in Ti …
On- and Off-Policy Monotonic Policy Improvement
| Title | On- and Off-Policy Monotonic Policy Improvement |
| Authors | Ryo Iwaki, Minoru Asada |
| Abstract | Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy improvement is guaranteed from on- and off-policy mixture samples. An optimization procedure which applies the proposed bound can be regarded as an off-policy natural policy gradient method. In order to support the theoretical result, we provide a trust region policy optimization method using experience replay as a naive application of our bound, and evaluate its performance in two classical benchmark problems. |
| Tasks | |
| Published | 2017-10-10 |
| URL | http://arxiv.org/abs/1710.03442v2 |
| http://arxiv.org/pdf/1710.03442v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-and-off-policy-monotonic-policy |
| Repo | |
| Framework | |
Rate-optimal Meta Learning of Classification Error
| Title | Rate-optimal Meta Learning of Classification Error |
| Authors | Morteza Noshad Iranzad, Alfred O. Hero III |
| Abstract | Meta learning of optimal classifier error rates allows an experimenter to empirically estimate the intrinsic ability of any estimator to discriminate between two populations, circumventing the difficult problem of estimating the optimal Bayes classifier. To this end we propose a weighted nearest neighbor (WNN) graph estimator for a tight bound on the Bayes classification error; the Henze-Penrose (HP) divergence. Similar to recently proposed HP estimators [berisha2016], the proposed estimator is non-parametric and does not require density estimation. However, unlike previous approaches the proposed estimator is rate-optimal, i.e., its mean squared estimation error (MSEE) decays to zero at the fastest possible rate of $O(1/M+1/N)$ where $M,N$ are the sample sizes of the respective populations. We illustrate the proposed WNN meta estimator for several simulated and real data sets. |
| Tasks | Density Estimation, Meta-Learning |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11315v1 |
| http://arxiv.org/pdf/1710.11315v1.pdf | |
| PWC | https://paperswithcode.com/paper/rate-optimal-meta-learning-of-classification |
| Repo | |
| Framework | |
Siamese Neural Networks for One-shot detection of Railway Track Switches
| Title | Siamese Neural Networks for One-shot detection of Railway Track Switches |
| Authors | Dattaraj J Rao, Shruti Mittal, S. Ritika |
| Abstract | Deep Learning methods have been extensively used to analyze video data to extract valuable information by classifying image frames and detecting objects. We describe a unique approach for using video feed from a moving Locomotive to continuously monitor the Railway Track and detect significant assets like Switches on the Track. The technique used here is called Siamese Networks, which uses 2 identical networks to learn the similarity between of 2 images. Here we will use a Siamese network to continuously compare Track images and detect any significant difference in the Track. Switch will be one of those images that will be different and we will find a mapping that clearly distinguishes the Switch from other possible Track anomalies. The same method will then be extended to detect any abnormalities on the Railway Track. Railway Transportation is unique in the sense that is has wheeled vehicles, Trains pulled by Locomotives, running on guided Rails at very high speeds nearing 200 mph. Multiple Tracks on the Rail network are connected to each other using an equipment called Switch or a Turnout. Switch is either operated manually or automatically through command from a Control center and it governs the movement of Trains on different Tracks of the network. Accurate location of these Switches is very important for the railroad and getting a true picture of their state in field is important. Modern trains use high definition video cameras facing the Track that continuously record video from track. Using a Siamese network and comparing to benchmark images, we describe a method to monitor the Track and highlight anomalies. |
| Tasks | |
| Published | 2017-12-21 |
| URL | http://arxiv.org/abs/1712.08036v1 |
| http://arxiv.org/pdf/1712.08036v1.pdf | |
| PWC | https://paperswithcode.com/paper/siamese-neural-networks-for-one-shot |
| Repo | |
| Framework | |
A Convex Framework for Fair Regression
| Title | A Convex Framework for Fair Regression |
| Authors | Richard Berk, Hoda Heidari, Shahin Jabbari, Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel, Aaron Roth |
| Abstract | We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. These regularizers all enjoy convexity, permitting fast optimization, and they span the rang from notions of group fairness to strong individual fairness. By varying the weight on the fairness regularizer, we can compute the efficient frontier of the accuracy-fairness trade-off on any given dataset, and we measure the severity of this trade-off via a numerical quantity we call the Price of Fairness (PoF). The centerpiece of our results is an extensive comparative study of the PoF across six different datasets in which fairness is a primary consideration. |
| Tasks | |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02409v1 |
| http://arxiv.org/pdf/1706.02409v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-convex-framework-for-fair-regression |
| Repo | |
| Framework | |
Classification and Representation via Separable Subspaces: Performance Limits and Algorithms
| Title | Classification and Representation via Separable Subspaces: Performance Limits and Algorithms |
| Authors | Ishan Jindal, Matthew Nokleby |
| Abstract | We study the classification performance of Kronecker-structured models in two asymptotic regimes and developed an algorithm for separable, fast and compact K-S dictionary learning for better classification and representation of multidimensional signals by exploiting the structure in the signal. First, we study the classification performance in terms of diversity order and pairwise geometry of the subspaces. We derive an exact expression for the diversity order as a function of the signal and subspace dimensions of a K-S model. Next, we study the classification capacity, the maximum rate at which the number of classes can grow as the signal dimension goes to infinity. Then we describe a fast algorithm for Kronecker-Structured Learning of Discriminative Dictionaries (K-SLD2). Finally, we evaluate the empirical classification performance of K-S models for the synthetic data, showing that they agree with the diversity order analysis. We also evaluate the performance of K-SLD2 on synthetic and real-world datasets showing that the K-SLD2 balances compact signal representation and good classification performance. |
| Tasks | Dictionary Learning |
| Published | 2017-05-07 |
| URL | http://arxiv.org/abs/1705.02556v2 |
| http://arxiv.org/pdf/1705.02556v2.pdf | |
| PWC | https://paperswithcode.com/paper/classification-and-representation-via |
| Repo | |
| Framework | |
Finding Algebraic Structure of Care in Time: A Deep Learning Approach
| Title | Finding Algebraic Structure of Care in Time: A Deep Learning Approach |
| Authors | Phuoc Nguyen, Truyen Tran, Svetha Venkatesh |
| Abstract | Understanding the latent processes from Electronic Medical Records could be a game changer in modern healthcare. However, the processes are complex due to the interaction between at least three dynamic components: the illness, the care and the recording practice. Existing methods are inadequate in capturing the dynamic structure of care. We propose an end-to-end model that reads medical record and predicts future risk. The model adopts the algebraic view in that discrete medical objects are embedded into continuous vectors lying in the same space. The bag of disease and comorbidities recorded at each hospital visit are modeled as function of sets. The same holds for the bag of treatments. The interaction between diseases and treatments at a visit is modeled as the residual of the diseases minus the treatments. Finally, the health trajectory, which is a sequence of visits, is modeled using a recurrent neural network. We report preliminary results on chronic diseases - diabetes and mental health - for predicting unplanned readmission. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07980v1 |
| http://arxiv.org/pdf/1711.07980v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-algebraic-structure-of-care-in-time-a |
| Repo | |
| Framework | |
Minimax deviation strategies for machine learning and recognition with short learning samples
| Title | Minimax deviation strategies for machine learning and recognition with short learning samples |
| Authors | Michail Schlesinger, Evgeniy Vodolazskiy |
| Abstract | The article is devoted to the problem of small learning samples in machine learning. The flaws of maximum likelihood learning and minimax learning are looked into and the concept of minimax deviation learning is introduced that is free of those flaws. |
| Tasks | |
| Published | 2017-07-16 |
| URL | http://arxiv.org/abs/1707.04849v1 |
| http://arxiv.org/pdf/1707.04849v1.pdf | |
| PWC | https://paperswithcode.com/paper/minimax-deviation-strategies-for-machine |
| Repo | |
| Framework | |
Algebraic Relations and Triangulation of Unlabeled Image Points
| Title | Algebraic Relations and Triangulation of Unlabeled Image Points |
| Authors | André Wagner |
| Abstract | In multiview geometry when correspondences among multiple views are unknown the image points can be understood as being unlabeled. This is a common problem in computer vision. We give a novel approach to handle such a situation by regarding unlabeled point configurations as points on the Chow variety $\text{Sym}_m(\mathbb{P}^2)$. For two unlabeled points we design an algorithm that solves the triangulation problem with unknown correspondences. Further the unlabeled multiview variety $\text{Sym}_m(V_A)$ is studied. |
| Tasks | |
| Published | 2017-07-27 |
| URL | http://arxiv.org/abs/1707.08722v1 |
| http://arxiv.org/pdf/1707.08722v1.pdf | |
| PWC | https://paperswithcode.com/paper/algebraic-relations-and-triangulation-of |
| Repo | |
| Framework | |
Nonconvex Sparse Spectral Clustering by Alternating Direction Method of Multipliers and Its Convergence Analysis
| Title | Nonconvex Sparse Spectral Clustering by Alternating Direction Method of Multipliers and Its Convergence Analysis |
| Authors | Canyi Lu, Jiashi Feng, Zhouchen Lin, Shuicheng Yan |
| Abstract | Spectral Clustering (SC) is a widely used data clustering method which first learns a low-dimensional embedding $U$ of data by computing the eigenvectors of the normalized Laplacian matrix, and then performs k-means on $U^\top$ to get the final clustering result. The Sparse Spectral Clustering (SSC) method extends SC with a sparse regularization on $UU^\top$ by using the block diagonal structure prior of $UU^\top$ in the ideal case. However, encouraging $UU^\top$ to be sparse leads to a heavily nonconvex problem which is challenging to solve and the work (Lu, Yan, and Lin 2016) proposes a convex relaxation in the pursuit of this aim indirectly. However, the convex relaxation generally leads to a loose approximation and the quality of the solution is not clear. This work instead considers to solve the nonconvex formulation of SSC which directly encourages $UU^\top$ to be sparse. We propose an efficient Alternating Direction Method of Multipliers (ADMM) to solve the nonconvex SSC and provide the convergence guarantee. In particular, we prove that the sequences generated by ADMM always exist a limit point and any limit point is a stationary point. Our analysis does not impose any assumptions on the iterates and thus is practical. Our proposed ADMM for nonconvex problems allows the stepsize to be increasing but upper bounded, and this makes it very efficient in practice. Experimental analysis on several real data sets verifies the effectiveness of our method. |
| Tasks | |
| Published | 2017-12-08 |
| URL | http://arxiv.org/abs/1712.02979v1 |
| http://arxiv.org/pdf/1712.02979v1.pdf | |
| PWC | https://paperswithcode.com/paper/nonconvex-sparse-spectral-clustering-by |
| Repo | |
| Framework | |
Unsupervised Basis Function Adaptation for Reinforcement Learning
| Title | Unsupervised Basis Function Adaptation for Reinforcement Learning |
| Authors | Edward Barker, Charl Ras |
| Abstract | When using reinforcement learning (RL) algorithms it is common, given a large state space, to introduce some form of approximation architecture for the value function (VF). The exact form of this architecture can have a significant effect on an agent’s performance, however, and determining a suitable approximation architecture can often be a highly complex task. Consequently there is currently interest among researchers in the potential for allowing RL algorithms to adaptively generate (i.e. to learn) approximation architectures. One relatively unexplored method of adapting approximation architectures involves using feedback regarding the frequency with which an agent has visited certain states to guide which areas of the state space to approximate with greater detail. In this article we will: (a) informally discuss the potential advantages offered by such methods; (b) introduce a new algorithm based on such methods which adapts a state aggregation approximation architecture on-line and is designed for use in conjunction with SARSA; (c) provide theoretical results, in a policy evaluation setting, regarding this particular algorithm’s complexity, convergence properties and potential to reduce VF error; and finally (d) test experimentally the extent to which this algorithm can improve performance given a number of different test problems. Taken together our results suggest that our algorithm (and potentially such methods more generally) can provide a versatile and computationally lightweight means of significantly boosting RL performance given suitable conditions which are commonly encountered in practice. |
| Tasks | |
| Published | 2017-03-23 |
| URL | http://arxiv.org/abs/1703.07940v3 |
| http://arxiv.org/pdf/1703.07940v3.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-basis-function-adaptation-for-1 |
| Repo | |
| Framework | |
Multilingual and Cross-lingual Timeline Extraction
| Title | Multilingual and Cross-lingual Timeline Extraction |
| Authors | Egoitz Laparra, Rodrigo Agerri, Itziar Aldabe, German Rigau |
| Abstract | In this paper we present an approach to extract ordered timelines of events, their participants, locations and times from a set of multilingual and cross-lingual data sources. Based on the assumption that event-related information can be recovered from different documents written in different languages, we extend the Cross-document Event Ordering task presented at SemEval 2015 by specifying two new tasks for, respectively, Multilingual and Cross-lingual Timeline Extraction. We then develop three deterministic algorithms for timeline extraction based on two main ideas. First, we address implicit temporal relations at document level since explicit time-anchors are too scarce to build a wide coverage timeline extraction system. Second, we leverage several multilingual resources to obtain a single, inter-operable, semantic representation of events across documents and across languages. The result is a highly competitive system that strongly outperforms the current state-of-the-art. Nonetheless, further analysis of the results reveals that linking the event mentions with their target entities and time-anchors remains a difficult challenge. The systems, resources and scorers are freely available to facilitate its use and guarantee the reproducibility of results. |
| Tasks | |
| Published | 2017-02-02 |
| URL | http://arxiv.org/abs/1702.00700v1 |
| http://arxiv.org/pdf/1702.00700v1.pdf | |
| PWC | https://paperswithcode.com/paper/multilingual-and-cross-lingual-timeline |
| Repo | |
| Framework | |
Generating Analytic Insights on Human Behaviour using Image Processing
| Title | Generating Analytic Insights on Human Behaviour using Image Processing |
| Authors | Namit Juneja, Rajesh Kumar Muthu |
| Abstract | This paper proposes a method to track human figures in physical spaces and then utilizes this data to generate several data points such as footfall distribution, demographic analysis,heat maps as well as gender distribution. The proposed framework aims to establish this while utilizing minimum computational resources while remaining real time. It is often useful to have information such as what kind of people visit a certain place or what hour of the day experiences maximum activity, Such analysis can be used improve sales, manage huge number of people as well as predict future behaviour. The proposed framework is designed in a way such that it can take input streams from IP cameras and use that to generate relevant data points using open source tools such as OpenCV and raspberryPi. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07992v1 |
| http://arxiv.org/pdf/1711.07992v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-analytic-insights-on-human |
| Repo | |
| Framework | |
DroidStar: Callback Typestates for Android Classes
| Title | DroidStar: Callback Typestates for Android Classes |
| Authors | Arjun Radhakrishna, Nicholas V. Lewchenko, Shawn Meier, Sergio Mover, Krishna Chaitanya Sripada, Damien Zufferey, Bor-Yuh Evan Chang, Pavol Černý |
| Abstract | Event-driven programming frameworks, such as Android, are based on components with asynchronous interfaces. The protocols for interacting with these components can often be described by finite-state machines we dub callback typestates. Callback typestates are akin to classical typestates, with the difference that their outputs (callbacks) are produced asynchronously. While useful, these specifications are not commonly available, because writing them is difficult and error-prone. Our goal is to make the task of producing callback typestates significantly easier. We present a callback typestate assistant tool, DroidStar, that requires only limited user interaction to produce a callback typestate. Our approach is based on an active learning algorithm, L*. We improved the scalability of equivalence queries (a key component of L*), thus making active learning tractable on the Android system. We use DroidStar to learn callback typestates for Android classes both for cases where one is already provided by the documentation, and for cases where the documentation is unclear. The results show that DroidStar learns callback typestates accurately and efficiently. Moreover, in several cases, the synthesized callback typestates uncovered surprising and undocumented behaviors. |
| Tasks | Active Learning |
| Published | 2017-01-26 |
| URL | http://arxiv.org/abs/1701.07842v3 |
| http://arxiv.org/pdf/1701.07842v3.pdf | |
| PWC | https://paperswithcode.com/paper/droidstar-callback-typestates-for-android |
| Repo | |
| Framework | |
Learning Neural Representations of Human Cognition across Many fMRI Studies
| Title | Learning Neural Representations of Human Cognition across Many fMRI Studies |
| Authors | Arthur Mensch, Julien Mairal, Danilo Bzdok, Bertrand Thirion, Gaël Varoquaux |
| Abstract | Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated solutions to an old challenge: how to aggregate heterogeneous information on brain function into a universal cognitive system that relates mental operations/cognitive processes/psychological tasks to brain networks? We cast this challenge in a machine-learning approach to predict conditions from statistical brain maps across different studies. For this, we leverage multi-task learning and multi-scale dimension reduction to learn low-dimensional representations of brain images that carry cognitive information and can be robustly associated with psychological stimuli. Our multi-dataset classification model achieves the best prediction performance on several large reference datasets, compared to models without cognitive-aware low-dimension representations, it brings a substantial performance boost to the analysis of small datasets, and can be introspected to identify universal template cognitive concepts. |
| Tasks | Dimensionality Reduction, Multi-Task Learning |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11438v2 |
| http://arxiv.org/pdf/1710.11438v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-neural-representations-of-human |
| Repo | |
| Framework | |
Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets
| Title | Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets |
| Authors | Andrea Tacchetti, Stephen Voinea, Georgios Evangelopoulos |
| Abstract | The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastically altering the visual appearance, these changes are orthogonal to recognition and should not be reflected in the representation or feature encoding used for learning. We introduce a framework for weakly supervised learning of image embeddings that are robust to transformations and selective to the class distribution, using sets of transforming examples (orbit sets), deep parametrizations and a novel orbit-based loss. The proposed loss combines a discriminative, contrastive part for orbits with a reconstruction error that learns to rectify orbit transformations. The learned embeddings are evaluated in distance metric-based tasks, such as one-shot classification under geometric transformations, as well as face verification and retrieval under more realistic visual variability. Our results suggest that orbit sets, suitably computed or observed, can be used for efficient, weakly-supervised learning of semantically relevant image embeddings. |
| Tasks | Face Verification, Object Recognition |
| Published | 2017-03-14 |
| URL | http://arxiv.org/abs/1703.04775v1 |
| http://arxiv.org/pdf/1703.04775v1.pdf | |
| PWC | https://paperswithcode.com/paper/discriminate-and-rectify-encoders-learning |
| Repo | |
| Framework | |
