Paper Group ANR 622
Differentially Private Data Generative Models. Deep Emotion: A Computational Model of Emotion Using Deep Neural Networks. Task-Relevant Object Discovery and Categorization for Playing First-person Shooter Games. A Particle Filter based Multi-Objective Optimization Algorithm: PFOPS. Iterative Low-Rank Approximation for CNN Compression. Model-based R …
Differentially Private Data Generative Models
| Title | Differentially Private Data Generative Models |
| Authors | Qingrong Chen, Chong Xiang, Minhui Xue, Bo Li, Nikita Borisov, Dali Kaarfar, Haojin Zhu |
| Abstract | Deep neural networks (DNNs) have recently been widely adopted in various applications, and such success is largely due to a combination of algorithmic breakthroughs, computation resource improvements, and access to a large amount of data. However, the large-scale data collections required for deep learning often contain sensitive information, therefore raising many privacy concerns. Prior research has shown several successful attacks in inferring sensitive training data information, such as model inversion, membership inference, and generative adversarial networks (GAN) based leakage attacks against collaborative deep learning. In this paper, to enable learning efficiency as well as to generate data with privacy guarantees and high utility, we propose a differentially private autoencoder-based generative model (DP-AuGM) and a differentially private variational autoencoder-based generative model (DP-VaeGM). We evaluate the robustness of two proposed models. We show that DP-AuGM can effectively defend against the model inversion, membership inference, and GAN-based attacks. We also show that DP-VaeGM is robust against the membership inference attack. We conjecture that the key to defend against the model inversion and GAN-based attacks is not due to differential privacy but the perturbation of training data. Finally, we demonstrate that both DP-AuGM and DP-VaeGM can be easily integrated with real-world machine learning applications, such as machine learning as a service and federated learning, which are otherwise threatened by the membership inference attack and the GAN-based attack, respectively. |
| Tasks | Inference Attack |
| Published | 2018-12-06 |
| URL | http://arxiv.org/abs/1812.02274v1 |
| http://arxiv.org/pdf/1812.02274v1.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-data-generative-models |
| Repo | |
| Framework | |
Deep Emotion: A Computational Model of Emotion Using Deep Neural Networks
| Title | Deep Emotion: A Computational Model of Emotion Using Deep Neural Networks |
| Authors | Chie Hieida, Takato Horii, Takayuki Nagai |
| Abstract | Emotions are very important for human intelligence. For example, emotions are closely related to the appraisal of the internal bodily state and external stimuli. This helps us to respond quickly to the environment. Another important perspective in human intelligence is the role of emotions in decision-making. Moreover, the social aspect of emotions is also very important. Therefore, if the mechanism of emotions were elucidated, we could advance toward the essential understanding of our natural intelligence. In this study, a model of emotions is proposed to elucidate the mechanism of emotions through the computational model. Furthermore, from the viewpoint of partner robots, the model of emotions may help us to build robots that can have empathy for humans. To understand and sympathize with people’s feelings, the robots need to have their own emotions. This may allow robots to be accepted in human society. The proposed model is implemented using deep neural networks consisting of three modules, which interact with each other. Simulation results reveal that the proposed model exhibits reasonable behavior as the basic mechanism of emotion. |
| Tasks | Decision Making |
| Published | 2018-08-25 |
| URL | http://arxiv.org/abs/1808.08447v1 |
| http://arxiv.org/pdf/1808.08447v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-emotion-a-computational-model-of-emotion |
| Repo | |
| Framework | |
Task-Relevant Object Discovery and Categorization for Playing First-person Shooter Games
| Title | Task-Relevant Object Discovery and Categorization for Playing First-person Shooter Games |
| Authors | Junchi Liang, Abdeslam Boularias |
| Abstract | We consider the problem of learning to play first-person shooter (FPS) video games using raw screen images as observations and keyboard inputs as actions. The high-dimensionality of the observations in this type of applications leads to prohibitive needs of training data for model-free methods, such as the deep Q-network (DQN), and its recurrent variant DRQN. Thus, recent works focused on learning low-dimensional representations that may reduce the need for data. This paper presents a new and efficient method for learning such representations. Salient segments of consecutive frames are detected from their optical flow, and clustered based on their feature descriptors. The clusters typically correspond to different discovered categories of objects. Segments detected in new frames are then classified based on their nearest clusters. Because only a few categories are relevant to a given task, the importance of a category is defined as the correlation between its occurrence and the agent’s performance. The result is encoded as a vector indicating objects that are in the frame and their locations, and used as a side input to DRQN. Experiments on the game Doom provide a good evidence for the benefit of this approach. |
| Tasks | Optical Flow Estimation |
| Published | 2018-06-17 |
| URL | http://arxiv.org/abs/1806.06392v1 |
| http://arxiv.org/pdf/1806.06392v1.pdf | |
| PWC | https://paperswithcode.com/paper/task-relevant-object-discovery-and |
| Repo | |
| Framework | |
A Particle Filter based Multi-Objective Optimization Algorithm: PFOPS
| Title | A Particle Filter based Multi-Objective Optimization Algorithm: PFOPS |
| Authors | Bin Liu, Yaochu Jin |
| Abstract | This paper is concerned with a recently developed paradigm for population-based optimization, termed particle filter optimization (PFO). This paradigm is attractive in terms of coherence in theory and easiness in mathematical analysis and interpretation. Current PFO algorithms only work for single-objective optimization cases, while many real-life problems involve multiple objectives to be optimized simultaneously. To this end, we make an effort to extend the scope of application of the PFO paradigm to multi-objective optimization (MOO) cases. An idea called path sampling is adopted within the PFO scheme to balance the different objectives to be optimized. The resulting algorithm is thus termed PFO with Path Sampling (PFOPS). The validity of the presented algorithm is assessed based on three benchmark MOO experiments, in which the shapes of the Pareto fronts are convex, concave and discontinuous, respectively. |
| Tasks | |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09446v4 |
| http://arxiv.org/pdf/1808.09446v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-particle-filter-based-multi-objective |
| Repo | |
| Framework | |
Iterative Low-Rank Approximation for CNN Compression
| Title | Iterative Low-Rank Approximation for CNN Compression |
| Authors | Maksym Kholiavchenko |
| Abstract | Deep convolutional neural networks contain tens of millions of parameters, making them impossible to work efficiently on embedded devices. We propose iterative approach of applying low-rank approximation to compress deep convolutional neural networks. Since classification and object detection are the most favored tasks for embedded devices, we demonstrate the effectiveness of our approach by compressing AlexNet, VGG-16, YOLOv2 and Tiny YOLO networks. Our results show the superiority of the proposed method compared to non-repetitive ones. We demonstrate higher compression ratio providing less accuracy loss. |
| Tasks | Object Detection |
| Published | 2018-03-23 |
| URL | https://arxiv.org/abs/1803.08995v2 |
| https://arxiv.org/pdf/1803.08995v2.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-low-rank-approximation-for-cnn |
| Repo | |
| Framework | |
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches
| Title | Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches |
| Authors | Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford |
| Abstract | We study the sample complexity of model-based reinforcement learning (henceforth RL) in general contextual decision processes that require strategic exploration to find a near-optimal policy. We design new algorithms for RL with a generic model class and analyze their statistical properties. Our algorithms have sample complexity governed by a new structural parameter called the witness rank, which we show to be small in several settings of interest, including factored MDPs. We also show that the witness rank is never larger than the recently proposed Bellman rank parameter governing the sample complexity of the model-free algorithm OLIVE (Jiang et al., 2017), the only other provably sample-efficient algorithm for global exploration at this level of generality. Focusing on the special case of factored MDPs, we prove an exponential lower bound for a general class of model-free approaches, including OLIVE, which, when combined with our algorithmic results, demonstrates exponential separation between model-based and model-free RL in some rich-observation settings. |
| Tasks | |
| Published | 2018-11-21 |
| URL | https://arxiv.org/abs/1811.08540v3 |
| https://arxiv.org/pdf/1811.08540v3.pdf | |
| PWC | https://paperswithcode.com/paper/model-based-rl-in-contextual-decision |
| Repo | |
| Framework | |
Ensemble Method for Censored Demand Prediction
| Title | Ensemble Method for Censored Demand Prediction |
| Authors | Evgeniy M. Ozhegov, Daria Teterina |
| Abstract | Many economic applications including optimal pricing and inventory management requires prediction of demand based on sales data and estimation of sales reaction to a price change. There is a wide range of econometric approaches which are used to correct a bias in estimates of demand parameters on censored sales data. These approaches can also be applied to various classes of machine learning models to reduce the prediction error of sales volume. In this study we construct two ensemble models for demand prediction with and without accounting for demand censorship. Accounting for sales censorship is based on the idea of censored quantile regression method where the model estimation is splitted on two separate parts: a) prediction of zero sales by classification model; and b) prediction of non-zero sales by regression model. Models with and without accounting for censorship are based on the predictions aggregations of Least squares, Ridge and Lasso regressions and Random Forest model. Having estimated the predictive properties of both models, we empirically test the best predictive power of the model that takes into account the censored nature of demand. We also show that machine learning method with censorship accounting provide bias corrected estimates of demand sensitivity for price change similar to econometric models. |
| Tasks | |
| Published | 2018-10-22 |
| URL | http://arxiv.org/abs/1810.09166v1 |
| http://arxiv.org/pdf/1810.09166v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensemble-method-for-censored-demand |
| Repo | |
| Framework | |
Infinite Mixture of Inverted Dirichlet Distributions
| Title | Infinite Mixture of Inverted Dirichlet Distributions |
| Authors | Zhanyu Ma, Yuping Lai |
| Abstract | In this work, we develop a novel Bayesian estimation method for the Dirichlet process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very flexible for modeling vectors with positive elements. The recently proposed extended variational inference (EVI) framework is adopted to derive an analytically tractable solution. The convergency of the proposed algorithm is theoretically guaranteed by introducing single lower bound approximation to the original objective function in the VI framework. In principle, the proposed model can be viewed as an infinite inverted Dirichelt mixture model (InIDMM) that allows the automatic determination of the number of mixture components from data. Therefore, the problem of pre-determining the optimal number of mixing components has been overcome. Moreover, the problems of over-fitting and under-fitting are avoided by the Bayesian estimation approach. Comparing with several recently proposed DP-related methods, the good performance and effectiveness of the proposed method have been demonstrated with both synthesized data and real data evaluations. |
| Tasks | |
| Published | 2018-07-27 |
| URL | https://arxiv.org/abs/1807.10693v2 |
| https://arxiv.org/pdf/1807.10693v2.pdf | |
| PWC | https://paperswithcode.com/paper/infinite-mixture-of-inverted-dirichlet |
| Repo | |
| Framework | |
Prospects for Theranostics in Neurosurgical Imaging: Empowering Confocal Laser Endomicroscopy Diagnostics via Deep Learning
| Title | Prospects for Theranostics in Neurosurgical Imaging: Empowering Confocal Laser Endomicroscopy Diagnostics via Deep Learning |
| Authors | Mohammadhassan Izadyyazdanabadi, Evgenii Belykh, Michael Mooney, Jennifer Eschbacher, Peter Nakaji, Yezhou Yang, Mark C. Preul |
| Abstract | Confocal laser endomicroscopy (CLE) is an advanced optical fluorescence imaging technology that has the potential to increase intraoperative precision, extend resection, and tailor surgery for malignant invasive brain tumors because of its subcellular dimension resolution. Despite its promising diagnostic potential, interpreting the gray tone fluorescence images can be difficult for untrained users. In this review, we provide a detailed description of bioinformatical analysis methodology of CLE images that begins to assist the neurosurgeon and pathologist to rapidly connect on-the-fly intraoperative imaging, pathology, and surgical observation into a conclusionary system within the concept of theranostics. We present an overview and discuss deep learning models for automatic detection of the diagnostic CLE images and discuss various training regimes and ensemble modeling effect on the power of deep learning predictive models. Two major approaches reviewed in this paper include the models that can automatically classify CLE images into diagnostic/nondiagnostic, glioma/nonglioma, tumor/injury/normal categories and models that can localize histological features on the CLE images using weakly supervised methods. We also briefly review advances in the deep learning approaches used for CLE image analysis in other organs. Significant advances in speed and precision of automated diagnostic frame selection would augment the diagnostic potential of CLE, improve operative workflow and integration into brain tumor surgery. Such technology and bioinformatics analytics lend themselves to improved precision, personalization, and theranostics in brain tumor treatment. |
| Tasks | |
| Published | 2018-04-26 |
| URL | http://arxiv.org/abs/1804.09873v2 |
| http://arxiv.org/pdf/1804.09873v2.pdf | |
| PWC | https://paperswithcode.com/paper/prospects-for-theranostics-in-neurosurgical |
| Repo | |
| Framework | |
GridFace: Face Rectification via Learning Local Homography Transformations
| Title | GridFace: Face Rectification via Learning Local Homography Transformations |
| Authors | Erjin Zhou, Zhimin Cao, Jian Sun |
| Abstract | In this paper, we propose a method, called GridFace, to reduce facial geometric variations and improve the recognition performance. Our method rectifies the face by local homography transformations, which are estimated by a face rectification network. To encourage the image generation with canonical views, we apply a regularization based on the natural face distribution. We learn the rectification network and recognition network in an end-to-end manner. Extensive experiments show our method greatly reduces geometric variations, and gains significant improvements in unconstrained face recognition scenarios. |
| Tasks | Face Recognition, Image Generation |
| Published | 2018-08-19 |
| URL | http://arxiv.org/abs/1808.06210v1 |
| http://arxiv.org/pdf/1808.06210v1.pdf | |
| PWC | https://paperswithcode.com/paper/gridface-face-rectification-via-learning |
| Repo | |
| Framework | |
Multi-resolution Tensor Learning for Large-Scale Spatial Data
| Title | Multi-resolution Tensor Learning for Large-Scale Spatial Data |
| Authors | Stephan Zheng, Rose Yu, Yisong Yue |
| Abstract | High-dimensional tensor models are notoriously computationally expensive to train. We present a meta-learning algorithm, MMT, that can significantly speed up the process for spatial tensor models. MMT leverages the property that spatial data can be viewed at multiple resolutions, which are related by coarsening and finegraining from one resolution to another. Using this property, MMT learns a tensor model by starting from a coarse resolution and iteratively increasing the model complexity. In order to not “over-train” on coarse resolution models, we investigate an information-theoretic fine-graining criterion to decide when to transition into higher-resolution models. We provide both theoretical and empirical evidence for the advantages of this approach. When applied to two real-world large-scale spatial datasets for basketball player and animal behavior modeling, our approach demonstrate 3 key benefits: 1) it efficiently captures higher-order interactions (i.e., tensor latent factors), 2) it is orders of magnitude faster than fixed resolution learning and scales to very fine-grained spatial resolutions, and 3) it reliably yields accurate and interpretable models. |
| Tasks | Meta-Learning |
| Published | 2018-02-19 |
| URL | http://arxiv.org/abs/1802.06825v2 |
| http://arxiv.org/pdf/1802.06825v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-resolution-tensor-learning-for-large |
| Repo | |
| Framework | |
REAS: Combining Numerical Optimization with SAT Solving
| Title | REAS: Combining Numerical Optimization with SAT Solving |
| Authors | Jeevana Priya Inala, Sicun Gao, Soonho Kong, Armando Solar-Lezama |
| Abstract | In this paper, we present ReaS, a technique that combines numerical optimization with SAT solving to synthesize unknowns in a program that involves discrete and floating point computation. ReaS makes the program end-to-end differentiable by smoothing any Boolean expression that introduces discontinuity such as conditionals and relaxing the Boolean unknowns so that numerical optimization can be performed. On top of this, ReaS uses a SAT solver to help the numerical search overcome local solutions by incrementally fixing values to the Boolean expressions. We evaluated the approach on 5 case studies involving hybrid systems and show that ReaS can synthesize programs that could not be solved by previous SMT approaches. |
| Tasks | |
| Published | 2018-02-13 |
| URL | http://arxiv.org/abs/1802.04408v1 |
| http://arxiv.org/pdf/1802.04408v1.pdf | |
| PWC | https://paperswithcode.com/paper/reas-combining-numerical-optimization-with |
| Repo | |
| Framework | |
Non-Gaussian information from weak lensing data via deep learning
| Title | Non-Gaussian information from weak lensing data via deep learning |
| Authors | Arushi Gupta, José Manuel Zorrilla Matilla, Daniel Hsu, Zoltán Haiman |
| Abstract | Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and apply a 2D convolutional neural network to simulated noiseless lensing maps covering 96 different cosmological models over a range of {$\Omega_m,\sigma_8$}. Using the area of the confidence contour in the {$\Omega_m,\sigma_8$} plane as a figure-of-merit, derived from simulated convergence maps smoothed on a scale of 1.0 arcmin, we show that the neural network yields $\approx 5 \times$ tighter constraints than the power spectrum, and $\approx 4 \times$ tighter than the lensing peaks. Such gains illustrate the extent to which weak lensing data encode cosmological information not accessible to the power spectrum or even other, non-Gaussian statistics such as lensing peaks. |
| Tasks | |
| Published | 2018-02-04 |
| URL | http://arxiv.org/abs/1802.01212v3 |
| http://arxiv.org/pdf/1802.01212v3.pdf | |
| PWC | https://paperswithcode.com/paper/non-gaussian-information-from-weak-lensing |
| Repo | |
| Framework | |
Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control
| Title | Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control |
| Authors | Moritz August, José Miguel Hernández-Lobato |
| Abstract | In this work we introduce the application of black-box quantum control as an interesting rein- forcement learning problem to the machine learning community. We analyze the structure of the reinforcement learning problems arising in quantum physics and argue that agents parameterized by long short-term memory (LSTM) networks trained via stochastic policy gradients yield a general method to solving them. In this context we introduce a variant of the proximal policy optimization (PPO) algorithm called the memory proximal policy optimization (MPPO) which is based on this analysis. We then show how it can be applied to specific learning tasks and present results of nu- merical experiments showing that our method achieves state-of-the-art results for several learning tasks in quantum control with discrete and continouous control parameters. |
| Tasks | |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.04063v2 |
| http://arxiv.org/pdf/1802.04063v2.pdf | |
| PWC | https://paperswithcode.com/paper/taking-gradients-through-experiments-lstms |
| Repo | |
| Framework | |
Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset
| Title | Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset |
| Authors | Qi Guo, Iuri Frosio, Orazio Gallo, Todd Zickler, Jan Kautz |
| Abstract | Scene motion, multiple reflections, and sensor noise introduce artifacts in the depth reconstruction performed by time-of-flight cameras. We propose a two-stage, deep-learning approach to address all of these sources of artifacts simultaneously. We also introduce FLAT, a synthetic dataset of 2000 ToF measurements that capture all of these nonidealities, and allows to simulate different camera hardware. Using the Kinect 2 camera as a baseline, we show improved reconstruction errors over state-of-the-art methods, on both simulated and real data. |
| Tasks | |
| Published | 2018-07-26 |
| URL | http://arxiv.org/abs/1807.10376v1 |
| http://arxiv.org/pdf/1807.10376v1.pdf | |
| PWC | https://paperswithcode.com/paper/tackling-3d-tof-artifacts-through-learning |
| Repo | |
| Framework | |
