Paper Group ANR 319
Discovery and Separation of Features for Invariant Representation Learning. Structure-preserving Method for Reconstructing Unknown Hamiltonian Systems from Trajectory Data. Modeling somatic computation with non-neural bioelectric networks. Learning from Bandit Feedback: An Overview of the State-of-the-art. Implicit Regularization for Optimal Sparse …
Discovery and Separation of Features for Invariant Representation Learning
| Title | Discovery and Separation of Features for Invariant Representation Learning |
| Authors | Ayush Jaiswal, Rob Brekelmans, Daniel Moyer, Greg Ver Steeg, Wael AbdAlmageed, Premkumar Natarajan |
| Abstract | Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization. We propose a framework for training robust neural networks that induces invariance to nuisances through learning to discover and separate predictive and nuisance factors of data. We present an information theoretic formulation of our approach, from which we derive training objectives and its connections with previous methods. Empirical results on a wide array of datasets show that the proposed framework achieves state-of-the-art performance, without requiring nuisance annotations during training. |
| Tasks | Representation Learning |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00646v1 |
| https://arxiv.org/pdf/1912.00646v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovery-and-separation-of-features-for |
| Repo | |
| Framework | |
Structure-preserving Method for Reconstructing Unknown Hamiltonian Systems from Trajectory Data
| Title | Structure-preserving Method for Reconstructing Unknown Hamiltonian Systems from Trajectory Data |
| Authors | Kailiang Wu, Tong Qin, Dongbin Xiu |
| Abstract | We present a numerical approach for approximating unknown Hamiltonian systems using observation data. A distinct feature of the proposed method is that it is structure-preserving, in the sense that it enforces conservation of the reconstructed Hamiltonian. This is achieved by directly approximating the underlying unknown Hamiltonian, rather than the right-hand-side of the governing equations. We present the technical details of the proposed algorithm and its error estimate, along with a practical de-noising procedure to cope with noisy data. A set of numerical examples are then presented to demonstrate the structure-preserving property and effectiveness of the algorithm. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10396v1 |
| https://arxiv.org/pdf/1905.10396v1.pdf | |
| PWC | https://paperswithcode.com/paper/structure-preserving-method-for |
| Repo | |
| Framework | |
Modeling somatic computation with non-neural bioelectric networks
| Title | Modeling somatic computation with non-neural bioelectric networks |
| Authors | Santosh Manicka, Michael Levin |
| Abstract | The field of basal cognition seeks to understand how adaptive, context-specific behavior occurs in non-neural biological systems. Embryogenesis and regeneration require plasticity in many tissue types to achieve structural and functional goals in diverse circumstances. Thus, advances in both evolutionary cell biology and regenerative medicine require an understanding of how non-neural tissues could process information. Neurons evolved from ancient cell types that used bioelectric signaling to perform computation. However, it has not been shown whether or how non-neural bioelectric cell networks can support computation. We generalize connectionist methods to non-neural tissue architectures, showing that a minimal non-neural Bio-Electric Network (BEN) model that utilizes the general principles of bioelectricity (electrodiffusion and gating) can compute. We characterize BEN behaviors ranging from elementary logic gates to pattern detectors, using both fixed and transient inputs to recapitulate various biological scenarios. We characterize the mechanisms of such networks using dynamical-systems and information-theory tools, demonstrating that logic can manifest in bidirectional, continuous, and relatively slow bioelectrical systems, complementing conventional neural-centric architectures. Our results reveal a variety of non-neural decision-making processes as manifestations of general cellular biophysical mechanisms and suggest novel bioengineering approaches to construct functional tissues for regenerative medicine and synthetic biology as well as new machine learning architectures. |
| Tasks | Decision Making |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.04246v1 |
| https://arxiv.org/pdf/1912.04246v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-somatic-computation-with-non-neural |
| Repo | |
| Framework | |
Learning from Bandit Feedback: An Overview of the State-of-the-art
| Title | Learning from Bandit Feedback: An Overview of the State-of-the-art |
| Authors | Olivier Jeunen, Dmytro Mykhaylov, David Rohde, Flavian Vasile, Alexandre Gilotte, Martin Bompaire |
| Abstract | In machine learning we often try to optimise a decision rule that would have worked well over a historical dataset; this is the so called empirical risk minimisation principle. In the context of learning from recommender system logs, applying this principle becomes a problem because we do not have available the reward of decisions we did not do. In order to handle this “bandit-feedback” setting, several Counterfactual Risk Minimisation (CRM) methods have been proposed in recent years, that attempt to estimate the performance of different policies on historical data. Through importance sampling and various variance reduction techniques, these methods allow more robust learning and inference than classical approaches. It is difficult to accurately estimate the performance of policies that frequently perform actions that were infrequently done in the past and a number of different types of estimators have been proposed. In this paper, we review several methods, based on different off-policy estimators, for learning from bandit feedback. We discuss key differences and commonalities among existing approaches, and compare their empirical performance on the RecoGym simulation environment. To the best of our knowledge, this work is the first comparison study for bandit algorithms in a recommender system setting. |
| Tasks | Recommendation Systems |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08471v1 |
| https://arxiv.org/pdf/1909.08471v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-bandit-feedback-an-overview-of |
| Repo | |
| Framework | |
Implicit Regularization for Optimal Sparse Recovery
| Title | Implicit Regularization for Optimal Sparse Recovery |
| Authors | Tomas Vaškevičius, Varun Kanade, Patrick Rebeschini |
| Abstract | We investigate implicit regularization schemes for gradient descent methods applied to unpenalized least squares regression to solve the problem of reconstructing a sparse signal from an underdetermined system of linear measurements under the restricted isometry assumption. For a given parametrization yielding a non-convex optimization problem, we show that prescribed choices of initialization, step size and stopping time yield a statistically and computationally optimal algorithm that achieves the minimax rate with the same cost required to read the data up to poly-logarithmic factors. Beyond minimax optimality, we show that our algorithm adapts to instance difficulty and yields a dimension-independent rate when the signal-to-noise ratio is high enough. Key to the computational efficiency of our method is an increasing step size scheme that adapts to refined estimates of the true solution. We validate our findings with numerical experiments and compare our algorithm against explicit $\ell_{1}$ penalization. Going from hard instances to easy ones, our algorithm is seen to undergo a phase transition, eventually matching least squares with an oracle knowledge of the true support. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05122v1 |
| https://arxiv.org/pdf/1909.05122v1.pdf | |
| PWC | https://paperswithcode.com/paper/implicit-regularization-for-optimal-sparse |
| Repo | |
| Framework | |
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis
| Title | A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis |
| Authors | Linda Studer, Michele Alberti, Vinaychandran Pondenkandath, Pinar Goktepe, Thomas Kolonko, Andreas Fischer, Marcus Liwicki, Rolf Ingold |
| Abstract | Automatic analysis of scanned historical documents comprises a wide range of image analysis tasks, which are often challenging for machine learning due to a lack of human-annotated learning samples. With the advent of deep neural networks, a promising way to cope with the lack of training data is to pre-train models on images from a different domain and then fine-tune them on historical documents. In the current research, a typical example of such cross-domain transfer learning is the use of neural networks that have been pre-trained on the ImageNet database for object recognition. It remains a mostly open question whether or not this pre-training helps to analyse historical documents, which have fundamentally different image properties when compared with ImageNet. In this paper, we present a comprehensive empirical survey on the effect of ImageNet pre-training for diverse historical document analysis tasks, including character recognition, style classification, manuscript dating, semantic segmentation, and content-based retrieval. While we obtain mixed results for semantic segmentation at pixel-level, we observe a clear trend across different network architectures that ImageNet pre-training has a positive effect on classification as well as content-based retrieval. |
| Tasks | Object Recognition, Semantic Segmentation, Transfer Learning |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09113v1 |
| https://arxiv.org/pdf/1905.09113v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-study-of-imagenet-pre |
| Repo | |
| Framework | |
Multi-level CNN for lung nodule classification with Gaussian Process assisted hyperparameter optimization
| Title | Multi-level CNN for lung nodule classification with Gaussian Process assisted hyperparameter optimization |
| Authors | Miao Zhang, Huiqi Li, Juan Lyu, Sai Ho Ling, Steven Su |
| Abstract | This paper investigates lung nodule classification by using deep neural networks (DNNs). Hyperparameter optimization in DNNs is a computationally expensive problem, where evaluating a hyperparameter configuration may take several hours or even days. Bayesian optimization has been recently introduced for the automatically searching of optimal hyperparameter configurations of DNNs. It applies probabilistic surrogate models to approximate the validation error function of hyperparameter configurations, such as Gaussian processes, and reduce the computational complexity to a large extent. However, most existing surrogate models adopt stationary covariance functions to measure the difference between hyperparameter points based on spatial distance without considering its spatial locations. This distance-based assumption together with the condition of constant smoothness throughout the whole hyperparameter search space clearly violates the property that the points far away from optimal points usually get similarly poor performance even though each two of them have huge spatial distance between them. In this paper, a non-stationary kernel is proposed which allows the surrogate model to adapt to functions whose smoothness varies with the spatial location of inputs, and a multi-level convolutional neural network (ML-CNN) is built for lung nodule classification whose hyperparameter configuration is optimized by using the proposed non-stationary kernel based Gaussian surrogate model. Our algorithm searches the surrogate for optimal setting via hyperparameter importance based evolutionary strategy, and the experiments demonstrate our algorithm outperforms manual tuning and well-established hyperparameter optimization methods such as Random search, Gaussian processes with stationary kernels, and recently proposed Hyperparameter Optimization via RBF and Dynamic coordinate search. |
| Tasks | Gaussian Processes, Hyperparameter Optimization, Lung Nodule Classification |
| Published | 2019-01-02 |
| URL | http://arxiv.org/abs/1901.00276v1 |
| http://arxiv.org/pdf/1901.00276v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-level-cnn-for-lung-nodule |
| Repo | |
| Framework | |
A Strongly Asymptotically Optimal Agent in General Environments
| Title | A Strongly Asymptotically Optimal Agent in General Environments |
| Authors | Michael K. Cohen, Elliot Catt, Marcus Hutter |
| Abstract | Reinforcement Learning agents are expected to eventually perform well. Typically, this takes the form of a guarantee about the asymptotic behavior of an algorithm given some assumptions about the environment. We present an algorithm for a policy whose value approaches the optimal value with probability 1 in all computable probabilistic environments, provided the agent has a bounded horizon. This is known as strong asymptotic optimality, and it was previously unknown whether it was possible for a policy to be strongly asymptotically optimal in the class of all computable probabilistic environments. Our agent, Inquisitive Reinforcement Learner (Inq), is more likely to explore the more it expects an exploratory action to reduce its uncertainty about which environment it is in, hence the term inquisitive. Exploring inquisitively is a strategy that can be applied generally; for more manageable environment classes, inquisitiveness is tractable. We conducted experiments in “grid-worlds” to compare the Inquisitive Reinforcement Learner to other weakly asymptotically optimal agents. |
| Tasks | |
| Published | 2019-03-04 |
| URL | https://arxiv.org/abs/1903.01021v2 |
| https://arxiv.org/pdf/1903.01021v2.pdf | |
| PWC | https://paperswithcode.com/paper/strong-asymptotic-optimality-in-general |
| Repo | |
| Framework | |
On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits
| Title | On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits |
| Authors | Roman Pogodin, Tor Lattimore |
| Abstract | We make three contributions to the theory of k-armed adversarial bandits. First, we prove a first-order bound for a modified variant of the INF strategy by Audibert and Bubeck [2009], without sacrificing worst case optimality or modifying the loss estimators. Second, we provide a variance analysis for algorithms based on follow the regularised leader, showing that without adaptation the variance of the regret is typically {\Omega}(n^2) where n is the horizon. Finally, we study bounds that depend on the degree of separation of the arms, generalising the results by Cowan and Katehakis [2015] from the stochastic setting to the adversarial and improving the result of Seldin and Slivkins [2014] by a factor of log(n)/log(log(n)). |
| Tasks | |
| Published | 2019-03-19 |
| URL | https://arxiv.org/abs/1903.07890v3 |
| https://arxiv.org/pdf/1903.07890v3.pdf | |
| PWC | https://paperswithcode.com/paper/adaptivity-variance-and-separation-for |
| Repo | |
| Framework | |
Emotion Generation and Recognition: A StarGAN Approach
| Title | Emotion Generation and Recognition: A StarGAN Approach |
| Authors | Aritra Banerjee, Dimitrios Kollias |
| Abstract | The main idea of this ISO is to use StarGAN (A type of GAN model) to perform training and testing on an emotion dataset resulting in a emotion recognition which can be generated by the valence arousal score of the 7 basic expressions. We have created an entirely new dataset consisting of 4K videos. This dataset consists of all the basic 7 types of emotions: Happy, Sad, Angry, Surprised, Fear, Disgust, Neutral. We have performed face detection and alignment followed by annotating basic valence arousal values to the frames/images in the dataset depending on the emotions manually. Then the existing StarGAN model is trained on our created dataset after which some manual subjects were chosen to test the efficiency of the trained StarGAN model. |
| Tasks | Emotion Recognition, Face Detection |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.11090v1 |
| https://arxiv.org/pdf/1910.11090v1.pdf | |
| PWC | https://paperswithcode.com/paper/emotion-generation-and-recognition-a-stargan |
| Repo | |
| Framework | |
BioNet: Infusing Biomarker Prior into Global-to-Local Network for Choroid Segmentation in Optical Coherence Tomography Images
| Title | BioNet: Infusing Biomarker Prior into Global-to-Local Network for Choroid Segmentation in Optical Coherence Tomography Images |
| Authors | Huihong Zhang, Jianlong Yang, Kang Zhou, Zhenjie Chai, Jun Cheng, Shenghua Gao, Jiang Liu |
| Abstract | Choroid is the vascular layer of the eye, which is directly related to the incidence and severity of many ocular diseases. Optical Coherence Tomography (OCT) is capable of imaging both the cross-sectional view of retina and choroid, but the segmentation of the choroid region is challenging because of the fuzzy choroid-sclera interface (CSI). In this paper, we propose a biomarker infused global-to-local network (BioNet) for choroid segmentation, which segments the choroid with higher credibility and robustness. Firstly, our method trains a biomarker prediction network to learn the features of the biomarker. Then a global multi-layers segmentation module is applied to segment the OCT image into 12 layers. Finally, the global multi-layered result and the original OCT image are fed into a local choroid segmentation module to segment the choroid region with the biomarker infused as regularizer. We conducted comparison experiments with the state-of-the-art methods on a dataset (named AROD). The experimental results demonstrate the superiority of our method with $90.77%$ Dice-index and 6.23 pixels Average-unsigned-surface-detection-error, etc. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05090v1 |
| https://arxiv.org/pdf/1912.05090v1.pdf | |
| PWC | https://paperswithcode.com/paper/bionet-infusing-biomarker-prior-into-global |
| Repo | |
| Framework | |
Exploiting Promising Sub-Sequences of Jobs to solve the No-Wait Flowshop Scheduling Problem
| Title | Exploiting Promising Sub-Sequences of Jobs to solve the No-Wait Flowshop Scheduling Problem |
| Authors | Lucien Mousin, Marie-Eléonore Kessaci, Clarisse Dhaenens |
| Abstract | The no-wait flowshop scheduling problem is a variant of the classical permutation flowshop problem, with the additional constraint that jobs have to be processed by the successive machines without waiting time. To efficiently address this NP-hard combinatorial optimization problem we conduct an analysis of the structure of good quality solutions. This analysis shows that the No-Wait specificity gives them a common structure: they share identical sub-sequences of jobs, we call super-jobs. After a discussion on the way to identify these super-jobs, we propose IG-SJ, an algorithm that exploits super-jobs within the state-of-the-art algorithm for the classical permutation flowshop, the well-known Iterated Greedy (IG) algorithm. An iterative approach of IG-SJ is also proposed. Experiments are conducted on Taillard’s instances. The experimental results show that exploiting super-jobs is successful since IG-SJ is able to find 64 new best solutions. |
| Tasks | Combinatorial Optimization |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.09035v1 |
| http://arxiv.org/pdf/1903.09035v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-promising-sub-sequences-of-jobs-to |
| Repo | |
| Framework | |
The FA Quantifier Fuzzification Mechanism: analysis of convergence and efficient implementations
| Title | The FA Quantifier Fuzzification Mechanism: analysis of convergence and efficient implementations |
| Authors | Félix Díaz-Hermida, Marcos Matabuena, Juan C. Vidal |
| Abstract | The fuzzy quantification model FA has been identified as one of the best behaved quantification models in several revisions of the field of fuzzy quantification. This model is, to our knowledge, the unique one fulfilling the strict Determiner Fuzzification Scheme axiomatic framework that does not induce the standard min and max operators. The main contribution of this paper is the proof of a convergence result that links this quantification model with the Zadeh’s model when the size of the input sets tends to infinite. The convergence proof is, in any case, more general than the convergence to the Zadeh’s model, being applicable to any quantitative quantifier. In addition, recent revisions papers have presented some doubts about the existence of suitable computational implementations to evaluate the FA model in practical applications. In order to prove that this model is not only a theoretical approach, we show exact algorithmic solutions for the most common linguistic quantifiers as well as an approximate implementation by means of Monte Carlo. Additionally, we will also give a general overview of the main properties fulfilled by the FA model, as a single compendium integrating the whole set of properties fulfilled by it has not been previously published. |
| Tasks | |
| Published | 2019-02-06 |
| URL | http://arxiv.org/abs/1902.02132v1 |
| http://arxiv.org/pdf/1902.02132v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-fa-quantifier-fuzzification-mechanism |
| Repo | |
| Framework | |
Traffic Flow Combination Forecasting Method Based on Improved LSTM and ARIMA
| Title | Traffic Flow Combination Forecasting Method Based on Improved LSTM and ARIMA |
| Authors | Boyi Liu, Xiangyan Tang, Jieren Cheng, Pengchao Shi |
| Abstract | Traffic flow forecasting is hot spot research of intelligent traffic system construction. The existing traffic flow prediction methods have problems such as poor stability, high data requirements, or poor adaptability. In this paper, we define the traffic data time singularity ratio in the dropout module and propose a combination prediction method based on the improved long short-term memory neural network and time series autoregressive integrated moving average model (SDLSTM-ARIMA), which is derived from the Recurrent Neural Networks (RNN) model. It compares the traffic data time singularity with the probability value in the dropout module and combines them at unequal time intervals to achieve an accurate prediction of traffic flow data. Then, we design an adaptive traffic flow embedded system that can adapt to Java, Python and other languages and other interfaces. The experimental results demonstrate that the method based on the SDLSTM - ARIMA model has higher accuracy than the similar method using only autoregressive integrated moving average or autoregressive. Our embedded traffic prediction system integrating computer vision, machine learning and cloud has the advantages such as high accuracy, high reliability and low cost. Therefore, it has a wide application prospect. |
| Tasks | Time Series, Traffic Prediction |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10407v1 |
| https://arxiv.org/pdf/1906.10407v1.pdf | |
| PWC | https://paperswithcode.com/paper/traffic-flow-combination-forecasting-method |
| Repo | |
| Framework | |
Regularized Evolutionary Algorithm for Dynamic Neural Topology Search
| Title | Regularized Evolutionary Algorithm for Dynamic Neural Topology Search |
| Authors | Cristiano Saltori, Subhankar Roy, Nicu Sebe, Giovanni Iacca |
| Abstract | Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary algorithms, has recently become very popular. Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i.e., network architectures) and is therefore memory expensive. In this work, we propose a Regularized Evolutionary Algorithm with low memory footprint to evolve a dynamic image classifier. In details, we introduce novel custom operators that regularize the evolutionary process of a micro-population of 10 individuals. We conduct experiments on three different digits datasets (MNIST, USPS, SVHN) and show that our evolutionary method obtains competitive results with the current state-of-the-art. |
| Tasks | Neural Architecture Search, Object Recognition |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06252v2 |
| https://arxiv.org/pdf/1905.06252v2.pdf | |
| PWC | https://paperswithcode.com/paper/regularized-evolutionary-algorithm-for |
| Repo | |
| Framework | |
