arXiv subjects

Kumar Sricharan

Publications and source records attributed to Kumar Sricharan.

11 recordsLinked to original sources

arXiv2018

Improving robustness of classifiers by training against live traffic

Deep learning models are known to be overconfident in their predictions on out of distribution inputs. This is a challenge when a model is trained on a particular input dataset, but receives out of sample data when deployed in practice. Recently, there has been work on building classifiers that are robust to out of distribution samples by adding a regularization term that maximizes the entropy of the classifier output on out of distribution data. However, given the challenge that it is not always possible to obtain out of distribution samples, the authors suggest a GAN based alternative that is independent of specific knowledge of out of distribution samples. From this existing work, we also know that having access to the true out of sample distribution for regularization works significantly better than using samples from the GAN. In this paper, we make the following observation: in practice, the out of distribution samples are contained in the traffic that hits a deployed classifier. However, the traffic will also contain a unknown proportion of in-distribution samples. If the entropy over of all of the traffic data were to be naively maximized, this will hurt the classifier performance on in-distribution data. To effectively leverage this traffic data, we propose an adaptive regularization technique (based on the maximum predictive probability score of a sample) which penalizes out of distribution samples more heavily than in distribution samples in the incoming traffic. This ensures that the overall performance of the classifier does not degrade on in-distribution data, while detection of out-of-distribution samples is significantly improved by leveraging the unlabeled traffic data. We show the effectiveness of our method via experiments on natural image datasets.

stat.ML↗

arXiv2018

Building robust classifiers through generation of confident out of distribution examples

Deep learning models are known to be overconfident in their predictions on out of distribution inputs. There have been several pieces of work to address this issue, including a number of approaches for building Bayesian neural networks, as well as closely related work on detection of out of distribution samples. Recently, there has been work on building classifiers that are robust to out of distribution samples by adding a regularization term that maximizes the entropy of the classifier output on out of distribution data. To approximate out of distribution samples (which are not known apriori), a GAN was used for generation of samples at the edges of the training distribution. In this paper, we introduce an alternative GAN based approach for building a robust classifier, where the idea is to use the GAN to explicitly generate out of distribution samples that the classifier is confident on (low entropy), and have the classifier maximize the entropy for these samples. We showcase the effectiveness of our approach relative to state-of-the-art on hand-written characters as well as on a variety of natural image datasets.

stat.ML↗

arXiv2017

ExprGAN: Facial Expression Editing with Controllable Expression Intensity

Facial expression editing is a challenging task as it needs a high-level semantic understanding of the input face image. In conventional methods, either paired training data is required or the synthetic face resolution is low. Moreover, only the categories of facial expression can be changed. To address these limitations, we propose an Expression Generative Adversarial Network (ExprGAN) for photo-realistic facial expression editing with controllable expression intensity. An expression controller module is specially designed to learn an expressive and compact expression code in addition to the encoder-decoder network. This novel architecture enables the expression intensity to be continuously adjusted from low to high. We further show that our ExprGAN can be applied for other tasks, such as expression transfer, image retrieval, and data augmentation for training improved face expression recognition models. To tackle the small size of the training database, an effective incremental learning scheme is proposed. Quantitative and qualitative evaluations on the widely used Oulu-CASIA dataset demonstrate the effectiveness of ExprGAN.

cs.CV↗

arXiv2017

Semi-supervised Conditional GANs

We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework. The proposed semi-supervised GAN (SS-GAN) model uses a pair of stacked discriminators to learn the marginal distribution of the data, and the conditional distribution of the attributes given the data respectively. In the semi-supervised setting, the marginal distribution (which is often harder to learn) is learned from the labeled + unlabeled data, and the conditional distribution is learned purely from the labeled data. Our experimental results demonstrate that this model performs significantly better compared to existing semi-supervised conditional GAN models.

stat.ML↗

arXiv2017

Recognizing Abnormal Heart Sounds Using Deep Learning

The work presented here applies deep learning to the task of automated cardiac auscultation, i.e. recognizing abnormalities in heart sounds. We describe an automated heart sound classification algorithm that combines the use of time-frequency heat map representations with a deep convolutional neural network (CNN). Given the cost-sensitive nature of misclassification, our CNN architecture is trained using a modified loss function that directly optimizes the trade-off between sensitivity and specificity. We evaluated our algorithm at the 2016 PhysioNet Computing in Cardiology challenge where the objective was to accurately classify normal and abnormal heart sounds from single, short, potentially noisy recordings. Our entry to the challenge achieved a final specificity of 0.95, sensitivity of 0.73 and overall score of 0.84. We achieved the greatest specificity score out of all challenge entries and, using just a single CNN, our algorithm differed in overall score by only 0.02 compared to the top place finisher, which used an ensemble approach.

cs.SD↗

arXiv2017

Ensemble Estimation of Distributional Functionals via $k$-Nearest Neighbors

The problem of accurate nonparametric estimation of distributional functionals (integral functionals of one or more probability distributions) has received recent interest due to their wide applicability in signal processing, information theory, machine learning, and statistics. In particular, $k$-nearest neighbor (nn) based methods have received a lot of attention due to their adaptive nature and their relatively low computational complexity. We derive the mean squared error (MSE) convergence rates of leave-one-out $k$-nn plug-in density estimators of a large class of distributional functionals without boundary correction. We then apply the theory of optimally weighted ensemble estimation to obtain weighted ensemble estimators that achieve the parametric MSE rate under assumptions that are competitive with the state of the art. The asymptotic distributions of these estimators, which are unknown for all other $k$-nn based distributional functional estimators, are also presented which enables us to perform hypothesis testing.

cs.IT↗

arXiv2017

Latent Laplacian Maximum Entropy Discrimination for Detection of High-Utility Anomalies

Data-driven anomaly detection methods suffer from the drawback of detecting all instances that are statistically rare, irrespective of whether the detected instances have real-world significance or not. In this paper, we are interested in the problem of specifically detecting anomalous instances that are known to have high real-world utility, while ignoring the low-utility statistically anomalous instances. To this end, we propose a novel method called Latent Laplacian Maximum Entropy Discrimination (LatLapMED) as a potential solution. This method uses the EM algorithm to simultaneously incorporate the Geometric Entropy Minimization principle for identifying statistical anomalies, and the Maximum Entropy Discrimination principle to incorporate utility labels, in order to detect high-utility anomalies. We apply our method in both simulated and real datasets to demonstrate that it has superior performance over existing alternatives that independently pre-process with unsupervised anomaly detection algorithms before classifying.

stat.ML↗

arXiv2017

Ensemble Estimation of Generalized Mutual Information with Applications to Genomics

Mutual information is a measure of the dependence between random variables that has been used successfully in myriad applications in many fields. Generalized mutual information measures that go beyond classical Shannon mutual information have also received much interest in these applications. We derive the mean squared error convergence rates of kernel density-based plug-in estimators of general mutual information measures between two multidimensional random variables $\mathbf{X}$ and $\mathbf{Y}$ for two cases: 1) $\mathbf{X}$ and $\mathbf{Y}$ are continuous; 2) $\mathbf{X}$ and $\mathbf{Y}$ may have any mixture of discrete and continuous components. Using the derived rates, we propose an ensemble estimator of these information measures called GENIE by taking a weighted sum of the plug-in estimators with varied bandwidths. The resulting ensemble estimators achieve the $1/N$ parametric mean squared error convergence rate when the conditional densities of the continuous variables are sufficiently smooth. To the best of our knowledge, this is the first nonparametric mutual information estimator known to achieve the parametric convergence rate for the mixture case, which frequently arises in applications (e.g. variable selection in classification). The estimator is simple to implement and it uses the solution to an offline convex optimization problem and simple plug-in estimators. A central limit theorem is also derived for the ensemble estimators and minimax rates are derived for the continuous case. We demonstrate the ensemble estimator for the mixed case on simulated data and apply the proposed estimator to analyze gene relationships in single cell data.

cs.IT↗

arXiv2016

Ensemble Estimation of Information Divergence

Recent work has focused on the problem of nonparametric estimation of information divergence functionals. Many existing approaches are restrictive in their assumptions on the density support set or require difficult calculations at the support boundary which must be known a priori. The MSE convergence rate of a leave-one-out kernel density plug-in divergence functional estimator for general bounded density support sets is derived where knowledge of the support boundary is not required. The theory of optimally weighted ensemble estimation is generalized to derive a divergence estimator that achieves the parametric rate when the densities are sufficiently smooth. The asymptotic distribution of this estimator and some guidelines for tuning parameter selection are provided. Based on the theory, an empirical estimator of R\'{e}nyi-$\alpha$ divergence is proposed that outperforms the standard kernel density plug-in estimator, especially in high dimension. The estimator is shown to be robust to the choice of tuning parameters. As an illustration, we use the estimator to estimate bounds on the Bayes error rate of a classification problem.

cs.IT↗

arXiv2013

Ensemble estimators for multivariate entropy estimation

The problem of estimation of density functionals like entropy and mutual information has received much attention in the statistics and information theory communities. A large class of estimators of functionals of the probability density suffer from the curse of dimensionality, wherein the mean squared error (MSE) decays increasingly slowly as a function of the sample size $T$ as the dimension $d$ of the samples increases. In particular, the rate is often glacially slow of order $O(T^{-γ/{d}})$, where $γ>0$ is a rate parameter. Examples of such estimators include kernel density estimators, $k$-nearest neighbor ($k$-NN) density estimators, $k$-NN entropy estimators, intrinsic dimension estimators and other examples. In this paper, we propose a weighted affine combination of an ensemble of such estimators, where optimal weights can be chosen such that the weighted estimator converges at a much faster dimension invariant rate of $O(T^{-1})$. Furthermore, we show that these optimal weights can be determined by solving a convex optimization problem which can be performed offline and does not require training data. We illustrate the superior performance of our weighted estimator for two important applications: (i) estimating the Panter-Dite distortion-rate factor and (ii) estimating the Shannon entropy for testing the probability distribution of a random sample.

math.ST↗

arXiv2012

Empirical estimation of entropy functionals with confidence

This paper introduces a class of k-nearest neighbor ($k$-NN) estimators called bipartite plug-in (BPI) estimators for estimating integrals of non-linear functions of a probability density, such as Shannon entropy and Rényi entropy. The density is assumed to be smooth, have bounded support, and be uniformly bounded from below on this set. Unlike previous $k$-NN estimators of non-linear density functionals, the proposed estimator uses data-splitting and boundary correction to achieve lower mean square error. Specifically, we assume that $T$ i.i.d. samples ${X}_i \in \mathbb{R}^d$ from the density are split into two pieces of cardinality $M$ and $N$ respectively, with $M$ samples used for computing a k-nearest-neighbor density estimate and the remaining $N$ samples used for empirical estimation of the integral of the density functional. By studying the statistical properties of k-NN balls, explicit rates for the bias and variance of the BPI estimator are derived in terms of the sample size, the dimension of the samples and the underlying probability distribution. Based on these results, it is possible to specify optimal choice of tuning parameters $M/T$, $k$ for maximizing the rate of decrease of the mean square error (MSE). The resultant optimized BPI estimator converges faster and achieves lower mean squared error than previous $k$-NN entropy estimators. In addition, a central limit theorem is established for the BPI estimator that allows us to specify tight asymptotic confidence intervals.

math.ST↗