April 3, 2020

# Paper Group ANR 64

Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance. 3D Gated Recurrent Fusion for Semantic Scene Completion. Learning Queuing Networks by Recurrent Neural Networks. 3D Deep Learning on Medical Images: A Review. SHX: Search History Driven Crossover for Real-Coded Genetic Al …

#### Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance

Title Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance
Abstract We use distributionally-robust optimization for machine learning to mitigate the effect of data poisoning attacks. We provide performance guarantees for the trained model on the original data (not including the poison records) by training the model for the worst-case distribution on a neighbourhood around the empirical distribution (extracted from the training dataset corrupted by a poisoning attack) defined using the Wasserstein distance. We relax the distributionally-robust machine learning problem by finding an upper bound for the worst-case fitness based on the empirical sampled-averaged fitness and the Lipschitz-constant of the fitness function (on the data for given model parameters) as regularizer. For regression models, we prove that this regularizer is equal to the dual norm of the model parameters. We use the Wine Quality dataset, the Boston Housing Market dataset, and the Adult dataset for demonstrating the results of this paper.
Published 2020-01-29
URL https://arxiv.org/abs/2001.10655v1
PDF https://arxiv.org/pdf/2001.10655v1.pdf
PWC https://paperswithcode.com/paper/regularization-helps-with-mitigating
Repo
Framework

#### 3D Gated Recurrent Fusion for Semantic Scene Completion

Title 3D Gated Recurrent Fusion for Semantic Scene Completion
Authors Yu Liu, Jie Li, Qingsen Yan, Xia Yuan, Chunxia Zhao, Ian Reid, Cesar Cadena
Abstract This paper tackles the problem of data fusion in the semantic scene completion (SSC) task, which can simultaneously deal with semantic labeling and scene completion. RGB images contain texture details of the object(s) which are vital for semantic scene understanding. Meanwhile, depth images capture geometric clues of high relevance for shape completion. Using both RGB and depth images can further boost the accuracy of SSC over employing one modality in isolation. We propose a 3D gated recurrent fusion network (GRFNet), which learns to adaptively select and fuse the relevant information from depth and RGB by making use of the gate and memory modules. Based on the single-stage fusion, we further propose a multi-stage fusion strategy, which could model the correlations among different stages within the network. Extensive experiments on two benchmark datasets demonstrate the superior performance and the effectiveness of the proposed GRFNet for data fusion in SSC. Code will be made available.
Published 2020-02-17
URL https://arxiv.org/abs/2002.07269v1
PDF https://arxiv.org/pdf/2002.07269v1.pdf
PWC https://paperswithcode.com/paper/3d-gated-recurrent-fusion-for-semantic-scene
Repo
Framework

#### Learning Queuing Networks by Recurrent Neural Networks

Title Learning Queuing Networks by Recurrent Neural Networks
Authors Giulio Garbi, Emilio Incerto, Mirco Tribastone
Abstract It is well known that building analytical performance models in practice is difficult because it requires a considerable degree of proficiency in the underlying mathematics. In this paper, we propose a machine-learning approach to derive performance models from data. We focus on queuing networks, and crucially exploit a deterministic approximation of their average dynamics in terms of a compact system of ordinary differential equations. We encode these equations into a recurrent neural network whose weights can be directly related to model parameters. This allows for an interpretable structure of the neural network, which can be trained from system measurements to yield a white-box parameterized model that can be used for prediction purposes such as what-if analyses and capacity planning. Using synthetic models as well as a real case study of a load-balancing system, we show the effectiveness of our technique in yielding models with high predictive power.
Published 2020-02-25
URL https://arxiv.org/abs/2002.10788v1
PDF https://arxiv.org/pdf/2002.10788v1.pdf
PWC https://paperswithcode.com/paper/learning-queuing-networks-by-recurrent-neural
Repo
Framework

#### 3D Deep Learning on Medical Images: A Review

Title 3D Deep Learning on Medical Images: A Review
Authors Satya P. Singh, Lipo Wang, Sukrit Gupta, Haveesh Goli, Parasuraman Padmanabhan, Balázs Gulyás
Abstract The rapid advancements in machine learning, graphics processing technologies and availability of medical imaging data has led to a rapid increase in use of machine learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, brief mathematical description of 3D CNN and the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection, and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models, in general) and possible future trends in the field.
Published 2020-04-01
URL https://arxiv.org/abs/2004.00218v1
PDF https://arxiv.org/pdf/2004.00218v1.pdf
PWC https://paperswithcode.com/paper/3d-deep-learning-on-medical-images-a-review
Repo
Framework

#### SHX: Search History Driven Crossover for Real-Coded Genetic Algorithm

Title SHX: Search History Driven Crossover for Real-Coded Genetic Algorithm
Authors Takumi Nakane, Xuequan Lu, Chao Zhang
Abstract In evolutionary algorithms, genetic operators iteratively generate new offspring which constitute a potentially valuable set of search history. To boost the performance of crossover in real-coded genetic algorithm (RCGA), in this paper we propose to exploit the search history cached so far in an online style during the iteration. Specifically, survivor individuals over past few generations are collected and stored in the archive to form the search history. We introduce a simple yet effective crossover model driven by the search history (abbreviated as SHX). In particular, the search history is clustered and each cluster is assigned a score for SHX. In essence, the proposed SHX is a data-driven method which exploits the search history to perform offspring selection after the offspring generation. Since no additional fitness evaluations are needed, SHX is favorable for the tasks with limited budget or expensive fitness evaluations. We experimentally verify the effectiveness of SHX over 4 benchmark functions. Quantitative results show that our SHX can significantly enhance the performance of RCGA, in terms of accuracy.
Published 2020-03-30
URL https://arxiv.org/abs/2003.13508v1
PDF https://arxiv.org/pdf/2003.13508v1.pdf
PWC https://paperswithcode.com/paper/shx-search-history-driven-crossover-for-real
Repo
Framework

#### Solving Non-Convex Non-Differentiable Min-Max Games using Proximal Gradient Method

Title Solving Non-Convex Non-Differentiable Min-Max Games using Proximal Gradient Method
Authors Babak Barazandeh, Meisam Razaviyayn
Abstract Min-max saddle point games appear in a wide range of applications in machine leaning and signal processing. Despite their wide applicability, theoretical studies are mostly limited to the special convex-concave structure. While some recent works generalized these results to special smooth non-convex cases, our understanding of non-smooth scenarios is still limited. In this work, we study special form of non-smooth min-max games when the objective function is (strongly) convex with respect to one of the player’s decision variable. We show that a simple multi-step proximal gradient descent-ascent algorithm converges to $\epsilon$-first-order Nash equilibrium of the min-max game with the number of gradient evaluations being polynomial in $1/\epsilon$. We will also show that our notion of stationarity is stronger than existing ones in the literature. Finally, we evaluate the performance of the proposed algorithm through adversarial attack on a LASSO estimator.
Published 2020-03-18
URL https://arxiv.org/abs/2003.08093v1
PDF https://arxiv.org/pdf/2003.08093v1.pdf
PWC https://paperswithcode.com/paper/solving-non-convex-non-differentiable-min-max
Repo
Framework

#### Non-exchangeable feature allocation models with sublinear growth of the feature sizes

Title Non-exchangeable feature allocation models with sublinear growth of the feature sizes
Authors Giuseppe Di Benedetto, François Caron, Yee Whye Teh
Abstract Feature allocation models are popular models used in different applications such as unsupervised learning or network modeling. In particular, the Indian buffet process is a flexible and simple one-parameter feature allocation model where the number of features grows unboundedly with the number of objects. The Indian buffet process, like most feature allocation models, satisfies a symmetry property of exchangeability: the distribution is invariant under permutation of the objects. While this property is desirable in some cases, it has some strong implications. Importantly, the number of objects sharing a particular feature grows linearly with the number of objects. In this article, we describe a class of non-exchangeable feature allocation models where the number of objects sharing a given feature grows sublinearly, where the rate can be controlled by a tuning parameter. We derive the asymptotic properties of the model, and show that such model provides a better fit and better predictive performances on various datasets.
Published 2020-03-30
URL https://arxiv.org/abs/2003.13491v1
PDF https://arxiv.org/pdf/2003.13491v1.pdf
PWC https://paperswithcode.com/paper/non-exchangeable-feature-allocation-models
Repo
Framework

#### A Multi-Hypothesis Approach to Color Constancy

Title A Multi-Hypothesis Approach to Color Constancy
Authors Daniel Hernandez-Juarez, Sarah Parisot, Benjamin Busam, Ales Leonardis, Gregory Slabaugh, Steven McDonagh
Abstract Contemporary approaches frame the color constancy problem as learning camera specific illuminant mappings. While high accuracy can be achieved on camera specific data, these models depend on camera spectral sensitivity and typically exhibit poor generalisation to new devices. Additionally, regression methods produce point estimates that do not explicitly account for potential ambiguities among plausible illuminant solutions, due to the ill-posed nature of the problem. We propose a Bayesian framework that naturally handles color constancy ambiguity via a multi-hypothesis strategy. Firstly, we select a set of candidate scene illuminants in a data-driven fashion and apply them to a target image to generate of set of corrected images. Secondly, we estimate, for each corrected image, the likelihood of the light source being achromatic using a camera-agnostic CNN. Finally, our method explicitly learns a final illumination estimate from the generated posterior probability distribution. Our likelihood estimator learns to answer a camera-agnostic question and thus enables effective multi-camera training by disentangling illuminant estimation from the supervised learning task. We extensively evaluate our proposed approach and additionally set a benchmark for novel sensor generalisation without re-training. Our method provides state-of-the-art accuracy on multiple public datasets (up to 11% median angular error improvement) while maintaining real-time execution.
Published 2020-02-28
URL https://arxiv.org/abs/2002.12896v2
PDF https://arxiv.org/pdf/2002.12896v2.pdf
PWC https://paperswithcode.com/paper/a-multi-hypothesis-classification-approach-to
Repo
Framework

#### Exchangeable Input Representations for Reinforcement Learning

Title Exchangeable Input Representations for Reinforcement Learning
Authors John Mern, Dorsa Sadigh, Mykel J. Kochenderfer
Abstract Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in an input space that is a factor of $m!$ smaller for inputs of $m$ objects. We also show that our method is able to represent inputs over variable numbers of objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using na"ive approaches.
Published 2020-03-19
URL https://arxiv.org/abs/2003.09022v1
PDF https://arxiv.org/pdf/2003.09022v1.pdf
PWC https://paperswithcode.com/paper/exchangeable-input-representations-for
Repo
Framework

#### Provably Convergent Policy Gradient Methods for Model-Agnostic Meta-Reinforcement Learning

Title Provably Convergent Policy Gradient Methods for Model-Agnostic Meta-Reinforcement Learning
Authors Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar
Abstract We consider Model-Agnostic Meta-Learning (MAML) methods for Reinforcement Learning (RL) problems where the goal is to find a policy (using data from several tasks represented by Markov Decision Processes (MDPs)) that can be updated by one step of stochastic policy gradient for the realized MDP. In particular, using stochastic gradients in MAML update step is crucial for RL problems since computation of exact gradients requires access to a large number of possible trajectories. For this formulation, we propose a variant of the MAML method, named Stochastic Gradient Meta-Reinforcement Learning (SG-MRL), and study its convergence properties. We derive the iteration and sample complexity of SG-MRL to find an $\epsilon$-first-order stationary point, which, to the best of our knowledge, provides the first convergence guarantee for model-agnostic meta-reinforcement learning algorithms. We further show how our results extend to the case where more than one step of stochastic policy gradient method is used in the update during the test time.
Published 2020-02-12
URL https://arxiv.org/abs/2002.05135v1
PDF https://arxiv.org/pdf/2002.05135v1.pdf
Repo
Framework

#### Bayesian Residual Policy Optimization: Scalable Bayesian Reinforcement Learning with Clairvoyant Experts

Title Bayesian Residual Policy Optimization: Scalable Bayesian Reinforcement Learning with Clairvoyant Experts
Authors Gilwoo Lee, Brian Hou, Sanjiban Choudhury, Siddhartha S. Srinivasa
Abstract Informed and robust decision making in the face of uncertainty is critical for robots that perform physical tasks alongside people. We formulate this as Bayesian Reinforcement Learning over latent Markov Decision Processes (MDPs). While Bayes-optimality is theoretically the gold standard, existing algorithms do not scale well to continuous state and action spaces. Our proposal builds on the following insight: in the absence of uncertainty, each latent MDP is easier to solve. We first obtain an ensemble of experts, one for each latent MDP, and fuse their advice to compute a baseline policy. Next, we train a Bayesian residual policy to improve upon the ensemble’s recommendation and learn to reduce uncertainty. Our algorithm, Bayesian Residual Policy Optimization (BRPO), imports the scalability of policy gradient methods and task-specific expert skills. BRPO significantly improves the ensemble of experts and drastically outperforms existing adaptive RL methods.
Published 2020-02-07
URL https://arxiv.org/abs/2002.03042v1
PDF https://arxiv.org/pdf/2002.03042v1.pdf
PWC https://paperswithcode.com/paper/bayesian-residual-policy-optimization-1
Repo
Framework

#### Deep Reinforcement Learning based Blind mmWave MIMO Beam Alignment

Title Deep Reinforcement Learning based Blind mmWave MIMO Beam Alignment
Authors Vishnu Raj, Sheetal Kalyani
Abstract Directional beamforming is a crucial component for realizing robust wireless communication systems using millimeter wave (mmWave) technology. Beam alignment using brute-force search of the space introduces time overhead while location aided blind beam alignment adds additional hardware requirements to the system. In this paper, we introduce a method for blind alignment based on the RF fingerprints of user equipment obtained by the base stations. The proposed system performs blind beamforming on a multiple base station cellular environment with multiple mobile users using deep reinforcement learning. We present a novel neural network architecture that can handle a mix of both continuous and discrete actions and use policy gradient methods to train the model. Our results show that the proposed model is able to give a considerable improvement in data rates over traditional methods.
Published 2020-01-25
URL https://arxiv.org/abs/2001.09251v1
PDF https://arxiv.org/pdf/2001.09251v1.pdf
PWC https://paperswithcode.com/paper/deep-reinforcement-learning-based-blind
Repo
Framework

#### HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference

Title HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference
Authors Tianyu Liu, Xin Zheng, Baobao Chang, Zhifang Sui
Abstract Many recent studies have shown that for models trained on datasets for natural language inference (NLI), it is possible to make correct predictions by merely looking at the hypothesis while completely ignoring the premise. In this work, we manage to derive adversarial examples in terms of the hypothesis-only bias and explore eligible ways to mitigate such bias. Specifically, we extract various phrases from the hypotheses (artificial patterns) in the training sets, and show that they have been strong indicators to the specific labels. We then figure out hard' and easy’ instances from the original test sets whose labels are opposite to or consistent with those indications. We also set up baselines including both pretrained models (BERT, RoBERTa, XLNet) and competitive non-pretrained models (InferSent, DAM, ESIM). Apart from the benchmark and baselines, we also investigate two debiasing approaches which exploit the artificial pattern modeling to mitigate such hypothesis-only bias: down-sampling and adversarial training. We believe those methods can be treated as competitive baselines in NLI debiasing tasks.
Published 2020-03-05
URL https://arxiv.org/abs/2003.02756v1
PDF https://arxiv.org/pdf/2003.02756v1.pdf
PWC https://paperswithcode.com/paper/hyponli-exploring-the-artificial-patterns-of
Repo
Framework

#### Extraction of Templates from Phrases Using Sequence Binary Decision Diagrams

Title Extraction of Templates from Phrases Using Sequence Binary Decision Diagrams
Authors Daiki Hirano, Kumiko Tanaka-Ishii, Andrew Finch
Abstract The extraction of templates such as regard X as Y’’ from a set of related phrases requires the identification of their internal structures. This paper presents an unsupervised approach for extracting templates on-the-fly from only tagged text by using a novel relaxed variant of the Sequence Binary Decision Diagram (SeqBDD). A SeqBDD can compress a set of sequences into a graphical structure equivalent to a minimal DFA, but more compact and better suited to the task of template extraction. The main contribution of this paper is a relaxed form of the SeqBDD construction algorithm that enables it to form general representations from a small amount of data. The process of compression of shared structures in the text during Relaxed SeqBDD construction, naturally induces the templates we wish to extract. Experiments show that the method is capable of high-quality extraction on tasks based on verb+preposition templates from corpora and phrasal templates from short messages from social media. |
Published 2020-01-28
URL https://arxiv.org/abs/2001.10175v1
PDF https://arxiv.org/pdf/2001.10175v1.pdf
PWC https://paperswithcode.com/paper/extraction-of-templates-from-phrases-using
Repo
Framework

#### AirSim Drone Racing Lab

Title AirSim Drone Racing Lab
Authors Ratnesh Madaan, Nicholas Gyde, Sai Vemprala, Matthew Brown, Keiko Nagami, Tim Taubner, Eric Cristofalo, Davide Scaramuzza, Mac Schwager, Ashish Kapoor
Abstract Autonomous drone racing is a challenging research problem at the intersection of computer vision, planning, state estimation, and control. We introduce AirSim Drone Racing Lab, a simulation framework for enabling fast prototyping of algorithms for autonomy and enabling machine learning research in this domain, with the goal of reducing the time, money, and risks associated with field robotics. Our framework enables generation of racing tracks in multiple photo-realistic environments, orchestration of drone races, comes with a suite of gate assets, allows for multiple sensor modalities (monocular, depth, neuromorphic events, optical flow), different camera models, and benchmarking of planning, control, computer vision, and learning-based algorithms. We used our framework to host a simulation based drone racing competition at NeurIPS 2019. The competition binaries are available at our github repository.