Paper Group ANR 661
Strategyproof Linear Regression in High Dimensions. Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions. Combining Multiple Algorithms in Classifier Ensembles using Generalized Mixture Functions. Cross-Domain Transfer in Reinforcement Learning using Target Apprentice. Analog simulator of integro-differential equations wit …
Strategyproof Linear Regression in High Dimensions
| Title | Strategyproof Linear Regression in High Dimensions |
| Authors | Yiling Chen, Chara Podimata, Ariel D. Procaccia, Nisarg Shah |
| Abstract | This paper is part of an emerging line of work at the intersection of machine learning and mechanism design, which aims to avoid noise in training data by correctly aligning the incentives of data sources. Specifically, we focus on the ubiquitous problem of linear regression, where strategyproof mechanisms have previously been identified in two dimensions. In our setting, agents have single-peaked preferences and can manipulate only their response variables. Our main contribution is the discovery of a family of group strategyproof linear regression mechanisms in any number of dimensions, which we call generalized resistant hyperplane mechanisms. The game-theoretic properties of these mechanisms – and, in fact, their very existence – are established through a connection to a discrete version of the Ham Sandwich Theorem. |
| Tasks | |
| Published | 2018-05-27 |
| URL | http://arxiv.org/abs/1805.10693v1 |
| http://arxiv.org/pdf/1805.10693v1.pdf | |
| PWC | https://paperswithcode.com/paper/strategyproof-linear-regression-in-high |
| Repo | |
| Framework | |
Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
| Title | Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions |
| Authors | Li Yao, Jordan Prosky, Eric Poblenz, Ben Covington, Kevin Lyman |
| Abstract | Diagnostic imaging often requires the simultaneous identification of a multitude of findings of varied size and appearance. Beyond global indication of said findings, the prediction and display of localization information improves trust in and understanding of results when augmenting clinical workflow. Medical training data rarely includes more than global image-level labels as segmentations are time-consuming and expensive to collect. We introduce an approach to managing these practical constraints by applying a novel architecture which learns at multiple resolutions while generating saliency maps with weak supervision. Further, we parameterize the Log-Sum-Exp pooling function with a learnable lower-bounded adaptation (LSE-LBA) to build in a sharpness prior and better handle localizing abnormalities of different sizes using only image-level labels. Applying this approach to interpreting chest x-rays, we set the state of the art on 9 abnormalities in the NIH’s CXR14 dataset while generating saliency maps with the highest resolution to date. |
| Tasks | Medical Diagnosis |
| Published | 2018-03-21 |
| URL | http://arxiv.org/abs/1803.07703v1 |
| http://arxiv.org/pdf/1803.07703v1.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-medical-diagnosis-and |
| Repo | |
| Framework | |
Combining Multiple Algorithms in Classifier Ensembles using Generalized Mixture Functions
| Title | Combining Multiple Algorithms in Classifier Ensembles using Generalized Mixture Functions |
| Authors | Valdigleis S. Costaa, Antonio Diego S. Farias, Benjamín Bedregal, Regivan H. N. Santiago, Anne Magaly de P. Canuto |
| Abstract | Classifier ensembles are pattern recognition structures composed of a set of classification algorithms (members), organized in a parallel way, and a combination method with the aim of increasing the classification accuracy of a classification system. In this study, we investigate the application of a generalized mixture (GM) functions as a new approach for providing an efficient combination procedure for these systems through the use of dynamic weights in the combination process. Therefore, we present three GM functions to be applied as a combination method. The main advantage of these functions is that they can define dynamic weights at the member outputs, making the combination process more efficient. In order to evaluate the feasibility of the proposed approach, an empirical analysis is conducted, applying classifier ensembles to 25 different classification data sets. In this analysis, we compare the use of the proposed approaches to ensembles using traditional combination methods as well as the state-of-the-art ensemble methods. Our findings indicated gains in terms of performance when comparing the proposed approaches to the traditional ones as well as comparable results with the state-of-the-art methods. |
| Tasks | |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01540v1 |
| http://arxiv.org/pdf/1806.01540v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-multiple-algorithms-in-classifier |
| Repo | |
| Framework | |
Cross-Domain Transfer in Reinforcement Learning using Target Apprentice
| Title | Cross-Domain Transfer in Reinforcement Learning using Target Apprentice |
| Authors | Girish Joshi, Girish Chowdhary |
| Abstract | In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the target task learning. We propose to adapt and reuse the mapped source task optimal-policy directly in related domains. We show the optimal policy from a related source task can be near optimal in target domain provided an adaptive policy accounts for the model error between target and source. The main benefit of this policy augmentation is generalizing policies across multiple related domains without having to re-learn the new tasks. Our results show that this architecture leads to better sample efficiency in the transfer, reducing sample complexity of target task learning to target apprentice learning. |
| Tasks | Transfer Learning |
| Published | 2018-01-22 |
| URL | http://arxiv.org/abs/1801.06920v1 |
| http://arxiv.org/pdf/1801.06920v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-domain-transfer-in-reinforcement |
| Repo | |
| Framework | |
Analog simulator of integro-differential equations with classical memristors
| Title | Analog simulator of integro-differential equations with classical memristors |
| Authors | G. Alvarado Barrios, J. C. Retamal, E. Solano, M. Sanz |
| Abstract | An analog computer makes use of continuously changeable quantities of a system, such as its electrical, mechanical, or hydraulic properties, to solve a given problem. While these devices are usually computationally more powerful than their digital counterparts, they suffer from analog noise which does not allow for error control. We will focus on analog computers based on active electrical networks comprised of resistors, capacitors, and operational amplifiers which are capable of simulating any linear ordinary differential equation. However, the class of nonlinear dynamics they can solve is limited. In this work, by adding memristors to the electrical network, we show that the analog computer can simulate a large variety of linear and nonlinear integro-differential equations by carefully choosing the conductance and the dynamics of the memristor state variable. To the best of our knowledge, this is the first time that circuits based on memristors are proposed for simulations. We study the performance of these analog computers by simulating integro-differential models related to fluid dynamics, nonlinear Volterra equations for population growth, and quantum models describing non-Markovian memory effects, among others. Finally, we perform stability tests by considering imperfect analog components, obtaining robust solutions with up to $13%$ relative error for relevant timescales. |
| Tasks | |
| Published | 2018-03-15 |
| URL | https://arxiv.org/abs/1803.05945v3 |
| https://arxiv.org/pdf/1803.05945v3.pdf | |
| PWC | https://paperswithcode.com/paper/analog-simulator-of-integro-differential |
| Repo | |
| Framework | |
Unsupervised Deep Multi-focus Image Fusion
| Title | Unsupervised Deep Multi-focus Image Fusion |
| Authors | Xiang Yan, Syed Zulqarnain Gilani, Hanlin Qin, Ajmal Mian |
| Abstract | Convolutional neural networks have recently been used for multi-focus image fusion. However, due to the lack of labeled data for supervised training of such networks, existing methods have resorted to adding Gaussian blur in focused images to simulate defocus and generate synthetic training data with ground-truth for supervised learning. Moreover, they classify pixels as focused or defocused and leverage the results to construct the fusion weight maps which then necessitates a series of post-processing steps. In this paper, we present unsupervised end-to-end learning for directly predicting the fully focused output image from multi-focus input image pairs. The proposed approach uses a novel CNN architecture trained to perform fusion without the need for ground truth fused images and exploits the image structural similarity (SSIM) to calculate the loss; a metric that is widely accepted for fused image quality evaluation. Consequently, we are able to utilize {\em real} benchmark datasets, instead of simulated ones, to train our network. The model is a feed-forward, fully convolutional neural network that can process images of variable sizes during test time. Extensive evaluations on benchmark datasets show that our method outperforms existing state-of-the-art in terms of visual quality and objective evaluations. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07272v1 |
| http://arxiv.org/pdf/1806.07272v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-deep-multi-focus-image-fusion |
| Repo | |
| Framework | |
Neural Particle Smoothing for Sampling from Conditional Sequence Models
| Title | Neural Particle Smoothing for Sampling from Conditional Sequence Models |
| Authors | Chu-Cheng Lin, Jason Eisner |
| Abstract | We introduce neural particle smoothing, a sequential Monte Carlo method for sampling annotations of an input string from a given probability model. In contrast to conventional particle filtering algorithms, we train a proposal distribution that looks ahead to the end of the input string by means of a right-to-left LSTM. We demonstrate that this innovation can improve the quality of the sample. To motivate our formal choices, we explain how our neural model and neural sampler can be viewed as low-dimensional but nonlinear approximations to working with HMMs over very large state spaces. |
| Tasks | |
| Published | 2018-04-28 |
| URL | http://arxiv.org/abs/1804.10747v1 |
| http://arxiv.org/pdf/1804.10747v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-particle-smoothing-for-sampling-from |
| Repo | |
| Framework | |
Zero-shot Deep Reinforcement Learning Driving Policy Transfer for Autonomous Vehicles based on Robust Control
| Title | Zero-shot Deep Reinforcement Learning Driving Policy Transfer for Autonomous Vehicles based on Robust Control |
| Authors | Zhuo Xu, Chen Tang, Masayoshi Tomizuka |
| Abstract | Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down by the modeling gap between the source (training) domain and the target (deployment) domain. Unlike current policy transfer approaches, which generally limit to the usage of uninterpretable neural network representations as the transferred features, we propose to transfer concrete kinematic quantities in autonomous driving. The proposed robust-control-based (RC) generic transfer architecture, which we call RL-RC, incorporates a transferable hierarchical RL trajectory planner and a robust tracking controller based on disturbance observer (DOB). The deep RL policies trained with known nominal dynamics model are transfered directly to the target domain, DOB-based robust tracking control is applied to tackle the modeling gap including the vehicle dynamics errors and the external disturbances such as side forces. We provide simulations validating the capability of the proposed method to achieve zero-shot transfer across multiple driving scenarios such as lane keeping, lane changing and obstacle avoidance. |
| Tasks | Autonomous Driving, Autonomous Vehicles |
| Published | 2018-12-07 |
| URL | http://arxiv.org/abs/1812.03216v1 |
| http://arxiv.org/pdf/1812.03216v1.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-deep-reinforcement-learning-driving |
| Repo | |
| Framework | |
Time-Sequence Channel Inference for Beam Alignment in Vehicular Networks
| Title | Time-Sequence Channel Inference for Beam Alignment in Vehicular Networks |
| Authors | Sheng Chen, Zhiyuan Jiang, Sheng Zhou, Zhisheng Niu |
| Abstract | In this paper, we propose a learning-based low-overhead beam alignment method for vehicle-to-infrastructure communication in vehicular networks. The main idea is to remotely infer the optimal beam directions at a target base station in future time slots, based on the CSI of a source base station in previous time slots. The proposed scheme can reduce channel acquisition and beam training overhead by replacing pilot-aided beam training with online inference from a sequence-to-sequence neural network. Simulation results based on ray-tracing channel data show that our proposed scheme achieves a $8.86%$ improvement over location-based beamforming schemes with a positioning error of $1$m, and is within a $4.93%$ performance loss compared with the genie-aided optimal beamformer. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01220v1 |
| http://arxiv.org/pdf/1812.01220v1.pdf | |
| PWC | https://paperswithcode.com/paper/time-sequence-channel-inference-for-beam |
| Repo | |
| Framework | |
ReenactGAN: Learning to Reenact Faces via Boundary Transfer
| Title | ReenactGAN: Learning to Reenact Faces via Boundary Transfer |
| Authors | Wayne Wu, Yunxuan Zhang, Cheng Li, Chen Qian, Chen Change Loy |
| Abstract | We present a novel learning-based framework for face reenactment. The proposed method, known as ReenactGAN, is capable of transferring facial movements and expressions from monocular video input of an arbitrary person to a target person. Instead of performing a direct transfer in the pixel space, which could result in structural artifacts, we first map the source face onto a boundary latent space. A transformer is subsequently used to adapt the boundary of source face to the boundary of target face. Finally, a target-specific decoder is used to generate the reenacted target face. Thanks to the effective and reliable boundary-based transfer, our method can perform photo-realistic face reenactment. In addition, ReenactGAN is appealing in that the whole reenactment process is purely feed-forward, and thus the reenactment process can run in real-time (30 FPS on one GTX 1080 GPU). Dataset and model will be publicly available at https://wywu.github.io/projects/ReenactGAN/ReenactGAN.html |
| Tasks | Face Reenactment |
| Published | 2018-07-29 |
| URL | http://arxiv.org/abs/1807.11079v1 |
| http://arxiv.org/pdf/1807.11079v1.pdf | |
| PWC | https://paperswithcode.com/paper/reenactgan-learning-to-reenact-faces-via |
| Repo | |
| Framework | |
Learning Models with Uniform Performance via Distributionally Robust Optimization
| Title | Learning Models with Uniform Performance via Distributionally Robust Optimization |
| Authors | John Duchi, Hongseok Namkoong |
| Abstract | A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and analyze a distributionally robust stochastic optimization (DRO) framework that learns a model providing good performance against perturbations to the data-generating distribution. We give a convex formulation for the problem, providing several convergence guarantees. We prove finite-sample minimax upper and lower bounds, showing that distributional robustness sometimes comes at a cost in convergence rates. We give limit theorems for the learned parameters, where we fully specify the limiting distribution so that confidence intervals can be computed. On real tasks including generalizing to unknown subpopulations, fine-grained recognition, and providing good tail performance, the distributionally robust approach often exhibits improved performance. |
| Tasks | Stochastic Optimization |
| Published | 2018-10-20 |
| URL | https://arxiv.org/abs/1810.08750v4 |
| https://arxiv.org/pdf/1810.08750v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-models-with-uniform-performance-via |
| Repo | |
| Framework | |
Efficiency and robustness in Monte Carlo sampling of 3-D geophysical inversions with Obsidian v0.1.2: Setting up for success
| Title | Efficiency and robustness in Monte Carlo sampling of 3-D geophysical inversions with Obsidian v0.1.2: Setting up for success |
| Authors | Richard Scalzo, David Kohn, Hugo Olierook, Gregory Houseman, Rohitash Chandra, Mark Girolami, Sally Cripps |
| Abstract | The rigorous quantification of uncertainty in geophysical inversions is a challenging problem. Inversions are often ill-posed and the likelihood surface may be multi-modal; properties of any single mode become inadequate uncertainty measures, and sampling methods become inefficient for irregular posteriors or high-dimensional parameter spaces. We explore the influences of different choices made by the practitioner on the efficiency and accuracy of Bayesian geophysical inversion methods that rely on Markov chain Monte Carlo sampling to assess uncertainty, using a multi-sensor inversion of the three-dimensional structure and composition of a region in the Cooper Basin of South Australia as a case study. The inversion is performed using an updated version of the Obsidian distributed inversion software. We find that the posterior for this inversion has complex local covariance structure, hindering the efficiency of adaptive sampling methods that adjust the proposal based on the chain history. Within the context of a parallel-tempered Markov chain Monte Carlo scheme for exploring high-dimensional multi-modal posteriors, a preconditioned Crank-Nicholson proposal outperforms more conventional forms of random walk. Aspects of the problem setup, such as priors on petrophysics or on 3-D geological structure, affect the shape and separation of posterior modes, influencing sampling performance as well as the inversion results. Use of uninformative priors on sensor noise can improve inversion results by enabling optimal weighting among multiple sensors even if noise levels are uncertain. Efficiency could be further increased by using posterior gradient information within proposals, which Obsidian does not currently support, but which could be emulated using posterior surrogates. |
| Tasks | |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00318v1 |
| http://arxiv.org/pdf/1812.00318v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficiency-and-robustness-in-monte-carlo |
| Repo | |
| Framework | |
On the Geometry of Adversarial Examples
| Title | On the Geometry of Adversarial Examples |
| Authors | Marc Khoury, Dylan Hadfield-Menell |
| Abstract | Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework, drawing on tools from the manifold reconstruction literature, to analyze the high-dimensional geometry of adversarial examples. In particular, we highlight the importance of codimension: for low-dimensional data manifolds embedded in high-dimensional space there are many directions off the manifold in which to construct adversarial examples. Adversarial examples are a natural consequence of learning a decision boundary that classifies the low-dimensional data manifold well, but classifies points near the manifold incorrectly. Using our geometric framework we prove (1) a tradeoff between robustness under different norms, (2) that adversarial training in balls around the data is sample inefficient, and (3) sufficient sampling conditions under which nearest neighbor classifiers and ball-based adversarial training are robust. |
| Tasks | |
| Published | 2018-11-01 |
| URL | http://arxiv.org/abs/1811.00525v2 |
| http://arxiv.org/pdf/1811.00525v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-geometry-of-adversarial-examples |
| Repo | |
| Framework | |
Personalized Exposure Control Using Adaptive Metering and Reinforcement Learning
| Title | Personalized Exposure Control Using Adaptive Metering and Reinforcement Learning |
| Authors | Huan Yang, Baoyuan Wang, Noranart Vesdapunt, Minyi Guo, Sing Bing Kang |
| Abstract | We propose a reinforcement learning approach for real-time exposure control of a mobile camera that is personalizable. Our approach is based on Markov Decision Process (MDP). In the camera viewfinder or live preview mode, given the current frame, our system predicts the change in exposure so as to optimize the trade-off among image quality, fast convergence, and minimal temporal oscillation. We model the exposure prediction function as a fully convolutional neural network that can be trained through Gaussian policy gradient in an end-to-end fashion. As a result, our system can associate scene semantics with exposure values; it can also be extended to personalize the exposure adjustments for a user and device. We improve the learning performance by incorporating an adaptive metering module that links semantics with exposure. This adaptive metering module generalizes the conventional spot or matrix metering techniques. We validate our system using the MIT FiveK and our own datasets captured using iPhone 7 and Google Pixel. Experimental results show that our system exhibits stable real-time behavior while improving visual quality compared to what is achieved through native camera control. |
| Tasks | |
| Published | 2018-03-06 |
| URL | http://arxiv.org/abs/1803.02269v3 |
| http://arxiv.org/pdf/1803.02269v3.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-exposure-control-using-adaptive |
| Repo | |
| Framework | |
Meta-Learning a Dynamical Language Model
| Title | Meta-Learning a Dynamical Language Model |
| Authors | Thomas Wolf, Julien Chaumond, Clement Delangue |
| Abstract | We consider the task of word-level language modeling and study the possibility of combining hidden-states-based short-term representations with medium-term representations encoded in dynamical weights of a language model. Our work extends recent experiments on language models with dynamically evolving weights by casting the language modeling problem into an online learning-to-learn framework in which a meta-learner is trained by gradient-descent to continuously update a language model weights. |
| Tasks | Language Modelling, Meta-Learning |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10631v1 |
| http://arxiv.org/pdf/1803.10631v1.pdf | |
| PWC | https://paperswithcode.com/paper/meta-learning-a-dynamical-language-model |
| Repo | |
| Framework | |
