Paper Group ANR 629
Fast Non-Parametric Learning to Accelerate Mixed-Integer Programming for Online Hybrid Model Predictive Control. ERASER: A Benchmark to Evaluate Rationalized NLP Models. Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines. Reliable and Explainable Machine Learning Methods for Accelerated Material Discovery. Efficient Sem …
Fast Non-Parametric Learning to Accelerate Mixed-Integer Programming for Online Hybrid Model Predictive Control
| Title | Fast Non-Parametric Learning to Accelerate Mixed-Integer Programming for Online Hybrid Model Predictive Control |
| Authors | Jia-Jie Zhu, Georg Martius |
| Abstract | Today’s fast linear algebra and numerical optimization tools have pushed the frontier of model predictive control (MPC) forward, to the efficient control of highly nonlinear and hybrid systems. The field of hybrid MPC has demonstrated that exact optimal control law can be computed, e.g., by mixed-integer programming (MIP) under piecewise-affine (PWA) system models. Despite the elegant theory, online solving hybrid MPC is still out of reach for many applications. We aim to speed up MIP by combining geometric insights from hybrid MPC, a simple-yet-effective learning algorithm, and MIP warm start techniques. Following a line of work in approximate explicit MPC, the proposed learning-control algorithm, LNMS, gains computational advantage over MIP at little cost and is straightforward for practitioners to implement. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09214v1 |
| https://arxiv.org/pdf/1911.09214v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-non-parametric-learning-to-accelerate |
| Repo | |
| Framework | |
ERASER: A Benchmark to Evaluate Rationalized NLP Models
| Title | ERASER: A Benchmark to Evaluate Rationalized NLP Models |
| Authors | Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric Lehman, Caiming Xiong, Richard Socher, Byron C. Wallace |
| Abstract | State-of-the-art models in NLP are now predominantly based on deep neural networks that are generally opaque in terms of how they come to specific predictions. This limitation has led to increased interest in designing more interpretable deep models for NLP that can reveal the `reasoning’ underlying model outputs. But work in this direction has been conducted on different datasets and tasks with correspondingly unique aims and metrics; this makes it difficult to track progress. We propose the Evaluating Rationales And Simple English Reasoning (ERASER) benchmark to advance research on interpretable models in NLP. This benchmark comprises multiple datasets and tasks for which human annotations of “rationales” (supporting evidence) have been collected. We propose several metrics that aim to capture how well the rationales provided by models align with human rationales, and also how faithful these rationales are (i.e., the degree to which provided rationales influenced the corresponding predictions). Our hope is that releasing this benchmark facilitates progress on designing more interpretable NLP systems. The benchmark, code, and documentation are available at: www.eraserbenchmark.com . | |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03429v1 |
| https://arxiv.org/pdf/1911.03429v1.pdf | |
| PWC | https://paperswithcode.com/paper/eraser-a-benchmark-to-evaluate-rationalized |
| Repo | |
| Framework | |
Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines
| Title | Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines |
| Authors | Haoshen Fan, Jie Wang, Bojin Zhuang, Shaojun Wang, Jing Xiao |
| Abstract | As one of the quintessence of Chinese traditional culture, couplet compromises two syntactically symmetric clauses equal in length, namely, an antecedent and subsequent clause. Moreover, corresponding characters and phrases at the same position of the two clauses are paired with each other under certain constraints of semantic and/or syntactic relatedness. Automatic couplet generation is recognized as a challenging problem even in the Artificial Intelligence field. In this paper, we comprehensively study on automatic generation of acrostic couplet with the first characters defined by users. The complete couplet generation is mainly divided into three stages, that is, antecedent clause generation pipeline, subsequent clause generation pipeline and clause re-ranker. To realize semantic and/or syntactic relatedness between two clauses, attention-based Sequence-to-Sequence (S2S) neural network is employed. Moreover, to provide diverse couplet candidates for re-ranking, a cluster-based beam search approach is incorporated into the S2S network. Both BLEU metrics and human judgments have demonstrated the effectiveness of our proposed method. Eventually, a mini-program based on this generation system is developed and deployed on Wechat for real users. |
| Tasks | |
| Published | 2019-06-15 |
| URL | https://arxiv.org/abs/1906.09321v1 |
| https://arxiv.org/pdf/1906.09321v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-acrostic-couplet-generation-with |
| Repo | |
| Framework | |
Reliable and Explainable Machine Learning Methods for Accelerated Material Discovery
| Title | Reliable and Explainable Machine Learning Methods for Accelerated Material Discovery |
| Authors | Bhavya Kailkhura, Brian Gallagher, Sookyung Kim, Anna Hiszpanski, T. Yong-Jin Han |
| Abstract | Material scientists are increasingly adopting the use of machine learning (ML) for making potentially important decisions, such as, discovery, development, optimization, synthesis and characterization of materials. However, despite ML’s impressive performance in commercial applications, several unique challenges exist when applying ML in materials science applications. In such a context, the contributions of this work are twofold. First, we identify common pitfalls of existing ML techniques when learning from underrepresented/imbalanced material data. Specifically, we show that with imbalanced data, standard methods for assessing quality of ML models break down and lead to misleading conclusions. Furthermore, we found that the model’s own confidence score cannot be trusted and model introspection methods (using simpler models) do not help as they result in loss of predictive performance (reliability-explainability trade-off). Second, to overcome these challenges, we propose a general-purpose explainable and reliable machine-learning framework. Specifically, we propose a novel pipeline that employs an ensemble of simpler models to reliably predict material properties. We also propose a transfer learning technique and show that the performance loss due to models’ simplicity can be overcome by exploiting correlations among different material properties. A new evaluation metric and a trust score to better quantify the confidence in the predictions are also proposed. To improve the interpretability, we add a rationale generator component to our framework which provides both model-level and decision-level explanations. Finally, we demonstrate the versatility of our technique on two applications: 1) predicting properties of crystalline compounds, and 2) identifying novel potentially stable solar cell materials. |
| Tasks | Transfer Learning |
| Published | 2019-01-05 |
| URL | http://arxiv.org/abs/1901.02717v2 |
| http://arxiv.org/pdf/1901.02717v2.pdf | |
| PWC | https://paperswithcode.com/paper/reliable-and-explainable-machine-learning |
| Repo | |
| Framework | |
Efficient Semantic Scene Completion Network with Spatial Group Convolution
| Title | Efficient Semantic Scene Completion Network with Spatial Group Convolution |
| Authors | Jiahui Zhang, Hao Zhao, Anbang Yao, Yurong Chen, Li Zhang, Hongen Liao |
| Abstract | We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks. SGC is orthogonal to group convolution, which works on spatial dimensions rather than feature channel dimension. It divides input voxels into different groups, then conducts 3D sparse convolution on these separated groups. As only valid voxels are considered when performing convolution, computation can be significantly reduced with a slight loss of accuracy. The proposed operations are validated on semantic scene completion task, which aims to predict a complete 3D volume with semantic labels from a single depth image. With SGC, we further present an efficient 3D sparse convolutional network, which harnesses a multiscale architecture and a coarse-to-fine prediction strategy. Evaluations are conducted on the SUNCG dataset, achieving state-of-the-art performance and fast speed. Code is available at https://github.com/zjhthu/SGC-Release.git |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05091v1 |
| https://arxiv.org/pdf/1907.05091v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-semantic-scene-completion-network-1 |
| Repo | |
| Framework | |
Active inference: demystified and compared
| Title | Active inference: demystified and compared |
| Authors | Noor Sajid, Philip J. Ball, Karl J. Friston |
| Abstract | Active inference is a first principle account of how autonomous agents operate in dynamic, non-stationary environments. This problem is also considered in reinforcement learning, but limited work exists on comparing the two approaches on the same discrete-state environments. In this paper, we provide: 1) an accessible overview of the discrete-state formulation of active inference, highlighting natural behaviors in active inference that are generally engineered in reinforcement learning; 2) to our knowledge, the first explicit discrete-state comparison between active inference and reinforcement learning on an OpenAI gym baseline. We begin by providing a condensed overview of the active inference literature, in particular viewing the various natural behaviors of active inference agents through the lens of reinforcement learning. We show that by operating in a pure belief-based setting, active inference agents can carry out epistemic exploration - and account for uncertainty about their environment - in a Bayes optimal fashion. We make these properties explicit by showing that the active inference agent’s ability to carry out online planning, in a pure-belief setting, enables it to act optimally, given the non-stationary dynamics of an environment when compared to both Q-learning and Bayesian model-based reinforcement learning agents. We conclude by noting that this formalism can be applied to more complex settings; e.g., robotic arm movement, Atari games, etc., if appropriate generative models can be formulated. In short, we aim to demystify the behavior of active inference agents by presenting an accessible discrete state-space and time formulation, and demonstrate these behaviors in a OpenAI gym environment, alongside reinforcement learning agents. |
| Tasks | Atari Games, Q-Learning |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.10863v2 |
| https://arxiv.org/pdf/1909.10863v2.pdf | |
| PWC | https://paperswithcode.com/paper/demystifying-active-inference |
| Repo | |
| Framework | |
Biased Estimates of Advantages over Path Ensembles
| Title | Biased Estimates of Advantages over Path Ensembles |
| Authors | Lanxin Lei, Zhizhong Li, Dahua Lin |
| Abstract | The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths. In this work, we propose a family of estimates based on the order statistics over the path ensemble, which allows one to flexibly drive the learning process, towards or against risks. On top of this formulation, we systematically study the impacts of different methods for estimating advantages. Our findings reveal that biased estimates, when chosen appropriately, can result in significant benefits. In particular, for the environments with sparse rewards, optimistic estimates would lead to more efficient exploration of the policy space; while for those where individual actions can have critical impacts, conservative estimates are preferable. On various benchmarks, including MuJoCo continuous control, Terrain locomotion, Atari games, and sparse-reward environments, the proposed biased estimation schemes consistently demonstrate improvement over mainstream methods, not only accelerating the learning process but also obtaining substantial performance gains. |
| Tasks | Atari Games, Continuous Control, Efficient Exploration |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1909.06851v1 |
| https://arxiv.org/pdf/1909.06851v1.pdf | |
| PWC | https://paperswithcode.com/paper/biased-estimates-of-advantages-over-path |
| Repo | |
| Framework | |
Reinforcement Learning and Video Games
| Title | Reinforcement Learning and Video Games |
| Authors | Yue Zheng |
| Abstract | Reinforcement learning has exceeded human-level performance in game playing AI with deep learning methods according to the experiments from DeepMind on Go and Atari games. Deep learning solves high dimension input problems which stop the development of reinforcement for many years. This study uses both two techniques to create several agents with different algorithms that successfully learn to play T-rex Runner. Deep Q network algorithm and three types of improvements are implemented to train the agent. The results from some of them are far from satisfactory but others are better than human experts. Batch normalization is a method to solve internal covariate shift problems in deep neural network. The positive influence of this on reinforcement learning has also been proved in this study. |
| Tasks | Atari Games |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04751v1 |
| https://arxiv.org/pdf/1909.04751v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-and-video-games |
| Repo | |
| Framework | |
Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field
| Title | Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field |
| Authors | Marin Toromanoff, Emilie Wirbel, Fabien Moutarde |
| Abstract | Consistent and reproducible evaluation of Deep Reinforcement Learning (DRL) is not straightforward. In the Arcade Learning Environment (ALE), small changes in environment parameters such as stochasticity or the maximum allowed play time can lead to very different performance. In this work, we discuss the difficulties of comparing different agents trained on ALE. In order to take a step further towards reproducible and comparable DRL, we introduce SABER, a Standardized Atari BEnchmark for general Reinforcement learning algorithms. Our methodology extends previous recommendations and contains a complete set of environment parameters as well as train and test procedures. We then use SABER to evaluate the current state of the art, Rainbow. Furthermore, we introduce a human world records baseline, and argue that previous claims of expert or superhuman performance of DRL might not be accurate. Finally, we propose Rainbow-IQN by extending Rainbow with Implicit Quantile Networks (IQN) leading to new state-of-the-art performance. Source code is available for reproducibility. |
| Tasks | Atari Games |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.04683v5 |
| https://arxiv.org/pdf/1908.04683v5.pdf | |
| PWC | https://paperswithcode.com/paper/is-deep-reinforcement-learning-really |
| Repo | |
| Framework | |
Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks
| Title | Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks |
| Authors | Tianyu Pang, Kun Xu, Jun Zhu |
| Abstract | It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. Applying mixup in training provides an effective mechanism to improve generalization performance and model robustness against adversarial perturbations, which introduces the globally linear behavior in-between training examples. However, in previous work, the mixup-trained models only passively defend adversarial attacks in inference by directly classifying the inputs, where the induced global linearity is not well exploited. Namely, since the locality of the adversarial perturbations, it would be more efficient to actively break the locality via the globality of the model predictions. Inspired by simple geometric intuition, we develop an inference principle, named mixup inference (MI), for mixup-trained models. MI mixups the input with other random clean samples, which can shrink and transfer the equivalent perturbation if the input is adversarial. Our experiments on CIFAR-10 and CIFAR-100 demonstrate that MI can further improve the adversarial robustness for the models trained by mixup and its variants. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11515v2 |
| https://arxiv.org/pdf/1909.11515v2.pdf | |
| PWC | https://paperswithcode.com/paper/mixup-inference-better-exploiting-mixup-to |
| Repo | |
| Framework | |
Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction
| Title | Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction |
| Authors | Giulia Luise, Dimitris Stamos, Massimiliano Pontil, Carlo Ciliberto |
| Abstract | We study the interplay between surrogate methods for structured prediction and techniques from multitask learning designed to leverage relationships between surrogate outputs. We propose an efficient algorithm based on trace norm regularization which, differently from previous methods, does not require explicit knowledge of the coding/decoding functions of the surrogate framework. As a result, our algorithm can be applied to the broad class of problems in which the surrogate space is large or even infinite dimensional. We study excess risk bounds for trace norm regularized structured prediction, implying the consistency and learning rates for our estimator. We also identify relevant regimes in which our approach can enjoy better generalization performance than previous methods. Numerical experiments on ranking problems indicate that enforcing low-rank relations among surrogate outputs may indeed provide a significant advantage in practice. |
| Tasks | Structured Prediction |
| Published | 2019-03-02 |
| URL | http://arxiv.org/abs/1903.00667v1 |
| http://arxiv.org/pdf/1903.00667v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-low-rank-relations-between |
| Repo | |
| Framework | |
Retinal OCT disease classification with variational autoencoder regularization
| Title | Retinal OCT disease classification with variational autoencoder regularization |
| Authors | Max-Heinrich Laves, Sontje Ihler, Lüder A. Kahrs, Tobias Ortmaier |
| Abstract | According to the World Health Organization, 285 million people worldwide live with visual impairment. The most commonly used imaging technique for diagnosis in ophthalmology is optical coherence tomography (OCT). However, analysis of retinal OCT requires trained ophthalmologists and time, making a comprehensive early diagnosis unlikely. A recent study established a diagnostic tool based on convolutional neural networks (CNN), which was trained on a large database of retinal OCT images. The performance of the tool in classifying retinal conditions was on par to that of trained medical experts. However, the training of these networks is based on an enormous amount of labeled data, which is expensive and difficult to obtain. Therefore, this paper describes a method based on variational autoencoder regularization that improves classification performance when using a limited amount of labeled data. This work uses a two-path CNN model combining a classification network with an autoencoder (AE) for regularization. The key idea behind this is to prevent overfitting when using a limited training dataset size with small number of patients. Results show superior classification performance compared to a pre-trained and fully fine-tuned baseline ResNet-34. Clustering of the latent space in relation to the disease class is distinct. Neural networks for disease classification on OCTs can benefit from regularization using variational autoencoders when trained with limited amount of patient data. Especially in the medical imaging domain, data annotated by experts is expensive to obtain. |
| Tasks | |
| Published | 2019-03-23 |
| URL | http://arxiv.org/abs/1904.00790v1 |
| http://arxiv.org/pdf/1904.00790v1.pdf | |
| PWC | https://paperswithcode.com/paper/retinal-oct-disease-classification-with |
| Repo | |
| Framework | |
Visual Measurement Integrity Monitoring for UAV Localization
| Title | Visual Measurement Integrity Monitoring for UAV Localization |
| Authors | Chengyao Li, Steven L. Waslander |
| Abstract | Unmanned aerial vehicles (UAVs) have increasingly been adopted for safety, security, and rescue missions, for which they need precise and reliable pose estimates relative to their environment. To ensure mission safety when relying on visual perception, it is essential to have an approach to assess the integrity of the visual localization solution. However, to the best of our knowledge, such an approach does not exist for optimization-based visual localization. Receiver autonomous integrity monitoring (RAIM) has been widely used in global navigation satellite systems (GNSS) applications such as automated aircraft landing. In this paper, we propose a novel approach inspired by RAIM to monitor the integrity of optimization-based visual localization and calculate the protection level of a state estimate, i.e. the largest possible translational error in each direction. We also propose a metric that quantitatively evaluates the performance of the error bounds. Finally, we validate the protection level using the EuRoC dataset and demonstrate that the proposed protection level provides a significantly more reliable bound than the commonly used $3\sigma$ method. |
| Tasks | Visual Localization |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08537v1 |
| https://arxiv.org/pdf/1909.08537v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-measurement-integrity-monitoring-for |
| Repo | |
| Framework | |
Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes using Transfer Learning
| Title | Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes using Transfer Learning |
| Authors | Aqeel Anwar, Arijit Raychowdhury |
| Abstract | Smart and agile drones are fast becoming ubiquitous at the edge of the cloud. The usage of these drones are constrained by their limited power and compute capability. In this paper, we present a Transfer Learning (TL) based approach to reduce on-board computation required to train a deep neural network for autonomous navigation via Deep Reinforcement Learning for a target algorithmic performance. A library of 3D realistic meta-environments is manually designed using Unreal Gaming Engine and the network is trained end-to-end. These trained meta-weights are then used as initializers to the network in a test environment and fine-tuned for the last few fully connected layers. Variation in drone dynamics and environmental characteristics is carried out to show robustness of the approach. Using NVIDIA GPU profiler it was shown that the energy consumption and training latency is reduced by 3.7x and 1.8x respectively without significant degradation in the performance in terms of average distance traveled before crash i.e. Mean Safe Flight (MSF). The approach is also tested on a real environment using DJI Tello drone and similar results were reported. |
| Tasks | Autonomous Navigation, Transfer Learning |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.05547v1 |
| https://arxiv.org/pdf/1910.05547v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-navigation-via-deep-reinforcement |
| Repo | |
| Framework | |
To Learn or Not to Learn: Visual Localization from Essential Matrices
| Title | To Learn or Not to Learn: Visual Localization from Essential Matrices |
| Authors | Qunjie Zhou, Torsten Sattler, Marc Pollefeys, Laura Leal-Taixe |
| Abstract | Visual localization is the problem of estimating a camera within a scene and a key component in computer vision applications such as self-driving cars and Mixed Reality. State-of-the-art approaches for accurate visual localization use scene-specific representations, resulting in the overhead of constructing these models when applying the techniques to new scenes. Recently, deep learning-based approaches based on relative pose estimation have been proposed, carrying the promise of easily adapting to new scenes. However, it has been shown such approaches are currently significantly less accurate than state-of-the-art approaches. In this paper, we are interested in analyzing this behavior. To this end, we propose a novel framework for visual localization from relative poses. Using a classical feature-based approach within this framework, we show state-of-the-art performance. Replacing the classical approach with learned alternatives at various levels, we then identify the reasons for why deep learned approaches do not perform well. Based on our analysis, we make recommendations for future work. |
| Tasks | Pose Estimation, Self-Driving Cars, Visual Localization |
| Published | 2019-08-04 |
| URL | https://arxiv.org/abs/1908.01293v2 |
| https://arxiv.org/pdf/1908.01293v2.pdf | |
| PWC | https://paperswithcode.com/paper/to-learn-or-not-to-learn-visual-localization |
| Repo | |
| Framework | |
