Paper Group ANR 381
An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient. FusionMapping: Learning Depth Prediction with Monocular Images and 2D Laser Scans. Identify the cells’ nuclei based on the deep learning neural network. The Query Translation Landscape: a Survey. CopyCAT: Taking Control of Neural Policies with Constant Attacks. Differe …
An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient
| Title | An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient |
| Authors | Pan Xu, Felicia Gao, Quanquan Gu |
| Abstract | We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\epsilon$-approximate stationary point of the performance function within $O(1/\epsilon^{5/3})$ trajectories. This sample complexity improves upon the best known result $O(1/\epsilon^2)$ by a factor of $O(1/\epsilon^{1/3})$. At the core of our analysis is (i) a tighter upper bound for the variance of importance sampling weights, where we prove that the variance can be controlled by the parameter distance between different policies; and (ii) a fine-grained analysis of the epoch length and batch size parameters such that we can significantly reduce the number of trajectories required in each iteration of SVRPG. We also empirically demonstrate the effectiveness of our theoretical claims of batch sizes on reinforcement learning benchmark tasks. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12615v1 |
| https://arxiv.org/pdf/1905.12615v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-improved-convergence-analysis-of |
| Repo | |
| Framework | |
FusionMapping: Learning Depth Prediction with Monocular Images and 2D Laser Scans
| Title | FusionMapping: Learning Depth Prediction with Monocular Images and 2D Laser Scans |
| Authors | Peng Yin, Jianing Qian, Yibo Cao, David Held, Howie Choset |
| Abstract | Acquiring accurate three-dimensional depth information conventionally requires expensive multibeam LiDAR devices. Recently, researchers have developed a less expensive option by predicting depth information from two-dimensional color imagery. However, there still exists a substantial gap in accuracy between depth information estimated from two-dimensional images and real LiDAR point-cloud. In this paper, we introduce a fusion-based depth prediction method, called FusionMapping. This is the first method that fuses colored imagery and two-dimensional laser scan to estimate depth in-formation. More specifically, we propose an autoencoder-based depth prediction network and a novel point-cloud refinement network for depth estimation. We analyze the performance of our FusionMapping approach on the KITTI LiDAR odometry dataset and an indoor mobile robot system. The results show that our introduced approach estimates depth with better accuracy when compared to existing methods. |
| Tasks | Depth Estimation |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1912.00096v1 |
| https://arxiv.org/pdf/1912.00096v1.pdf | |
| PWC | https://paperswithcode.com/paper/fusionmapping-learning-depth-prediction-with |
| Repo | |
| Framework | |
Identify the cells’ nuclei based on the deep learning neural network
| Title | Identify the cells’ nuclei based on the deep learning neural network |
| Authors | Tianyang Zhang, Rui Ma |
| Abstract | Identify the cells’ nuclei is the important point for most medical analyses. To assist doctors finding the accurate cell’ nuclei location automatically is highly demanded in the clinical practice. Recently, fully convolutional neural network (FCNs) serve as the back-bone in many image segmentation, like liver and tumer segmentation in medical field, human body block in technical filed. The cells’ nuclei identification task is also kind of image segmentation. To achieve this, we prefer to use deep learning algorithms. we construct three general frameworks, one is Mask Region-based Convolutional Neural Network (Mask RCNN), which has the high performance in many image segmentations, one is U-net, which has the high generalization performance on small dataset and the other is DenseUNet, which is mixture network architecture with Dense Net and U-net. we compare the performance of these three frameworks. And we evaluated our method on the dataset of data science bowl 2018 challenge. For single model without any ensemble, they all have good performance. |
| Tasks | Semantic Segmentation |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09830v1 |
| https://arxiv.org/pdf/1911.09830v1.pdf | |
| PWC | https://paperswithcode.com/paper/identify-the-cells-nuclei-based-on-the-deep |
| Repo | |
| Framework | |
The Query Translation Landscape: a Survey
| Title | The Query Translation Landscape: a Survey |
| Authors | Mohamed Nadjib Mami, Damien Graux, Harsh Thakkar, Simon Scerri, Sören Auer, Jens Lehmann |
| Abstract | Whereas the availability of data has seen a manyfold increase in past years, its value can be only shown if the data variety is effectively tackled —one of the prominent Big Data challenges. The lack of data interoperability limits the potential of its collective use for novel applications. Achieving interoperability through the full transformation and integration of diverse data structures remains an ideal that is hard, if not impossible, to achieve. Instead, methods that can simultaneously interpret different types of data available in different data structures and formats have been explored. On the other hand, many query languages have been designed to enable users to interact with the data, from relational, to object-oriented, to hierarchical, to the multitude emerging NoSQL languages. Therefore, the interoperability issue could be solved not by enforcing physical data transformation, but by looking at techniques that are able to query heterogeneous sources using one uniform language. Both industry and research communities have been keen to develop such techniques, which require the translation of a chosen ‘universal’ query language to the various data model specific query languages that make the underlying data accessible. In this article, we survey more than forty query translation methods and tools for popular query languages, and classify them according to eight criteria. In particular, we study which query language is a most suitable candidate for that ‘universal’ query language. Further, the results enable us to discover the weakly addressed and unexplored translation paths, to discover gaps and to learn lessons that can benefit future research in the area. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.03118v1 |
| https://arxiv.org/pdf/1910.03118v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-query-translation-landscape-a-survey |
| Repo | |
| Framework | |
CopyCAT: Taking Control of Neural Policies with Constant Attacks
| Title | CopyCAT: Taking Control of Neural Policies with Constant Attacks |
| Authors | Léonard Hussenot, Matthieu Geist, Olivier Pietquin |
| Abstract | We propose a new perspective on adversarial attacks against deep reinforcement learning agents. Our main contribution is CopyCAT, a targeted attack able to consistently lure an agent into following an outsider’s policy. It is pre-computed, therefore fast inferred, and could thus be usable in a real-time scenario. We show its effectiveness on Atari 2600 games in the novel read-only setting. In this setting, the adversary cannot directly modify the agent’s state – its representation of the environment – but can only attack the agent’s observation – its perception of the environment. Directly modifying the agent’s state would require a write-access to the agent’s inner workings and we argue that this assumption is too strong in realistic settings. |
| Tasks | Atari Games |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12282v2 |
| https://arxiv.org/pdf/1905.12282v2.pdf | |
| PWC | https://paperswithcode.com/paper/targeted-attacks-on-deep-reinforcement |
| Repo | |
| Framework | |
Differentially Private Summation with Multi-Message Shuffling
| Title | Differentially Private Summation with Multi-Message Shuffling |
| Authors | Borja Balle, James Bell, Adria Gascon, Kobbi Nissim |
| Abstract | In recent work, Cheu et al. (Eurocrypt 2019) proposed a protocol for $n$-party real summation in the shuffle model of differential privacy with $O_{\epsilon, \delta}(1)$ error and $\Theta(\epsilon\sqrt{n})$ one-bit messages per party. In contrast, every local model protocol for real summation must incur error $\Omega(1/\sqrt{n})$, and there exist protocols matching this lower bound which require just one bit of communication per party. Whether this gap in number of messages is necessary was left open by Cheu et al. In this note we show a protocol with $O(1/\epsilon)$ error and $O(\log(n/\delta))$ messages of size $O(\log(n))$ per party. This protocol is based on the work of Ishai et al.\ (FOCS 2006) showing how to implement distributed summation from secure shuffling, and the observation that this allows simulating the Laplace mechanism in the shuffle model. |
| Tasks | |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.09116v3 |
| https://arxiv.org/pdf/1906.09116v3.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-summation-with-multi |
| Repo | |
| Framework | |
Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments
| Title | Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments |
| Authors | Xueting Li, Sifei Liu, Kihwan Kim, Xiaolong Wang, Ming-Hsuan Yang, Jan Kautz |
| Abstract | Affordance modeling plays an important role in visual understanding. In this paper, we aim to predict affordances of 3D indoor scenes, specifically what human poses are afforded by a given indoor environment, such as sitting on a chair or standing on the floor. In order to predict valid affordances and learn possible 3D human poses in indoor scenes, we need to understand the semantic and geometric structure of a scene as well as its potential interactions with a human. To learn such a model, a large-scale dataset of 3D indoor affordances is required. In this work, we build a fully automatic 3D pose synthesizer that fuses semantic knowledge from a large number of 2D poses extracted from TV shows as well as 3D geometric knowledge from voxel representations of indoor scenes. With the data created by the synthesizer, we introduce a 3D pose generative model to predict semantically plausible and physically feasible human poses within a given scene (provided as a single RGB, RGB-D, or depth image). We demonstrate that our human affordance prediction method consistently outperforms existing state-of-the-art methods. |
| Tasks | |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05690v2 |
| http://arxiv.org/pdf/1903.05690v2.pdf | |
| PWC | https://paperswithcode.com/paper/putting-humans-in-a-scene-learning-affordance |
| Repo | |
| Framework | |
Refined Complexity of PCA with Outliers
| Title | Refined Complexity of PCA with Outliers |
| Authors | Fedor V. Fomin, Petr A. Golovach, Fahad Panolan, Kirill Simonov |
| Abstract | Principal component analysis (PCA) is one of the most fundamental procedures in exploratory data analysis and is the basic step in applications ranging from quantitative finance and bioinformatics to image analysis and neuroscience. However, it is well-documented that the applicability of PCA in many real scenarios could be constrained by an “immune deficiency” to outliers such as corrupted observations. We consider the following algorithmic question about the PCA with outliers. For a set of $n$ points in $\mathbb{R}^{d}$, how to learn a subset of points, say 1% of the total number of points, such that the remaining part of the points is best fit into some unknown $r$-dimensional subspace? We provide a rigorous algorithmic analysis of the problem. We show that the problem is solvable in time $n^{O(d^2)}$. In particular, for constant dimension the problem is solvable in polynomial time. We complement the algorithmic result by the lower bound, showing that unless Exponential Time Hypothesis fails, in time $f(d)n^{o(d)}$, for any function $f$ of $d$, it is impossible not only to solve the problem exactly but even to approximate it within a constant factor. |
| Tasks | |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.04124v1 |
| https://arxiv.org/pdf/1905.04124v1.pdf | |
| PWC | https://paperswithcode.com/paper/refined-complexity-of-pca-with-outliers |
| Repo | |
| Framework | |
Explaining a prediction in some nonlinear models
| Title | Explaining a prediction in some nonlinear models |
| Authors | Cosimo Izzo |
| Abstract | In this article we will analyse how to compute the contribution of each input value to its aggregate output in some nonlinear models. Regression and classification applications, together with related algorithms for deep neural networks are presented. The proposed approach merges two methods currently present in the literature: integrated gradient and deep Taylor decomposition. Compared to DeepLIFT and Deep SHAP, it provides a natural choice of the reference point peculiar to the model at use. |
| Tasks | |
| Published | 2019-04-21 |
| URL | https://arxiv.org/abs/1904.09615v3 |
| https://arxiv.org/pdf/1904.09615v3.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-a-prediction-in-some-nonlinear |
| Repo | |
| Framework | |
Graph Spectral Embedding for Parsimonious Transmission of Multivariate Time Series
| Title | Graph Spectral Embedding for Parsimonious Transmission of Multivariate Time Series |
| Authors | Lihan Yao, Paul Bendich |
| Abstract | We propose a graph spectral representation of time series data that 1) is parsimoniously encoded to user-demanded resolution; 2) is unsupervised and performant in data-constrained scenarios; 3) captures event and event-transition structure within the time series; and 4) has near-linear computational complexity in both signal length and ambient dimension. This representation, which we call Laplacian Events Signal Segmentation (LESS), can be computed on time series of arbitrary dimension and originating from sensors of arbitrary type. Hence, time series originating from sensors of heterogeneous type can be compressed to levels demanded by constrained-communication environments, before being fused at a common center. Temporal dynamics of the data is summarized without explicit partitioning or probabilistic modeling. As a proof-of-principle, we apply this technique on high dimensional wavelet coefficients computed from the Free Spoken Digit Dataset to generate a memory efficient representation that is interpretable. Due to its unsupervised and non-parametric nature, LESS representations remain performant in the digit classification task despite the absence of labels and limited data. |
| Tasks | Time Series |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04689v1 |
| https://arxiv.org/pdf/1910.04689v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-spectral-embedding-for-parsimonious |
| Repo | |
| Framework | |
Improving Malaria Parasite Detection from Red Blood Cell using Deep Convolutional Neural Networks
| Title | Improving Malaria Parasite Detection from Red Blood Cell using Deep Convolutional Neural Networks |
| Authors | Aimon Rahman, Hasib Zunair, M Sohel Rahman, Jesia Quader Yuki, Sabyasachi Biswas, Md Ashraful Alam, Nabila Binte Alam, M. R. C. Mahdy |
| Abstract | Malaria is a female anopheles mosquito-bite inflicted life-threatening disease which is considered endemic in many parts of the world. This article focuses on improving malaria detection from patches segmented from microscopic images of red blood cell smears by introducing a deep convolutional neural network. Compared to the traditional methods that use tedious hand engineering feature extraction, the proposed method uses deep learning in an end-to-end arrangement that performs both feature extraction and classification directly from the raw segmented patches of the red blood smears. The dataset used in this study was taken from National Institute of Health named NIH Malaria Dataset. The evaluation metric accuracy and loss along with 5-fold cross validation was used to compare and select the best performing architecture. To maximize the performance, existing standard pre-processing techniques from the literature has also been experimented. In addition, several other complex architectures have been implemented and tested to pick the best performing model. A holdout test has also been conducted to verify how well the proposed model generalizes on unseen data. Our best model achieves an accuracy of almost 97.77%. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.10418v1 |
| https://arxiv.org/pdf/1907.10418v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-malaria-parasite-detection-from-red |
| Repo | |
| Framework | |
A different take on the best-first game tree pruning algorithms
| Title | A different take on the best-first game tree pruning algorithms |
| Authors | Ishan Srivastava |
| Abstract | The alpha-beta pruning algorithms have been popular in game tree searching ever since they were discovered. Numerous enhancements are proposed in literature and it is often overwhelming as to which would be the best for implementation. A certain enhancement can take far too long to fine tune its hyper parameters or to decide whether it is going to not make much of a difference due to the memory limitations. On the other hand are the best first pruning techniques, mostly the counterparts of the infamous SSS* algorithm, the algorithm which proved out to be disruptive at the time of its discovery but gradually became outcast as being too memory intensive and having a higher time complexity. Later research doesn’t see the best first approaches to be completely different from the depth first based enhancements but both seem to be transitionary in the sense that a best first approach could be looked as a depth first approach with a certain set of enhancements and with the growing power of the computers, SSS* didn’t seem to be as taxing on the memory either. Even so, there seems to be quite difficulty in understanding the nature of the SSS* algorithm, why it does what it does and it being termed as being too complex to fathom, visualize and understand on an intellectual level. This article tries to bridge this gap and provide some experimental results comparing the two with the most promising advances. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03388v1 |
| https://arxiv.org/pdf/1911.03388v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-different-take-on-the-best-first-game-tree |
| Repo | |
| Framework | |
An Efficient B-spline-Based Kinodynamic Replanning Framework for Quadrotors
| Title | An Efficient B-spline-Based Kinodynamic Replanning Framework for Quadrotors |
| Authors | Wenchao Ding, Wenliang Gao, Kaixuan Wang, Shaojie Shen |
| Abstract | Trajectory replanning for quadrotors is essential to enable fully autonomous flight in unknown environments. Hierarchical motion planning frameworks, which combine path planning with path parameterization, are popular due to their time efficiency. However, the path planning cannot properly deal with non-static initial states of the quadrotor, which may result in non-smooth or even dynamically infeasible trajectories. In this paper, we present an efficient kinodynamic replanning framework by exploiting the advantageous properties of the B-spline, which facilitates dealing with the non-static state and guarantees safety and dynamical feasibility. Our framework starts with an efficient B-spline-based kinodynamic (EBK) search algorithm which finds a feasible trajectory with minimum control effort and time. To compensate for the discretization induced by the EBK search, an elastic optimization (EO) approach is proposed to refine the control point placement to the optimal location. Systematic comparisons against the state-of-the-art are conducted to validate the performance. Comprehensive onboard experiments using two different vision-based quadrotors are carried out showing the general applicability of the framework. |
| Tasks | Motion Planning |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09785v1 |
| https://arxiv.org/pdf/1906.09785v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-b-spline-based-kinodynamic |
| Repo | |
| Framework | |
Designing Trustworthy AI: A Human-Machine Teaming Framework to Guide Development
| Title | Designing Trustworthy AI: A Human-Machine Teaming Framework to Guide Development |
| Authors | Carol J. Smith |
| Abstract | Artificial intelligence (AI) holds great promise to empower us with knowledge and augment our effectiveness. We can – and must – ensure that we keep humans safe and in control, particularly with regard to government and public sector applications that affect broad populations. How can AI development teams harness the power of AI systems and design them to be valuable to humans? Diverse teams are needed to build trustworthy artificial intelligent systems, and those teams need to coalesce around a shared set of ethics. There are many discussions in the AI field about ethics and trust, but there are few frameworks available for people to use as guidance when creating these systems. The Human-Machine Teaming (HMT) Framework for Designing Ethical AI Experiences described in this paper, when used with a set of technical ethics, will guide AI development teams to create AI systems that are accountable, de-risked, respectful, secure, honest, and usable. To support the team’s efforts, activities to understand people’s needs and concerns will be introduced along with the themes to support the team’s efforts. For example, usability testing can help determine if the audience understands how the AI system works and complies with the HMT Framework. The HMT Framework is based on reviews of existing ethical codes and best practices in human-computer interaction and software development. Human-machine teams are strongest when human users can trust AI systems to behave as expected, safely, securely, and understandably. Using the HMT Framework to design trustworthy AI systems will provide support to teams in identifying potential issues ahead of time and making great experiences for humans. |
| Tasks | |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03515v1 |
| https://arxiv.org/pdf/1910.03515v1.pdf | |
| PWC | https://paperswithcode.com/paper/designing-trustworthy-ai-a-human-machine |
| Repo | |
| Framework | |
A Kaczmarz Algorithm for Solving Tree Based Distributed Systems of Equations
| Title | A Kaczmarz Algorithm for Solving Tree Based Distributed Systems of Equations |
| Authors | Chinmay Hegde, Fritz Keinert, Eric S. Weber |
| Abstract | The Kaczmarz algorithm is an iterative method for solving systems of linear equations. We introduce a modified Kaczmarz algorithm for solving systems of linear equations in a distributed environment, i.e. the equations within the system are distributed over multiple nodes within a network. The modification we introduce is designed for a network with a tree structure that allows for passage of solution estimates between the nodes in the network. We prove that the modified algorithm converges under no additional assumptions on the equations. We demonstrate that the algorithm converges to the solution, or the solution of minimal norm, when the system is consistent. We also demonstrate that in the case of an inconsistent system of equations, the modified relaxed Kaczmarz algorithm converges to a weighted least squares solution as the relaxation parameter approaches $0$. |
| Tasks | |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.05732v1 |
| http://arxiv.org/pdf/1904.05732v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-kaczmarz-algorithm-for-solving-tree-based |
| Repo | |
| Framework | |
