Paper Group ANR 558
Focal Loss in 3D Object Detection. Collaborative targeted inference from continuously indexed nuisance parameter estimators. The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples. Representation, Justification and Explanation in a Value Driven Agent: An Argumentation-Based Approach. An Adaptive Clipping Approach for Pro …
Focal Loss in 3D Object Detection
Title | Focal Loss in 3D Object Detection |
Authors | Peng Yun, Lei Tai, Yuan Wang, Chengju Liu, Ming Liu |
Abstract | 3D object detection is still an open problem in autonomous driving scenes. When recognizing and localizing key objects from sparse 3D inputs, autonomous vehicles suffer from a larger continuous searching space and higher fore-background imbalance compared to image-based object detection. In this paper, we aim to solve this fore-background imbalance in 3D object detection. Inspired by the recent use of focal loss in image-based object detection, we extend this hard-mining improvement of binary cross entropy to point-cloud-based object detection and conduct experiments to show its performance based on two different 3D detectors: 3D-FCN and VoxelNet. The evaluation results show up to 11.2AP gains through the focal loss in a wide range of hyperparameters for 3D object detection. |
Tasks | 3D Object Detection, Autonomous Driving, Autonomous Vehicles, Object Detection |
Published | 2018-09-17 |
URL | http://arxiv.org/abs/1809.06065v3 |
http://arxiv.org/pdf/1809.06065v3.pdf | |
PWC | https://paperswithcode.com/paper/focal-loss-in-3d-object-detection |
Repo | |
Framework | |
Collaborative targeted inference from continuously indexed nuisance parameter estimators
Title | Collaborative targeted inference from continuously indexed nuisance parameter estimators |
Authors | Cheng Ju, Antoine Chambaz, Mark J. van der Laan |
Abstract | We wish to infer the value of a parameter at a law from which we sample independent observations. The parameter is smooth and we can define two variation-independent features of the law, its $Q$- and $G$-components, such that estimating them consistently at a fast enough product of rates allows to build a confidence interval (CI) with a given asymptotic level from a plain targeted minimum loss estimator (TMLE). Say that the above product is not fast enough and the algorithm for the $G$-component is fine-tuned by a real-valued $h$. A plain TMLE with an $h$ chosen by cross-validation would typically not yield a CI. We construct a collaborative TMLE (C-TMLE) and show under mild conditions that, if there exists an oracle $h$ that makes a bulky remainder term asymptotically Gaussian, then the C-TMLE yields a CI. We illustrate our findings with the inference of the average treatment effect. We conduct a simulation study where the $G$-component is estimated by the LASSO and $h$ is the bound on the coefficients’ norms. It sheds light on small sample properties, in the face of low- to high-dimensional baseline covariates, and possibly positivity violation. |
Tasks | |
Published | 2018-03-31 |
URL | http://arxiv.org/abs/1804.00102v2 |
http://arxiv.org/pdf/1804.00102v2.pdf | |
PWC | https://paperswithcode.com/paper/collaborative-targeted-inference-from |
Repo | |
Framework | |
The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples
Title | The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples |
Authors | Ayse Elvan Aydemir, Alptekin Temizel, Tugba Taskaya Temizel |
Abstract | Adversarial examples are known to have a negative effect on the performance of classifiers which have otherwise good performance on undisturbed images. These examples are generated by adding non-random noise to the testing samples in order to make classifier misclassify the given data. Adversarial attacks use these intentionally generated examples and they pose a security risk to the machine learning based systems. To be immune to such attacks, it is desirable to have a pre-processing mechanism which removes these effects causing misclassification while keeping the content of the image. JPEG and JPEG2000 are well-known image compression techniques which suppress the high-frequency content taking the human visual system into account. JPEG has been also shown to be an effective method for reducing adversarial noise. In this paper, we propose applying JPEG2000 compression as an alternative and systematically compare the classification performance of adversarial images compressed using JPEG and JPEG2000 at different target PSNR values and maximum compression levels. Our experiments show that JPEG2000 is more effective in reducing adversarial noise as it allows higher compression rates with less distortion and it does not introduce blocking artifacts. |
Tasks | Image Compression |
Published | 2018-03-28 |
URL | http://arxiv.org/abs/1803.10418v2 |
http://arxiv.org/pdf/1803.10418v2.pdf | |
PWC | https://paperswithcode.com/paper/the-effects-of-jpeg-and-jpeg2000-compression |
Repo | |
Framework | |
Representation, Justification and Explanation in a Value Driven Agent: An Argumentation-Based Approach
Title | Representation, Justification and Explanation in a Value Driven Agent: An Argumentation-Based Approach |
Authors | Beishui Liao, Michael Anderson, Susan Leigh Anderson |
Abstract | Ethical and explainable artificial intelligence is an interdisciplinary research area involving computer science, philosophy, logic, the social sciences, etc. For an ethical autonomous system, the ability to justify and explain its decision making is a crucial aspect of transparency and trustworthiness. This paper takes a Value Driven Agent (VDA) as an example, explicitly representing implicit knowledge of a machine learning-based autonomous agent and using this formalism to justify and explain the decisions of the agent. For this purpose, we introduce a novel formalism to describe the intrinsic knowledge and solutions of a VDA in each situation. Based on this formalism, we formulate an approach to justify and explain the decision-making process of a VDA, in terms of a typical argumentation formalism, Assumption-based Argumentation (ABA). As a result, a VDA in a given situation is mapped onto an argumentation framework in which arguments are defined by the notion of deduction. Justified actions with respect to semantics from argumentation correspond to solutions of the VDA. The acceptance (rejection) of arguments and their premises in the framework provides an explanation for why an action was selected (or not). Furthermore, we go beyond the existing version of VDA, considering not only practical reasoning, but also epistemic reasoning, such that the inconsistency of knowledge of the VDA can be identified, handled and explained. |
Tasks | Decision Making |
Published | 2018-12-13 |
URL | https://arxiv.org/abs/1812.05362v2 |
https://arxiv.org/pdf/1812.05362v2.pdf | |
PWC | https://paperswithcode.com/paper/representation-justification-and-explanation |
Repo | |
Framework | |
An Adaptive Clipping Approach for Proximal Policy Optimization
Title | An Adaptive Clipping Approach for Proximal Policy Optimization |
Authors | Gang Chen, Yiming Peng, Mengjie Zhang |
Abstract | Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by the same learning theory that justifies trust region policy optimization (TRPO), PPO substantially simplifies algorithm design and improves data efficiency by performing multiple epochs of \emph{clipped policy optimization} from sampled data. Although clipping in PPO stands for an important new mechanism for efficient and reliable policy update, it may fail to adaptively improve learning performance in accordance with the importance of each sampled state. To address this issue, a new surrogate learning objective featuring an adaptive clipping mechanism is proposed in this paper, enabling us to develop a new algorithm, known as PPO-$\lambda$. PPO-$\lambda$ optimizes policies repeatedly based on a theoretical target for adaptive policy improvement. Meanwhile, destructively large policy update can be effectively prevented through both clipping and adaptive control of a hyperparameter $\lambda$ in PPO-$\lambda$, ensuring high learning reliability. PPO-$\lambda$ enjoys the same simple and efficient design as PPO. Empirically on several Atari game playing tasks and benchmark control tasks, PPO-$\lambda$ also achieved clearly better performance than PPO. |
Tasks | |
Published | 2018-04-17 |
URL | http://arxiv.org/abs/1804.06461v1 |
http://arxiv.org/pdf/1804.06461v1.pdf | |
PWC | https://paperswithcode.com/paper/an-adaptive-clipping-approach-for-proximal |
Repo | |
Framework | |
Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation
Title | Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation |
Authors | Rodrigo Nogueira, Jannis Bulian, Massimiliano Ciaramita |
Abstract | We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to produce a final answer. Sub-agents are trained on disjoint partitions of the training data, while the meta-agent is trained on the full training set. Our method makes learning faster, because it is highly parallelizable, and has better generalization performance than strong baselines, such as an ensemble of agents trained on the full data. We show that the improved performance is due to the increased diversity of reformulation strategies. |
Tasks | Question Answering |
Published | 2018-09-27 |
URL | http://arxiv.org/abs/1809.10658v2 |
http://arxiv.org/pdf/1809.10658v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-coordinate-multiple-reinforcement |
Repo | |
Framework | |
Large-Scale Model Selection with Misspecification
Title | Large-Scale Model Selection with Misspecification |
Authors | Emre Demirkaya, Yang Feng, Pallavi Basu, Jinchi Lv |
Abstract | Model selection is crucial to high-dimensional learning and inference for contemporary big data applications in pinpointing the best set of covariates among a sequence of candidate interpretable models. Most existing work assumes implicitly that the models are correctly specified or have fixed dimensionality. Yet both features of model misspecification and high dimensionality are prevalent in practice. In this paper, we exploit the framework of model selection principles in misspecified models originated in Lv and Liu (2014) and investigate the asymptotic expansion of Bayesian principle of model selection in the setting of high-dimensional misspecified models. With a natural choice of prior probabilities that encourages interpretability and incorporates Kullback-Leibler divergence, we suggest the high-dimensional generalized Bayesian information criterion with prior probability (HGBIC_p) for large-scale model selection with misspecification. Our new information criterion characterizes the impacts of both model misspecification and high dimensionality on model selection. We further establish the consistency of covariance contrast matrix estimation and the model selection consistency of HGBIC_p in ultra-high dimensions under some mild regularity conditions. The advantages of our new method are supported by numerical studies. |
Tasks | Model Selection |
Published | 2018-03-17 |
URL | http://arxiv.org/abs/1803.07418v1 |
http://arxiv.org/pdf/1803.07418v1.pdf | |
PWC | https://paperswithcode.com/paper/large-scale-model-selection-with |
Repo | |
Framework | |
Logistic Regression Augmented Community Detection for Network Data with Application in Identifying Autism-Related Gene Pathways
Title | Logistic Regression Augmented Community Detection for Network Data with Application in Identifying Autism-Related Gene Pathways |
Authors | Yunpeng Zhao, Qing Pan, Chengan Du |
Abstract | When searching for gene pathways leading to specific disease outcomes, additional information on gene characteristics is often available that may facilitate to differentiate genes related to the disease from irrelevant background when connections involving both types of genes are observed and their relationships to the disease are unknown. We propose method to single out irrelevant background genes with the help of auxiliary information through a logistic regression, and cluster relevant genes into cohesive groups using the adjacency matrix. Expectation-maximization algorithm is modified to maximize a joint pseudo-likelihood assuming latent indicators for relevance to the disease and latent group memberships as well as Poisson or multinomial distributed link numbers within and between groups. A robust version allowing arbitrary linkage patterns within the background is further derived. Asymptotic consistency of label assignments under the stochastic blockmodel is proven. Superior performance and robustness in finite samples are observed in simulation studies. The proposed robust method identifies previously missed gene sets underlying autism related neurological diseases using diverse data sources including de novo mutations, gene expressions and protein-protein interactions. |
Tasks | Community Detection |
Published | 2018-09-07 |
URL | http://arxiv.org/abs/1809.02262v1 |
http://arxiv.org/pdf/1809.02262v1.pdf | |
PWC | https://paperswithcode.com/paper/logistic-regression-augmented-community |
Repo | |
Framework | |
Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity
Title | Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity |
Authors | Glorianna Jagfeld, Sabrina Jenne, Ngoc Thang Vu |
Abstract | We present a comparison of word-based and character-based sequence-to-sequence models for data-to-text natural language generation, which generate natural language descriptions for structured inputs. On the datasets of two recent generation challenges, our models achieve comparable or better automatic evaluation results than the best challenge submissions. Subsequent detailed statistical and human analyses shed light on the differences between the two input representations and the diversity of the generated texts. In a controlled experiment with synthetic training data generated from templates, we demonstrate the ability of neural models to learn novel combinations of the templates and thereby generalize beyond the linguistic structures they were trained on. |
Tasks | Text Generation |
Published | 2018-10-11 |
URL | http://arxiv.org/abs/1810.04864v1 |
http://arxiv.org/pdf/1810.04864v1.pdf | |
PWC | https://paperswithcode.com/paper/sequence-to-sequence-models-for-data-to-text |
Repo | |
Framework | |
Machine Learning with Abstention for Automated Liver Disease Diagnosis
Title | Machine Learning with Abstention for Automated Liver Disease Diagnosis |
Authors | Kanza Hamid, Amina Asif, Wajid Abbasi, Durre Sabih, Fayyaz Minhas |
Abstract | This paper presents a novel approach for detection of liver abnormalities in an automated manner using ultrasound images. For this purpose, we have implemented a machine learning model that can not only generate labels (normal and abnormal) for a given ultrasound image but it can also detect when its prediction is likely to be incorrect. The proposed model abstains from generating the label of a test example if it is not confident about its prediction. Such behavior is commonly practiced by medical doctors who, when given insufficient information or a difficult case, can chose to carry out further clinical or diagnostic tests before generating a diagnosis. However, existing machine learning models are designed in a way to always generate a label for a given example even when the confidence of their prediction is low. We have proposed a novel stochastic gradient based solver for the learning with abstention paradigm and use it to make a practical, state of the art method for liver disease classification. The proposed method has been benchmarked on a data set of approximately 100 patients from MINAR, Multan, Pakistan and our results show that the proposed scheme offers state of the art classification performance. |
Tasks | |
Published | 2018-11-11 |
URL | http://arxiv.org/abs/1811.04463v1 |
http://arxiv.org/pdf/1811.04463v1.pdf | |
PWC | https://paperswithcode.com/paper/machine-learning-with-abstention-for |
Repo | |
Framework | |
Deep Haar Scattering Networks in Pattern Recognition: A promising approach
Title | Deep Haar Scattering Networks in Pattern Recognition: A promising approach |
Authors | Fernando Fernandes Neto, Alemayehu Admasu Solomon, Rodrigo de Losso, Claudio Garcia, Pedro Delano Cavalcanti |
Abstract | The aim of this paper is to discuss the use of Haar scattering networks, which is a very simple architecture that naturally supports a large number of stacked layers, yet with very few parameters, in a relatively broad set of pattern recognition problems, including regression and classification tasks. This architecture, basically, consists of stacking convolutional filters, that can be thought as a generalization of Haar wavelets, followed by non-linear operators which aim to extract symmetries and invariances that are later fed in a classification/regression algorithm. We show that good results can be obtained with the proposed method for both kind of tasks. We have outperformed the best available algorithms in 4 out of 18 important data classification problems, and have obtained a more robust performance than ARIMA and ETS time series methods in regression problems for data with strong periodicities. |
Tasks | Time Series |
Published | 2018-11-29 |
URL | http://arxiv.org/abs/1811.12081v1 |
http://arxiv.org/pdf/1811.12081v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-haar-scattering-networks-in-pattern |
Repo | |
Framework | |
Deep Reinforcement Learning for Programming Language Correction
Title | Deep Reinforcement Learning for Programming Language Correction |
Authors | Rahul Gupta, Aditya Kanade, Shirish Shevade |
Abstract | Novice programmers often struggle with the formal syntax of programming languages. To assist them, we design a novel programming language correction framework amenable to reinforcement learning. The framework allows an agent to mimic human actions for text navigation and editing. We demonstrate that the agent can be trained through self-exploration directly from the raw input, that is, program text itself, without any knowledge of the formal syntax of the programming language. We leverage expert demonstrations for one tenth of the training data to accelerate training. The proposed technique is evaluated on 6975 erroneous C programs with typographic errors, written by students during an introductory programming course. Our technique fixes 14% more programs and 29% more compiler error messages relative to those fixed by a state-of-the-art tool, DeepFix, which uses a fully supervised neural machine translation approach. |
Tasks | Machine Translation |
Published | 2018-01-31 |
URL | http://arxiv.org/abs/1801.10467v1 |
http://arxiv.org/pdf/1801.10467v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-programming |
Repo | |
Framework | |
Context-Aware Mixed Reality: A Framework for Ubiquitous Interaction
Title | Context-Aware Mixed Reality: A Framework for Ubiquitous Interaction |
Authors | Long Chen, Wen Tang, Nigel John, Tao Ruan Wan, Jian Jun Zhang |
Abstract | Mixed Reality (MR) is a powerful interactive technology that yields new types of user experience. We present a semantic based interactive MR framework that exceeds the current geometry level approaches, a step change in generating high-level context-aware interactions. Our key insight is to build semantic understanding in MR that not only can greatly enhance user experience through object-specific behaviours, but also pave the way for solving complex interaction design challenges. The framework generates semantic properties of the real world environment through dense scene reconstruction and deep image understanding. We demonstrate our approach with a material-aware prototype system for generating context-aware physical interactions between the real and the virtual objects. Quantitative and qualitative evaluations are carried out and the results show that the framework delivers accurate and fast semantic information in interactive MR environment, providing effective semantic level interactions. |
Tasks | |
Published | 2018-03-14 |
URL | http://arxiv.org/abs/1803.05541v1 |
http://arxiv.org/pdf/1803.05541v1.pdf | |
PWC | https://paperswithcode.com/paper/context-aware-mixed-reality-a-framework-for |
Repo | |
Framework | |
An Optimal Policy for Patient Laboratory Tests in Intensive Care Units
Title | An Optimal Policy for Patient Laboratory Tests in Intensive Care Units |
Authors | Li-Fang Cheng, Niranjani Prasad, Barbara E Engelhardt |
Abstract | Laboratory testing is an integral tool in the management of patient care in hospitals, particularly in intensive care units (ICUs). There exists an inherent trade-off in the selection and timing of lab tests between considerations of the expected utility in clinical decision-making of a given test at a specific time, and the associated cost or risk it poses to the patient. In this work, we introduce a framework that learns policies for ordering lab tests which optimizes for this trade-off. Our approach uses batch off-policy reinforcement learning with a composite reward function based on clinical imperatives, applied to data that include examples of clinicians ordering labs for patients. To this end, we develop and extend principles of Pareto optimality to improve the selection of actions based on multiple reward function components while respecting typical procedural considerations and prioritization of clinical goals in the ICU. Our experiments show that we can estimate a policy that reduces the frequency of lab tests and optimizes timing to minimize information redundancy. We also find that the estimated policies typically suggest ordering lab tests well ahead of critical onsets–such as mechanical ventilation or dialysis–that depend on the lab results. We evaluate our approach by quantifying how these policies may initiate earlier onset of treatment. |
Tasks | Decision Making |
Published | 2018-08-14 |
URL | http://arxiv.org/abs/1808.04679v1 |
http://arxiv.org/pdf/1808.04679v1.pdf | |
PWC | https://paperswithcode.com/paper/an-optimal-policy-for-patient-laboratory |
Repo | |
Framework | |
Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights
Title | Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights |
Authors | Melanie F. Pradier, Weiwei Pan, Jiayu Yao, Soumya Ghosh, Finale Doshi-velez |
Abstract | As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkable gains in terms of predictive accuracy, characterizing uncertainty over the parameters of these models is challenging because of the high dimensionality and complex correlations of the network parameter space. This paper introduces a novel variational inference framework for Bayesian neural networks that (1) encodes complex distributions in high-dimensional parameter space with representations in a low-dimensional latent space, and (2) performs inference efficiently on the low-dimensional representations. Across a large array of synthetic and real-world datasets, we show that our method improves uncertainty characterization and model generalization when compared with methods that work directly in the parameter space. |
Tasks | |
Published | 2018-11-16 |
URL | https://arxiv.org/abs/1811.07006v3 |
https://arxiv.org/pdf/1811.07006v3.pdf | |
PWC | https://paperswithcode.com/paper/projected-bnns-avoiding-weight-space |
Repo | |
Framework | |