Paper Group ANR 709
Towards Characterizing Divergence in Deep Q-Learning. Automatic Evaluation of Local Topic Quality. MonoNet: Towards Interpretable Models by Learning Monotonic Features. Multi-Player Bandits: The Adversarial Case. Extension of Rough Set Based on Positive Transitive Relation. Unsupervised Automatic Building Extraction Using Active Contour Model on Un …
Towards Characterizing Divergence in Deep Q-Learning
| Title | Towards Characterizing Divergence in Deep Q-Learning |
| Authors | Joshua Achiam, Ethan Knight, Pieter Abbeel |
| Abstract | Deep Q-Learning (DQL), a family of temporal difference algorithms for control, employs three techniques collectively known as the `deadly triad’ in reinforcement learning: bootstrapping, off-policy learning, and function approximation. Prior work has demonstrated that together these can lead to divergence in Q-learning algorithms, but the conditions under which divergence occurs are not well-understood. In this note, we give a simple analysis based on a linear approximation to the Q-value updates, which we believe provides insight into divergence under the deadly triad. The central point in our analysis is to consider when the leading order approximation to the deep-Q update is or is not a contraction in the sup norm. Based on this analysis, we develop an algorithm which permits stable deep Q-learning for continuous control without any of the tricks conventionally used (such as target networks, adaptive gradient optimizers, or using multiple Q functions). We demonstrate that our algorithm performs above or near state-of-the-art on standard MuJoCo benchmarks from the OpenAI Gym. | |
| Tasks | Continuous Control, Q-Learning |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.08894v1 |
| http://arxiv.org/pdf/1903.08894v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-characterizing-divergence-in-deep-q |
| Repo | |
| Framework | |
Automatic Evaluation of Local Topic Quality
| Title | Automatic Evaluation of Local Topic Quality |
| Authors | Jeffrey Lund, Piper Armstrong, Wilson Fearn, Stephen Cowley, Courtni Byun, Jordan Boyd-Graber, Kevin Seppi |
| Abstract | Topic models are typically evaluated with respect to the global topic distributions that they generate, using metrics such as coherence, but without regard to local (token-level) topic assignments. Token-level assignments are important for downstream tasks such as classification. Even recent models, which aim to improve the quality of these token-level topic assignments, have been evaluated only with respect to global metrics. We propose a task designed to elicit human judgments of token-level topic assignments. We use a variety of topic model types and parameters and discover that global metrics agree poorly with human assignments. Since human evaluation is expensive we propose a variety of automated metrics to evaluate topic models at a local level. Finally, we correlate our proposed metrics with human judgments from the task on several datasets. We show that an evaluation based on the percent of topic switches correlates most strongly with human judgment of local topic quality. We suggest that this new metric, which we call consistency, be adopted alongside global metrics such as topic coherence when evaluating new topic models. |
| Tasks | Topic Models |
| Published | 2019-05-18 |
| URL | https://arxiv.org/abs/1905.13126v1 |
| https://arxiv.org/pdf/1905.13126v1.pdf | |
| PWC | https://paperswithcode.com/paper/190513126 |
| Repo | |
| Framework | |
MonoNet: Towards Interpretable Models by Learning Monotonic Features
| Title | MonoNet: Towards Interpretable Models by Learning Monotonic Features |
| Authors | An-phi Nguyen, María Rodríguez Martínez |
| Abstract | Being able to interpret, or explain, the predictions made by a machine learning model is of fundamental importance. This is especially true when there is interest in deploying data-driven models to make high-stakes decisions, e.g. in healthcare. While recent years have seen an increasing interest in interpretable machine learning research, this field is currently lacking an agreed-upon definition of interpretability, and some researchers have called for a more active conversation towards a rigorous approach to interpretability. Joining this conversation, we claim in this paper that the difficulty of interpreting a complex model stems from the existing interactions among features. We argue that by enforcing monotonicity between features and outputs, we are able to reason about the effect of a single feature on an output independently from other features, and consequently better understand the model. We show how to structurally introduce this constraint in deep learning models by adding new simple layers. We validate our model on benchmark datasets, and compare our results with previously proposed interpretable models. |
| Tasks | Interpretable Machine Learning |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13611v1 |
| https://arxiv.org/pdf/1909.13611v1.pdf | |
| PWC | https://paperswithcode.com/paper/mononet-towards-interpretable-models-by |
| Repo | |
| Framework | |
Multi-Player Bandits: The Adversarial Case
| Title | Multi-Player Bandits: The Adversarial Case |
| Authors | Pragnya Alatur, Kfir Y. Levy, Andreas Krause |
| Abstract | We consider a setting where multiple players sequentially choose among a common set of actions (arms). Motivated by a cognitive radio networks application, we assume that players incur a loss upon colliding, and that communication between players is not possible. Existing approaches assume that the system is stationary. Yet this assumption is often violated in practice, e.g., due to signal strength fluctuations. In this work, we design the first Multi-player Bandit algorithm that provably works in arbitrarily changing environments, where the losses of the arms may even be chosen by an adversary. This resolves an open problem posed by Rosenski, Shamir, and Szlak (2016). |
| Tasks | |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.08036v1 |
| http://arxiv.org/pdf/1902.08036v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-player-bandits-the-adversarial-case |
| Repo | |
| Framework | |
Extension of Rough Set Based on Positive Transitive Relation
| Title | Extension of Rough Set Based on Positive Transitive Relation |
| Authors | Min Shu, Wei Zhu |
| Abstract | The application of rough set theory in incomplete information systems is a key problem in practice since missing values almost always occur in knowledge acquisition due to the error of data measuring, the limitation of data collection, or the limitation of data comprehension, etc. An incomplete information system is mainly processed by compressing the indiscernibility relation. The existing rough set extension models based on tolerance or symmetric similarity relations typically discard one relation among the reflexive, symmetric and transitive relations, especially the transitive relation. In order to overcome the limitations of the current rough set extension models, we define a new relation called the positive transitive relation and then propose a novel rough set extension model built upon which. The new model holds the merit of the existing rough set extension models while avoids their limitations of discarding transitivity or symmetry. In comparison to the existing extension models, the proposed model has a better performance in processing the incomplete information systems while substantially reducing the computational complexity, taking into account the relation of tolerance and similarity of positive transitivity, and supplementing the related theories in accordance to the intuitive classification of incomplete information. In summary, the positive transitive relation can improve current theoretical analysis of incomplete information systems and the newly proposed extension model is more suitable for processing incomplete information systems and has a broad application prospect. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.03337v2 |
| https://arxiv.org/pdf/1906.03337v2.pdf | |
| PWC | https://paperswithcode.com/paper/extension-of-rough-set-based-on-positive |
| Repo | |
| Framework | |
Unsupervised Automatic Building Extraction Using Active Contour Model on Unregistered Optical Imagery and Airborne LiDAR Data
| Title | Unsupervised Automatic Building Extraction Using Active Contour Model on Unregistered Optical Imagery and Airborne LiDAR Data |
| Authors | Thanh Huy Nguyen, Sylvie Daniel, Didier Gueriot, Christophe Sintes, Jean-Marc Le Caillec |
| Abstract | Automatic extraction of buildings in urban scenes has become a subject of growing interest in the domain of photogrammetry and remote sensing, particularly with the emergence of LiDAR systems since mid-1990s. However, in reality, this task is still very challenging due to the complexity of building size and shapes, as well as its surrounding environment. Active contour model, colloquially called snake model, which has been extensively used in many applications in computer vision and image processing, is also applied to extract buildings from aerial/satellite imagery. Motivated by the limitations of existing snake models addressing to the building extraction, this paper presents an unsupervised and fully automatic snake model to extract buildings using optical imagery and an unregistered airborne LiDAR dataset, without manual initial points or training data. The proposed method is shown to be capable of extracting buildings with varying color from complex environments, and yielding high overall accuracy. |
| Tasks | |
| Published | 2019-07-14 |
| URL | https://arxiv.org/abs/1907.06206v1 |
| https://arxiv.org/pdf/1907.06206v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-automatic-building-extraction |
| Repo | |
| Framework | |
Quantum and Classical Algorithms for Approximate Submodular Function Minimization
| Title | Quantum and Classical Algorithms for Approximate Submodular Function Minimization |
| Authors | Yassine Hamoudi, Patrick Rebentrost, Ansis Rosmanis, Miklos Santha |
| Abstract | Submodular functions are set functions mapping every subset of some ground set of size $n$ into the real numbers and satisfying the diminishing returns property. Submodular minimization is an important field in discrete optimization theory due to its relevance for various branches of mathematics, computer science and economics. The currently fastest strongly polynomial algorithm for exact minimization [LSW15] runs in time $\widetilde{O}(n^3 \cdot \mathrm{EO} + n^4)$ where $\mathrm{EO}$ denotes the cost to evaluate the function on any set. For functions with range $[-1,1]$, the best $\epsilon$-additive approximation algorithm [CLSW17] runs in time $\widetilde{O}(n^{5/3}/\epsilon^{2} \cdot \mathrm{EO})$. In this paper we present a classical and a quantum algorithm for approximate submodular minimization. Our classical result improves on the algorithm of [CLSW17] and runs in time $\widetilde{O}(n^{3/2}/\epsilon^2 \cdot \mathrm{EO})$. Our quantum algorithm is, up to our knowledge, the first attempt to use quantum computing for submodular optimization. The algorithm runs in time $\widetilde{O}(n^{5/4}/\epsilon^{5/2} \cdot \log(1/\epsilon) \cdot \mathrm{EO})$. The main ingredient of the quantum result is a new method for sampling with high probability $T$ independent elements from any discrete probability distribution of support size $n$ in time $O(\sqrt{Tn})$. Previous quantum algorithms for this problem were of complexity $O(T\sqrt{n})$. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05378v2 |
| https://arxiv.org/pdf/1907.05378v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-and-classical-algorithms-for |
| Repo | |
| Framework | |
TalkDown: A Corpus for Condescension Detection in Context
| Title | TalkDown: A Corpus for Condescension Detection in Context |
| Authors | Zijian Wang, Christopher Potts |
| Abstract | Condescending language use is caustic; it can bring dialogues to an end and bifurcate communities. Thus, systems for condescension detection could have a large positive impact. A challenge here is that condescension is often impossible to detect from isolated utterances, as it depends on the discourse and social context. To address this, we present TalkDown, a new labeled dataset of condescending linguistic acts in context. We show that extending a language-only model with representations of the discourse improves performance, and we motivate techniques for dealing with the low rates of condescension overall. We also use our model to estimate condescension rates in various online communities and relate these differences to differing community norms. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11272v1 |
| https://arxiv.org/pdf/1909.11272v1.pdf | |
| PWC | https://paperswithcode.com/paper/talkdown-a-corpus-for-condescension-detection |
| Repo | |
| Framework | |
Local minimax rates for closeness testing of discrete distributions
| Title | Local minimax rates for closeness testing of discrete distributions |
| Authors | Joseph Lam-Weil, Alexandra Carpentier, Bharath K. Sriperumbudur |
| Abstract | We consider the closeness testing (or two-sample testing) problem in the Poisson vector model - which is known to be asymptotically equivalent to the model of multinomial distributions. The goal is to distinguish whether two data samples are drawn from the same unspecified distribution, or whether their respective distributions are separated in $L_1$-norm. In this paper, we focus on adapting the rate to the shape of the underlying distributions, i.e. we consider a local minimax setting. We provide, to the best of our knowledge, the first local minimax rate for the separation distance up to logarithmic factors, together with a test that achieves it. In view of the rate, closeness testing turns out to be substantially harder than the related one-sample testing problem over a wide range of cases. |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://arxiv.org/abs/1902.01219v2 |
| https://arxiv.org/pdf/1902.01219v2.pdf | |
| PWC | https://paperswithcode.com/paper/local-minimax-rates-for-closeness-testing-of |
| Repo | |
| Framework | |
Stable Learning via Sample Reweighting
| Title | Stable Learning via Sample Reweighting |
| Authors | Zheyan Shen, Peng Cui, Tong Zhang, Kun Kuang |
| Abstract | We consider the problem of learning linear prediction models with model misspecification bias. In such case, the collinearity among input variables may inflate the error of parameter estimation, resulting in instability of prediction results when training and test distributions do not match. In this paper we theoretically analyze this fundamental problem and propose a sample reweighting method that reduces collinearity among input variables. Our method can be seen as a pretreatment of data to improve the condition of design matrix, and it can then be combined with any standard learning method for parameter estimation and variable selection. Empirical studies on both simulation and real datasets demonstrate the effectiveness of our method in terms of more stable performance across different distributed data. |
| Tasks | |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12580v1 |
| https://arxiv.org/pdf/1911.12580v1.pdf | |
| PWC | https://paperswithcode.com/paper/stable-learning-via-sample-reweighting |
| Repo | |
| Framework | |
DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects
| Title | DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects |
| Authors | Edgar Tretschk, Ayush Tewari, Michael Zollhöfer, Vladislav Golyanik, Christian Theobalt |
| Abstract | Mesh autoencoders are commonly used for dimensionality reduction, sampling and mesh modeling. We propose a general-purpose DEep MEsh Autoencoder (DEMEA) which adds a novel embedded deformation layer to a graph-convolutional mesh autoencoder. The embedded deformation layer (EDL) is a differentiable deformable geometric proxy which explicitly models point displacements of non-rigid deformations in a lower dimensional space and serves as a local rigidity regularizer. DEMEA decouples the parameterization of the deformation from the final mesh resolution since the deformation is defined over a lower dimensional embedded deformation graph. We perform a large-scale study on four different datasets of deformable objects. Reasoning about the local rigidity of meshes using EDL allows us to achieve higher-quality results for highly deformable objects, compared to directly regressing vertex positions. We demonstrate multiple applications of DEMEA, including non-rigid 3D reconstruction from depth and shading cues, non-rigid surface tracking, as well as the transfer of deformations over different meshes. |
| Tasks | 3D Reconstruction, Dimensionality Reduction |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10290v1 |
| https://arxiv.org/pdf/1905.10290v1.pdf | |
| PWC | https://paperswithcode.com/paper/demea-deep-mesh-autoencoders-for-non-rigidly |
| Repo | |
| Framework | |
Conditional t-SNE: Complementary t-SNE embeddings through factoring out prior information
| Title | Conditional t-SNE: Complementary t-SNE embeddings through factoring out prior information |
| Authors | Bo Kang, Darío García García, Jefrey Lijffijt, Raúl Santos-Rodríguez, Tijl De Bie |
| Abstract | Dimensionality reduction and manifold learning methods such as t-Distributed Stochastic Neighbor Embedding (t-SNE) are routinely used to map high-dimensional data into a 2-dimensional space to visualize and explore the data. However, two dimensions are typically insufficient to capture all structure in the data, the salient structure is often already known, and it is not obvious how to extract the remaining information in a similarly effective manner. To fill this gap, we introduce \emph{conditional t-SNE} (ct-SNE), a generalization of t-SNE that discounts prior information from the embedding in the form of labels. To achieve this, we propose a conditioned version of the t-SNE objective, obtaining a single, integrated, and elegant method. ct-SNE has one extra parameter over t-SNE; we investigate its effects and show how to efficiently optimize the objective. Factoring out prior knowledge allows complementary structure to be captured in the embedding, providing new insights. Qualitative and quantitative empirical results on synthetic and (large) real data show ct-SNE is effective and achieves its goal. |
| Tasks | Dimensionality Reduction |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10086v1 |
| https://arxiv.org/pdf/1905.10086v1.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-t-sne-complementary-t-sne |
| Repo | |
| Framework | |
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
| Title | Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes |
| Authors | Chengquan Zhang, Borong Liang, Zuming Huang, Mengyi En, Junyu Han, Errui Ding, Xinghao Ding |
| Abstract | Previous scene text detection methods have progressed substantially over the past years. However, limited by the receptive field of CNNs and the simple representations like rectangle bounding box or quadrangle adopted to describe text, previous methods may fall short when dealing with more challenging text instances, such as extremely long text and arbitrarily shaped text. To address these two problems, we present a novel text detector namely LOMO, which localizes the text progressively for multiple times (or in other word, LOok More than Once). LOMO consists of a direct regressor (DR), an iterative refinement module (IRM) and a shape expression module (SEM). At first, text proposals in the form of quadrangle are generated by DR branch. Next, IRM progressively perceives the entire long text by iterative refinement based on the extracted feature blocks of preliminary proposals. Finally, a SEM is introduced to reconstruct more precise representation of irregular text by considering the geometry properties of text instance, including text region, text center line and border offsets. The state-of-the-art results on several public benchmarks including ICDAR2017-RCTW, SCUT-CTW1500, Total-Text, ICDAR2015 and ICDAR17-MLT confirm the striking robustness and effectiveness of LOMO. |
| Tasks | Scene Text Detection |
| Published | 2019-04-13 |
| URL | http://arxiv.org/abs/1904.06535v1 |
| http://arxiv.org/pdf/1904.06535v1.pdf | |
| PWC | https://paperswithcode.com/paper/look-more-than-once-an-accurate-detector-for |
| Repo | |
| Framework | |
Neural Transfer Learning for Cry-based Diagnosis of Perinatal Asphyxia
| Title | Neural Transfer Learning for Cry-based Diagnosis of Perinatal Asphyxia |
| Authors | Charles C. Onu, Jonathan Lebensold, William L. Hamilton, Doina Precup |
| Abstract | Despite continuing medical advances, the rate of newborn morbidity and mortality globally remains high, with over 6 million casualties every year. The prediction of pathologies affecting newborns based on their cry is thus of significant clinical interest, as it would facilitate the development of accessible, low-cost diagnostic tools\cut{ based on wearables and smartphones}. However, the inadequacy of clinically annotated datasets of infant cries limits progress on this task. This study explores a neural transfer learning approach to developing accurate and robust models for identifying infants that have suffered from perinatal asphyxia. In particular, we explore the hypothesis that representations learned from adult speech could inform and improve performance of models developed on infant speech. Our experiments show that models based on such representation transfer are resilient to different types and degrees of noise, as well as to signal loss in time and frequency domains. |
| Tasks | Transfer Learning |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.10199v3 |
| https://arxiv.org/pdf/1906.10199v3.pdf | |
| PWC | https://paperswithcode.com/paper/neural-transfer-learning-for-cry-based |
| Repo | |
| Framework | |
Deep-gKnock: nonlinear group-feature selection with deep neural network
| Title | Deep-gKnock: nonlinear group-feature selection with deep neural network |
| Authors | Guangyu Zhu, Tingting Zhao |
| Abstract | Feature selection is central to contemporary high-dimensional data analysis. Grouping structure among features arises naturally in various scientific problems. Many methods have been proposed to incorporate the grouping structure information into feature selection. However, these methods are normally restricted to a linear regression setting. To relax the linear constraint, we combine the deep neural networks (DNNs) with the recent Knockoffs technique, which has been successful in an individual feature selection context. We propose Deep-gKnock (Deep group-feature selection using Knockoffs) as a methodology for model interpretation and dimension reduction. Deep-gKnock performs model-free group-feature selection by controlling group-wise False Discovery Rate (gFDR). Our method improves the interpretability and reproducibility of DNNs. Experimental results on both synthetic and real data demonstrate that our method achieves superior power and accurate gFDR control compared with state-of-the-art methods. |
| Tasks | Dimensionality Reduction, Feature Selection |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10013v2 |
| https://arxiv.org/pdf/1905.10013v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-gknock-nonlinear-group-feature-selection |
| Repo | |
| Framework | |
