January 29, 2020

3404 words 16 mins read

Paper Group ANR 523

Improving Discrete Latent Representations With Differentiable Approximation Bridges. Interior-Point Methods Strike Back: Solving the Wasserstein Barycenter Problem. MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data. Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach. Inverse R …

Improving Discrete Latent Representations With Differentiable Approximation Bridges


Title	Improving Discrete Latent Representations With Differentiable Approximation Bridges
Authors	Jason Ramapuram, Russ Webb
Abstract	Modern neural network training relies on piece-wise (sub-)differentiable functions in order to use backpropagation to update model parameters. In this work, we introduce a novel method to allow simple non-differentiable functions at intermediary layers of deep neural networks. We do so by training with a differentiable approximation bridge (DAB) neural network which approximates the non-differentiable forward function and provides gradient updates during backpropagation. We present strong empirical results (performing over 600 experiments) in four different domains: unsupervised (image) representation learning, variational (image) density estimation, image classification, and sequence sorting to demonstrate that our proposed method improves state of the art performance. We demonstrate that training with DAB aided discrete non-differentiable functions improves image reconstruction quality and posterior linear separability by 10% against the Gumbel-Softmax relaxed estimator [37, 26] as well as providing a 9% improvement in the test variational lower bound in comparison to the state of the art RELAX [16] discrete estimator. We also observe an accuracy improvement of 77% in neural sequence sorting and a 25% improvement against the straight-through estimator [5] in an image classification setting. The DAB network is not used for inference and expands the class of functions that are usable in neural networks.
Tasks	Density Estimation, Image Classification, Image Reconstruction, Representation Learning
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03658v3
PDF	https://arxiv.org/pdf/1905.03658v3.pdf
PWC	https://paperswithcode.com/paper/190503658
Repo
Framework

Interior-Point Methods Strike Back: Solving the Wasserstein Barycenter Problem


Title	Interior-Point Methods Strike Back: Solving the Wasserstein Barycenter Problem
Authors	Dongdong Ge, Haoyue Wang, Zikai Xiong, Yinyu Ye
Abstract	Computing the Wasserstein barycenter of a set of probability measures under the optimal transport metric can quickly become prohibitive for traditional second-order algorithms, such as interior-point methods, as the support size of the measures increases. In this paper, we overcome the difficulty by developing a new adapted interior-point method that fully exploits the problem’s special matrix structure to reduce the iteration complexity and speed up the Newton procedure. Different from regularization approaches, our method achieves a well-balanced tradeoff between accuracy and speed. A numerical comparison on various distributions with existing algorithms exhibits the computational advantages of our approach. Moreover, we demonstrate the practicality of our algorithm on image benchmark problems including MNIST and Fashion-MNIST.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12895v2
PDF	https://arxiv.org/pdf/1905.12895v2.pdf
PWC	https://paperswithcode.com/paper/interior-point-methods-strike-back-solving
Repo
Framework

MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data


Title	MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data
Authors	Lei Xu, Shubhra Kanti Karmaker Santu, Kalyan Veeramachaneni
Abstract	Most automation in machine learning focuses on model selection and hyper parameter tuning, and many overlook the challenge of automatically defining predictive tasks. We still heavily rely on human experts to define prediction tasks, and generate labels by aggregating raw data. In this paper, we tackle the challenge of defining useful prediction problems on event-driven time-series data. We introduce MLFriend to address this challenge. MLFriend first generates all possible prediction tasks under a predefined space, then interacts with a data scientist to learn the context of the data and recommend good prediction tasks from all the tasks in the space. We evaluate our system on three different datasets and generate a total of 2885 prediction tasks and solve them. Out of these 722 were deemed useful by expert data scientists. We also show that an automatic prediction task discovery system is able to identify top 10 tasks that a user may like within a batch of 100 tasks.
Tasks	Model Selection, Time Series
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12348v1
PDF	https://arxiv.org/pdf/1906.12348v1.pdf
PWC	https://paperswithcode.com/paper/mlfriend-interactive-prediction-task
Repo
Framework

Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach


Title	Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach
Authors	Rodrigo Pérez-Dattari, Carlos Celemin, Javier Ruiz-del-Solar, Jens Kober
Abstract	Deep Reinforcement Learning (DRL) has become a powerful methodology to solve complex decision-making problems. However, DRL has several limitations when used in real-world problems (e.g., robotics applications). For instance, long training times are required and cannot be accelerated in contrast to simulated environments, and reward functions may be hard to specify/model and/or to compute. Moreover, the transfer of policies learned in a simulator to the real-world has limitations (reality gap). On the other hand, machine learning methods that rely on the transfer of human knowledge to an agent have shown to be time efficient for obtaining well performing policies and do not require a reward function. In this context, we analyze the use of human corrective feedback during task execution to learn policies with high-dimensional state spaces, by using the D-COACH framework, and we propose new variants of this framework. D-COACH is a Deep Learning based extension of COACH (COrrective Advice Communicated by Humans), where humans are able to shape policies through corrective advice. The enhanced version of D-COACH, which is proposed in this paper, largely reduces the time and effort of a human for training a policy. Experimental results validate the efficiency of the D-COACH framework in three different problems (simulated and with real robots), and show that its enhanced version reduces the human training effort considerably, and makes it feasible to learn policies within periods of time in which a DRL agent do not reach any improvement.
Tasks	Continuous Control, Decision Making
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05256v1
PDF	https://arxiv.org/pdf/1908.05256v1.pdf
PWC	https://paperswithcode.com/paper/continuous-control-for-high-dimensional-state
Repo
Framework

Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics


Title	Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics
Authors	Saurabh Daptardar, Paul Schrater, Xaq Pitkow
Abstract	Continuous control and planning remains a major challenge in robotics and machine learning. Neuroscience offers the possibility of learning from animal brains that implement highly successful controllers, but it is unclear how to relate an animal’s behavior to control principles. Animals may not always act optimally from the perspective of an external observer, but may still act rationally: we hypothesize that animals choose actions with highest expected future subjective value according to their own internal model of the world. Their actions thus result from solving a different optimal control problem from those on which they are evaluated in neuroscience experiments. With this assumption, we propose a novel framework of model-based inverse rational control that learns the agent’s internal model that best explains their actions in a task described as a partially observable Markov decision process (POMDP). In this approach we first learn optimal policies generalized over the entire model space of dynamics and subjective rewards, using an extended Kalman filter to represent the belief space, a neural network in the actor-critic framework to optimize the policy, and a simplified basis for the parameter space. We then compute the model that maximizes the likelihood of the experimentally observable data comprising the agent’s sensory observations and chosen actions. Our proposed method is able to recover the true model of simulated agents within theoretical error bounds given by limited data. We illustrate this method by applying it to a complex naturalistic task currently used in neuroscience experiments. This approach provides a foundation for interpreting the behavioral and neural dynamics of highly adapted controllers in animal brains.
Tasks	Continuous Control
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04696v1
PDF	https://arxiv.org/pdf/1908.04696v1.pdf
PWC	https://paperswithcode.com/paper/inverse-rational-control-with-partially
Repo
Framework

Safe Testing


Title	Safe Testing
Authors	Peter Grünwald, Rianne de Heide, Wouter Koolen
Abstract	We present a new theory of hypothesis testing. The main concept is the S-value, a notion of evidence which, unlike p-values, allows for effortlessly combining evidence from several tests, even in the common scenario where the decision to perform a new test depends on the previous test outcome: safe tests based on S-values generally preserve Type-I error guarantees under such “optional continuation”. S-values exist for completely general testing problems with composite null and alternatives. Their prime interpretation is in terms of gambling or investing, each S-value corresponding to a particular investment. Surprisingly, optimal “GROW” S-values, which lead to fastest capital growth, are fully characterized by the joint information projection (JIPr) between the set of all Bayes marginal distributions on H0 and H1. Thus, optimal S-values also have an interpretation as Bayes factors, with priors given by the JIPr. We illustrate the theory using two classical testing scenarios: the one-sample t-test and the 2x2 contingency table. In the t-test setting, GROW s-values correspond to adopting the right Haar prior on the variance, like in Jeffreys’ Bayesian t-test. However, unlike Jeffreys’, the “default” safe t-test puts a discrete 2-point prior on the effect size, leading to better behavior in terms of statistical power. Sharing Fisherian, Neymanian and Jeffreys-Bayesian interpretations, S-values and safe tests may provide a methodology acceptable to adherents of all three schools.
Tasks
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07801v1
PDF	https://arxiv.org/pdf/1906.07801v1.pdf
PWC	https://paperswithcode.com/paper/safe-testing
Repo
Framework

Value-laden Disciplinary Shifts in Machine Learning


Title	Value-laden Disciplinary Shifts in Machine Learning
Authors	Ravit Dotan, Smitha Milli
Abstract	As machine learning models are increasingly used for high-stakes decision making, scholars have sought to intervene to ensure that such models do not encode undesirable social and political values. However, little attention thus far has been given to how values influence the machine learning discipline as a whole. How do values influence what the discipline focuses on and the way it develops? If undesirable values are at play at the level of the discipline, then intervening on particular models will not suffice to address the problem. Instead, interventions at the disciplinary-level are required. This paper analyzes the discipline of machine learning through the lens of philosophy of science. We develop a conceptual framework to evaluate the process through which types of machine learning models (e.g. neural networks, support vector machines, graphical models) become predominant. The rise and fall of model-types is often framed as objective progress. However, such disciplinary shifts are more nuanced. First, we argue that the rise of a model-type is self-reinforcing–it influences the way model-types are evaluated. For example, the rise of deep learning was entangled with a greater focus on evaluations in compute-rich and data-rich environments. Second, the way model-types are evaluated encodes loaded social and political values. For example, a greater focus on evaluations in compute-rich and data-rich environments encodes values about centralization of power, privacy, and environmental concerns.
Tasks	Decision Making
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01172v1
PDF	https://arxiv.org/pdf/1912.01172v1.pdf
PWC	https://paperswithcode.com/paper/value-laden-disciplinary-shifts-in-machine
Repo
Framework

Visual Appearance Analysis of Forest Scenes for Monocular SLAM


Title	Visual Appearance Analysis of Forest Scenes for Monocular SLAM
Authors	James Garforth, Barbara Webb
Abstract	Monocular simultaneous localisation and mapping (SLAM) is a cheap and energy efficient way to enable Unmanned Aerial Vehicles (UAVs) to safely navigate managed forests and gather data crucial for monitoring tree health. SLAM research, however, has mostly been conducted in structured human environments, and as such is poorly adapted to unstructured forests. In this paper, we compare the performance of state of the art monocular SLAM systems on forest data and use visual appearance statistics to characterise the differences between forests and other environments, including a photorealistic simulated forest. We find that SLAM systems struggle with all but the most straightforward forest terrain and identify key attributes (lighting changes and in-scene motion) which distinguish forest scenes from “classic” urban datasets. These differences offer an insight into what makes forests harder to map and open the way for targeted improvements. We also demonstrate that even simulations that look impressive to the human eye can fail to properly reflect the difficult attributes of the environment they simulate, and provide suggestions for more closely mimicking natural scenes.
Tasks
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02824v1
PDF	https://arxiv.org/pdf/1907.02824v1.pdf
PWC	https://paperswithcode.com/paper/visual-appearance-analysis-of-forest-scenes
Repo
Framework

The Generalized Complex Kernel Least-Mean-Square Algorithm


Title	The Generalized Complex Kernel Least-Mean-Square Algorithm
Authors	Rafael Boloix-Tortosa, Juan José Murillo-Fuentes, Sotirios A. Tsaftaris
Abstract	We propose a novel adaptive kernel based regression method for complex-valued signals: the generalized complex-valued kernel least-mean-square (gCKLMS). We borrow from the new results on widely linear reproducing kernel Hilbert space (WL-RKHS) for nonlinear regression and complex-valued signals, recently proposed by the authors. This paper shows that in the adaptive version of the kernel regression for complex-valued signals we need to include another kernel term, the so-called pseudo-kernel. This new solution is endowed with better representation capabilities in complex-valued fields, since it can efficiently decouple the learning of the real and the imaginary part. Also, we review previous realizations of the complex KLMS algorithm and its augmented version to prove that they can be rewritten as particular cases of the gCKLMS. Furthermore, important conclusions on the kernels design are drawn that help to greatly improve the convergence of the algorithms. In the experiments, we revisit the nonlinear channel equalization problem to highlight the better convergence of the gCKLMS compared to previous solutions. Also, the flexibility of the proposed generalized approach is tested in a second experiment with non-independent real and imaginary parts. The results illustrate the significant performance improvements of the gCKLMS approach when the complex-valued signals have different properties for the real and imaginary parts.
Tasks
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08692v1
PDF	http://arxiv.org/pdf/1902.08692v1.pdf
PWC	https://paperswithcode.com/paper/the-generalized-complex-kernel-least-mean
Repo
Framework

RED-Attack: Resource Efficient Decision based Attack for Machine Learning


Title	RED-Attack: Resource Efficient Decision based Attack for Machine Learning
Authors	Faiq Khalid, Hassan Ali, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique
Abstract	Due to data dependency and model leakage properties, Deep Neural Networks (DNNs) exhibit several security vulnerabilities. Several security attacks exploited them but most of them require the output probability vector. These attacks can be mitigated by concealing the output probability vector. To address this limitation, decision-based attacks have been proposed which can estimate the model but they require several thousand queries to generate a single untargeted attack image. However, in real-time attacks, resources and attack time are very crucial parameters. Therefore, in resource-constrained systems, e.g., autonomous vehicles where an untargeted attack can have a catastrophic effect, these attacks may not work efficiently. To address this limitation, we propose a resource efficient decision-based methodology which generates the imperceptible attack, i.e., the RED-Attack, for a given black-box model. The proposed methodology follows two main steps to generate the imperceptible attack, i.e., classification boundary estimation and adversarial noise optimization. Firstly, we propose a half-interval search-based algorithm for estimating a sample on the classification boundary using a target image and a randomly selected image from another class. Secondly, we propose an optimization algorithm which first, introduces a small perturbation in some randomly selected pixels of the estimated sample. Then to ensure imperceptibility, it optimizes the distance between the perturbed and target samples. For illustration, we evaluate it for CFAR-10 and German Traffic Sign Recognition (GTSR) using state-of-the-art networks.
Tasks	Autonomous Vehicles, Traffic Sign Recognition
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10258v2
PDF	http://arxiv.org/pdf/1901.10258v2.pdf
PWC	https://paperswithcode.com/paper/red-attack-resource-efficient-decision-based
Repo
Framework

Meta-Neighborhoods


Title	Meta-Neighborhoods
Authors	Siyuan Shan, Junier Oliva
Abstract	Traditional methods for training neural networks use training data just once, as it is discarded after training. Instead, in this work we also leverage the training data during testing to adjust the network and gain more expressivity. Our approach, named Meta-Neighborhoods, is developed under a multi-task learning framework and is a generalization of k-nearest neighbors methods. It can flexibly adapt network parameters w.r.t. different query data using their respective local neighborhood information. Local information is learned and stored in a dictionary of learnable neighbors rather than directly retrieved from the training set for greater flexibility and performance. The network parameters and the dictionary are optimized end-to-end via meta-learning. Extensive experiments demonstrate that Meta-Neighborhoods consistently improved classification and regression performance across various network architectures and datasets. We also observed superior improvements than other state-of-the-art meta-learning methods designed to improve supervised learning.
Tasks	Meta-Learning, Multi-Task Learning
Published	2019-09-18
URL	https://arxiv.org/abs/1909.09140v1
PDF	https://arxiv.org/pdf/1909.09140v1.pdf
PWC	https://paperswithcode.com/paper/meta-neighborhoods
Repo
Framework

ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding


Title	ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding
Authors	Harald Hanselmann, Hermann Ney
Abstract	The task of fine-grained visual classification (FGVC) deals with classification problems that display a small inter-class variance such as distinguishing between different bird species or car models. State-of-the-art approaches typically tackle this problem by integrating an elaborate attention mechanism or (part-) localization method into a standard convolutional neural network (CNN). Also in this work the aim is to enhance the performance of a backbone CNN such as ResNet by including three efficient and lightweight components specifically designed for FGVC. This is achieved by using global k-max pooling, a discriminative embedding layer trained by optimizing class means and an efficient bounding box estimator that only needs class labels for training. The resulting model achieves new best state-of-the-art recognition accuracies on the Stanford cars and FGVC-Aircraft datasets.
Tasks	Fine-Grained Image Classification
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07344v1
PDF	https://arxiv.org/pdf/1911.07344v1.pdf
PWC	https://paperswithcode.com/paper/elope-fine-grained-visual-classification-with
Repo
Framework

On the computational complexity of the probabilistic label tree algorithms


Title	On the computational complexity of the probabilistic label tree algorithms
Authors	Robert Busa-Fekete, Krzysztof Dembczynski, Alexander Golovnev, Kalina Jasinska, Mikhail Kuznetsov, Maxim Sviridenko, Chao Xu
Abstract	Label tree-based algorithms are widely used to tackle multi-class and multi-label problems with a large number of labels. We focus on a particular subclass of these algorithms that use probabilistic classifiers in the tree nodes. Examples of such algorithms are hierarchical softmax (HSM), designed for multi-class classification, and probabilistic label trees (PLTs) that generalize HSM to multi-label problems. If the tree structure is given, learning of PLT can be solved with provable regret guaranties [Wydmuch et.al. 2018]. However, to find a tree structure that results in a PLT with a low training and prediction computational costs as well as low statistical error seems to be a very challenging problem, not well-understood yet. In this paper, we address the problem of finding a tree structure that has low computational cost. First, we show that finding a tree with optimal training cost is NP-complete, nevertheless there are some tractable special cases with either perfect approximation or exact solution that can be obtained in linear time in terms of the number of labels $m$. For the general case, we obtain $O(\log m)$ approximation in linear time too. Moreover, we prove an upper bound on the expected prediction cost expressed in terms of the expected training cost. We also show that under additional assumptions the prediction cost of a PLT is $O(\log m)$.
Tasks
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00294v1
PDF	https://arxiv.org/pdf/1906.00294v1.pdf
PWC	https://paperswithcode.com/paper/190600294
Repo
Framework

Self-Supervised Learning for Stereo Reconstruction on Aerial Images


Title	Self-Supervised Learning for Stereo Reconstruction on Aerial Images
Authors	Patrick Knöbelreiter, Christoph Vogel, Thomas Pock
Abstract	Recent developments established deep learning as an inevitable tool to boost the performance of dense matching and stereo estimation. On the downside, learning these networks requires a substantial amount of training data to be successful. Consequently, the application of these models outside of the laboratory is far from straight forward. In this work we propose a self-supervised training procedure that allows us to adapt our network to the specific (imaging) characteristics of the dataset at hand, without the requirement of external ground truth data. We instead generate interim training data by running our intermediate network on the whole dataset, followed by conservative outlier filtering. Bootstrapped from a pre-trained version of our hybrid CNN-CRF model, we alternate the generation of training data and network training. With this simple concept we are able to lift the completeness and accuracy of the pre-trained version significantly. We also show that our final model compares favorably to other popular stereo estimation algorithms on an aerial dataset.
Tasks
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12446v1
PDF	https://arxiv.org/pdf/1907.12446v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-learning-for-stereo
Repo
Framework

Balanced Ranking with Diversity Constraints


Title	Balanced Ranking with Diversity Constraints
Authors	Ke Yang, Vasilis Gkatzelis, Julia Stoyanovich
Abstract	Many set selection and ranking algorithms have recently been enhanced with diversity constraints that aim to explicitly increase representation of historically disadvantaged populations, or to improve the overall representativeness of the selected set. An unintended consequence of these constraints, however, is reduced in-group fairness: the selected candidates from a given group may not be the best ones, and this unfairness may not be well-balanced across groups. In this paper we study this phenomenon using datasets that comprise multiple sensitive attributes. We then introduce additional constraints, aimed at balancing the \in-group fairness across groups, and formalize the induced optimization problems as integer linear programs. Using these programs, we conduct an experimental evaluation with real datasets, and quantify the feasible trade-offs between balance and overall performance in the presence of diversity constraints.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01747v1
PDF	https://arxiv.org/pdf/1906.01747v1.pdf
PWC	https://paperswithcode.com/paper/balanced-ranking-with-diversity-constraints
Repo
Framework