Paper Group ANR 1676
Feature Selection via Mutual Information: New Theoretical Insights. Generative Parameter Sampler For Scalable Uncertainty Quantification. Is Deep Learning an RG Flow?. Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training. More Efficient Off-Policy Evaluation through Regularized Targeted Learning. Submodula …
Feature Selection via Mutual Information: New Theoretical Insights
| Title | Feature Selection via Mutual Information: New Theoretical Insights |
| Authors | Mario Beraha, Alberto Maria Metelli, Matteo Papini, Andrea Tirinzoni, Marcello Restelli |
| Abstract | Mutual information has been successfully adopted in filter feature-selection methods to assess both the relevancy of a subset of features in predicting the target variable and the redundancy with respect to other variables. However, existing algorithms are mostly heuristic and do not offer any guarantee on the proposed solution. In this paper, we provide novel theoretical results showing that conditional mutual information naturally arises when bounding the ideal regression/classification errors achieved by different subsets of features. Leveraging on these insights, we propose a novel stopping condition for backward and forward greedy methods which ensures that the ideal prediction error using the selected feature subset remains bounded by a user-specified threshold. We provide numerical simulations to support our theoretical claims and compare to common heuristic methods. |
| Tasks | Feature Selection |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07384v1 |
| https://arxiv.org/pdf/1907.07384v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-selection-via-mutual-information-new |
| Repo | |
| Framework | |
Generative Parameter Sampler For Scalable Uncertainty Quantification
| Title | Generative Parameter Sampler For Scalable Uncertainty Quantification |
| Authors | Minsuk Shin, Young Lee, Jun S. Liu |
| Abstract | Uncertainty quantification has been a core of the statistical machine learning, but its computational bottleneck has been a serious challenge for both Bayesians and frequentists. We propose a model-based framework in quantifying uncertainty, called predictive-matching Generative Parameter Sampler (GPS). This procedure considers an Uncertainty Quantification (UQ) distribution on the targeted parameter, which matches the corresponding predictive distribution to the observed data. This framework adopts a hierarchical modeling perspective such that each observation is modeled by an individual parameter. This individual parameterization permits the resulting inference to be computationally scalable and robust to outliers. Our approach is illustrated for linear models, Poisson processes, and deep neural networks for classification. The results show that the GPS is successful in providing uncertainty quantification as well as additional flexibility beyond what is allowed by classical statistical procedures under the postulated statistical models. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12440v2 |
| https://arxiv.org/pdf/1905.12440v2.pdf | |
| PWC | https://paperswithcode.com/paper/generative-parameter-sampler-for-scalable |
| Repo | |
| Framework | |
Is Deep Learning an RG Flow?
| Title | Is Deep Learning an RG Flow? |
| Authors | Ellen de Mello Koch, Robert de Mello Koch, Ling Cheng |
| Abstract | Although there has been a rapid development of practical applications, theoretical explanations of deep learning are in their infancy. A possible starting point suggests that deep learning performs a sophisticated coarse graining. Coarse graining is the foundation of the renormalization group (RG), which provides a systematic construction of the theory of large scales starting from an underlying microscopic theory. In this way RG can be interpreted as providing a mechanism to explain the emergence of large scale structure, which is directly relevant to deep learning. We pursue the possibility that RG may provide a useful framework within which to pursue a theoretical explanation of deep learning. A statistical mechanics model for a magnet, the Ising model, is used to train an unsupervised RBM. The patterns generated by the trained RBM are compared to the configurations generated through a RG treatment of the Ising model. We argue that correlation functions between hidden and visible neurons are capable of diagnosing RG-like coarse graining. Numerical experiments show the presence of RG-like patterns in correlators computed using the trained RBMs. The observables we consider are also able to exhibit important differences between RG and deep learning. |
| Tasks | |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05212v1 |
| https://arxiv.org/pdf/1906.05212v1.pdf | |
| PWC | https://paperswithcode.com/paper/is-deep-learning-an-rg-flow |
| Repo | |
| Framework | |
Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training
| Title | Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training |
| Authors | Qiao Cheng, Meiyuan Fang, Yaqian Han, Jin Huang, Yitao Duan |
| Abstract | In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using adversarial learning and data augmentation, respectively. Experimental results on IWSLT2018 speech translation task show that our approach can bridge the gap between the ASR output and the MT input, outperforms the baseline by up to 2.83 BLEU on noisy ASR output, while maintaining close performance on clean text. |
| Tasks | Data Augmentation, Machine Translation, Speech Recognition |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11430v3 |
| https://arxiv.org/pdf/1909.11430v3.pdf | |
| PWC | https://paperswithcode.com/paper/breaking-the-data-barrier-towards-robust |
| Repo | |
| Framework | |
More Efficient Off-Policy Evaluation through Regularized Targeted Learning
| Title | More Efficient Off-Policy Evaluation through Regularized Targeted Learning |
| Authors | Aurélien F. Bibaut, Ivana Malenica, Nikos Vlassis, Mark J. van der Laan |
| Abstract | We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In particular, we introduce a novel doubly-robust estimator for the OPE problem in RL, based on the Targeted Maximum Likelihood Estimation principle from the statistical causal inference literature. We also introduce several variance reduction techniques that lead to impressive performance gains in off-policy evaluation. We show empirically that our estimator uniformly wins over existing off-policy evaluation methods across multiple RL environments and various levels of model misspecification. Finally, we further the existing theoretical analysis of estimators for the RL off-policy estimation problem by showing their $O_P(1/\sqrt{n})$ rate of convergence and characterizing their asymptotic distribution. |
| Tasks | Causal Inference |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06292v1 |
| https://arxiv.org/pdf/1912.06292v1.pdf | |
| PWC | https://paperswithcode.com/paper/more-efficient-off-policy-evaluation-through |
| Repo | |
| Framework | |
Submodular Load Clustering with Robust Principal Component Analysis
| Title | Submodular Load Clustering with Robust Principal Component Analysis |
| Authors | Yishen Wang, Xiao Lu, Yiran Xu, Di Shi, Zhehan Yi, Jiajun Duan, Zhiwei Wang |
| Abstract | Traditional load analysis is facing challenges with the new electricity usage patterns due to demand response as well as increasing deployment of distributed generations, including photovoltaics (PV), electric vehicles (EV), and energy storage systems (ESS). At the transmission system, despite of irregular load behaviors at different areas, highly aggregated load shapes still share similar characteristics. Load clustering is to discover such intrinsic patterns and provide useful information to other load applications, such as load forecasting and load modeling. This paper proposes an efficient submodular load clustering method for transmission-level load areas. Robust principal component analysis (R-PCA) firstly decomposes the annual load profiles into low-rank components and sparse components to extract key features. A novel submodular cluster center selection technique is then applied to determine the optimal cluster centers through constructed similarity graph. Following the selection results, load areas are efficiently assigned to different clusters for further load analysis and applications. Numerical results obtained from PJM load demonstrate the effectiveness of the proposed approach. |
| Tasks | Load Forecasting |
| Published | 2019-02-20 |
| URL | http://arxiv.org/abs/1902.07376v1 |
| http://arxiv.org/pdf/1902.07376v1.pdf | |
| PWC | https://paperswithcode.com/paper/submodular-load-clustering-with-robust |
| Repo | |
| Framework | |
Adaptive template systems: Data-driven feature selection for learning with persistence diagrams
| Title | Adaptive template systems: Data-driven feature selection for learning with persistence diagrams |
| Authors | Luis Polanco, Jose A. Perea |
| Abstract | Feature extraction from persistence diagrams, as a tool to enrich machine learning techniques, has received increasing attention in recent years. In this paper we explore an adaptive methodology to localize features in persistent diagrams, which are then used in learning tasks. Specifically, we investigate three algorithms, CDER, GMM and HDBSCAN, to obtain adaptive template functions/features. Said features are evaluated in three classification experiments with persistence diagrams. Namely, manifold, human shapes and protein classification. The main conclusion of our analysis is that adaptive template systems, as a feature extraction technique, yield competitive and often superior results in the studied examples. Moreover, from the adaptive algorithms here studied, CDER consistently provides the most reliable and robust adaptive featurization. |
| Tasks | Feature Selection |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.06741v1 |
| https://arxiv.org/pdf/1910.06741v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-template-systems-data-driven-feature |
| Repo | |
| Framework | |
Improving Deep Reinforcement Learning in Minecraft with Action Advice
| Title | Improving Deep Reinforcement Learning in Minecraft with Action Advice |
| Authors | Spencer Frazier, Mark Riedl |
| Abstract | Training deep reinforcement learning agents complex behaviors in 3D virtual environments requires significant computational resources. This is especially true in environments with high degrees of aliasing, where many states share nearly identical visual features. Minecraft is an exemplar of such an environment. We hypothesize that interactive machine learning IML, wherein human teachers play a direct role in training through demonstrations, critique, or action advice, may alleviate agent susceptibility to aliasing. However, interactive machine learning is only practical when the number of human interactions is limited, requiring a balance between human teacher effort and agent performance. We conduct experiments with two reinforcement learning algorithms which enable human teachers to give action advice, Feedback Arbitration and Newtonian Action Advice, under visual aliasing conditions. To assess potential cognitive load per advice type, we vary the accuracy and frequency of various human action advice techniques. Training efficiency, robustness against infrequent and inaccurate advisor input, and sensitivity to aliasing are examined. |
| Tasks | |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.01007v1 |
| https://arxiv.org/pdf/1908.01007v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-deep-reinforcement-learning-in |
| Repo | |
| Framework | |
explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
| Title | explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning |
| Authors | Thilo Spinner, Udo Schlegel, Hanna Schäfer, Mennatallah El-Assady |
| Abstract | We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions. |
| Tasks | |
| Published | 2019-07-29 |
| URL | https://arxiv.org/abs/1908.00087v2 |
| https://arxiv.org/pdf/1908.00087v2.pdf | |
| PWC | https://paperswithcode.com/paper/explainer-a-visual-analytics-framework-for |
| Repo | |
| Framework | |
Corpora Generation for Grammatical Error Correction
| Title | Corpora Generation for Grammatical Error Correction |
| Authors | Jared Lichtarge, Chris Alberti, Shankar Kumar, Noam Shazeer, Niki Parmar, Simon Tong |
| Abstract | Grammatical Error Correction (GEC) has been recently modeled using the sequence-to-sequence framework. However, unlike sequence transduction problems such as machine translation, GEC suffers from the lack of plentiful parallel data. We describe two approaches for generating large parallel datasets for GEC using publicly available Wikipedia data. The first method extracts source-target pairs from Wikipedia edit histories with minimal filtration heuristics, while the second method introduces noise into Wikipedia sentences via round-trip translation through bridge languages. Both strategies yield similar sized parallel corpora containing around 4B tokens. We employ an iterative decoding strategy that is tailored to the loosely supervised nature of our constructed corpora. We demonstrate that neural GEC models trained using either type of corpora give similar performance. Fine-tuning these models on the Lang-8 corpus and ensembling allows us to surpass the state of the art on both the CoNLL-2014 benchmark and the JFLEG task. We provide systematic analysis that compares the two approaches to data generation and highlights the effectiveness of ensembling. |
| Tasks | Grammatical Error Correction, Machine Translation |
| Published | 2019-04-10 |
| URL | http://arxiv.org/abs/1904.05780v1 |
| http://arxiv.org/pdf/1904.05780v1.pdf | |
| PWC | https://paperswithcode.com/paper/corpora-generation-for-grammatical-error |
| Repo | |
| Framework | |
Applying Quantum Hardware to non-Scientific Problems: Grover’s Algorithm and Rule-based Algorithmic Music Composition
| Title | Applying Quantum Hardware to non-Scientific Problems: Grover’s Algorithm and Rule-based Algorithmic Music Composition |
| Authors | Alexis Kirke |
| Abstract | Of all novel computing methods, quantum computation (QC) is currently the most likely to move from the realm of the unconventional into the conventional. As a result some initial work has been done on applications of QC outside of science: for example music. The small amount of arts research done in hardware or with actual physical systems has not utilized any of the advantages of quantum computation (QC): the main advantage being the potential speed increase of quantum algorithms. This paper introduces a way of utilizing Grover’s algorithm - which has been shown to provide a quadratic speed-up over its classical equivalent - in algorithmic rule-based music composition. The system introduced - qgMuse - is simple but scalable. Example melodies are composed using qgMuse using the ibmqx4 quantum hardware. The paper concludes with discussion on how such an approach can grow with the improvement of quantum computer hardware and software. |
| Tasks | |
| Published | 2019-02-02 |
| URL | https://arxiv.org/abs/1902.04237v3 |
| https://arxiv.org/pdf/1902.04237v3.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-grovers-algorithm-on-the |
| Repo | |
| Framework | |
A Multi-armed Bandit MCMC, with applications in sampling from doubly intractable posterior
| Title | A Multi-armed Bandit MCMC, with applications in sampling from doubly intractable posterior |
| Authors | Guanyang Wang |
| Abstract | Markov chain Monte Carlo (MCMC) algorithms are widely used to sample from complicated distributions, especially to sample from the posterior distribution in Bayesian inference. However, MCMC is not directly applicable when facing the doubly intractable problem. In this paper, we discussed and compared two existing solutions – Pseudo-marginal Monte Carlo and Exchange Algorithm. This paper also proposes a novel algorithm: Multi-armed Bandit MCMC (MABMC), which chooses between two (or more) randomized acceptance ratios in each step. MABMC could be applied directly to incorporate Pseudo-marginal Monte Carlo and Exchange algorithm, with higher average acceptance probability. |
| Tasks | Bayesian Inference |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05726v2 |
| http://arxiv.org/pdf/1903.05726v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-armed-bandit-mcmc-with-applications |
| Repo | |
| Framework | |
Self-adaptive decision-making mechanisms to balance the execution of multiple tasks for a multi-robots team
| Title | Self-adaptive decision-making mechanisms to balance the execution of multiple tasks for a multi-robots team |
| Authors | Nunzia Palmieri, Xin-She Yang, Floriano De Rango, Amilcare Francesco Santamaria |
| Abstract | This work addresses the coordination problem of multiple robots with the goal of finding specific hazardous targets in an unknown area and dealing with them cooperatively. The desired behaviour for the robotic system entails multiple requirements, which may also be conflicting. The paper presents the problem as a constrained bi-objective optimization problem in which mobile robots must perform two specific tasks of exploration and at same time cooperation and coordination for disarming the hazardous targets. These objectives are opposed goals, in which one may be favored, but only at the expense of the other. Therefore, a good trade-off must be found. For this purpose, a nature-inspired approach and an analytical mathematical model to solve this problem considering a single equivalent weighted objective function are presented. The results of proposed coordination model, simulated in a two dimensional terrain, are showed in order to assess the behaviour of the proposed solution to tackle this problem. We have analyzed the performance of the approach and the influence of the weights of the objective function under different conditions: static and dynamic. In this latter situation, the robots may fail under the stringent limited budget of energy or for hazardous events. The paper concludes with a critical discussion of the experimental results. |
| Tasks | Decision Making |
| Published | 2019-03-27 |
| URL | http://arxiv.org/abs/1903.11621v1 |
| http://arxiv.org/pdf/1903.11621v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-adaptive-decision-making-mechanisms-to |
| Repo | |
| Framework | |
Effective Sub-clonal Cancer Representation to Predict Tumor Evolution
| Title | Effective Sub-clonal Cancer Representation to Predict Tumor Evolution |
| Authors | Adnan Akbar, Geoffroy Dubourg-Felonneau, Andrey Solovyev, John W Cassidy, Nirmesh Patel, Harry W Clifford |
| Abstract | The majority of cancer treatments end in failure due to Intra-Tumor Heterogeneity (ITH). ITH in cancer is represented by clonal evolution where different sub-clones compete with each other for resources under conditions of Darwinian natural selection. Predicting the growth of these sub-clones within a tumour is among the key challenges of modern cancer research. Predicting tumor behavior enables the creation of risk profiles for patients and the optimisation of their treatment by therapeutically targeting sub-clones more likely to grow. Current research efforts in this space are focused on mathematical modelling of population genetics to quantify the selective advantage of sub-clones, thus enabling predictions of which sub-clones are more likely to grow. These tumor evolution models are based on assumptions which are not valid for real-world tumor micro-environment. Furthermore, these models are often fit on a single instance of a tumor, and hence prediction models cannot be validated. This paper presents an alternative approach for predicting cancer evolution using a data-driven machine learning method. Our proposed method is based on the intuition that if we can capture the true characteristics of sub-clones within a tumor and represent it in the form of features, a sophisticated machine learning algorithm can be trained to predict its behavior. The work presented here provides a novel approach to predicting cancer evolution, utilizing a data-driver approach. We strongly believe that the accumulation of data from microbiologists, oncologists and machine learning researchers could be used to encapsulate the true essence of tumor sub-clones, and can play a vital role in selecting the best cancer treatments for patients. |
| Tasks | |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12774v1 |
| https://arxiv.org/pdf/1911.12774v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-sub-clonal-cancer-representation-to |
| Repo | |
| Framework | |
autoAx: An Automatic Design Space Exploration and Circuit Building Methodology utilizing Libraries of Approximate Components
| Title | autoAx: An Automatic Design Space Exploration and Circuit Building Methodology utilizing Libraries of Approximate Components |
| Authors | Vojtech Mrazek, Muhammad Abdullah Hanif, Zdenek Vasicek, Lukas Sekanina, Muhammad Shafique |
| Abstract | Approximate computing is an emerging paradigm for developing highly energy-efficient computing systems such as various accelerators. In the literature, many libraries of elementary approximate circuits have already been proposed to simplify the design process of approximate accelerators. Because these libraries contain from tens to thousands of approximate implementations for a single arithmetic operation it is intractable to find an optimal combination of approximate circuits in the library even for an application consisting of a few operations. An open problem is “how to effectively combine circuits from these libraries to construct complex approximate accelerators”. This paper proposes a novel methodology for searching, selecting and combining the most suitable approximate circuits from a set of available libraries to generate an approximate accelerator for a given application. To enable fast design space generation and exploration, the methodology utilizes machine learning techniques to create computational models estimating the overall quality of processing and hardware cost without performing full synthesis at the accelerator level. Using the methodology, we construct hundreds of approximate accelerators (for a Sobel edge detector) showing different but relevant tradeoffs between the quality of processing and hardware cost and identify a corresponding Pareto-frontier. Furthermore, when searching for approximate implementations of a generic Gaussian filter consisting of 17 arithmetic operations, the proposed approach allows us to identify approximately $10^3$ highly important implementations from $10^{23}$ possible solutions in a few hours, while the exhaustive search would take four months on a high-end processor. |
| Tasks | |
| Published | 2019-02-22 |
| URL | http://arxiv.org/abs/1902.10807v2 |
| http://arxiv.org/pdf/1902.10807v2.pdf | |
| PWC | https://paperswithcode.com/paper/autoax-an-automatic-design-space-exploration |
| Repo | |
| Framework | |
