arXiv research

DSPG improves SPSA for distributed optimization with wireless delays.

This paper aims at achieving a "good" estimator for the gradient of a function on a high-dimensional space. Often such functions are not sensitive in all coordinates and the gradient of the function is almost sparse. We propose a method for gradient estimation that combines ideas from Spall's Simultaneous Perturbation …

Study stability of trading strategy under market perturbations.

Improved GSPGS estimators reduce bias in noisy function measurements.

Feature selection (FS) has become an indispensable task in dealing with today's highly complex pattern recognition problems with massive number of features. In this study, we propose a new wrapper approach for FS based on binary simultaneous perturbation stochastic approximation (BSPSA). This pseudo-gradient descent st…

New algorithm reduces prediction errors across various loss functions.

New method generates universal adversarial perturbations across different image sources.

Novel geometry-informed irreversible perturbation accelerates Langevin dynamics convergence.

Free adversarial training reduces the generalization gap compared to vanilla method.

Study optimal strategies for insurer's dividends, investments, and liabilities.

Develops new methods to create imperceptible image changes that fool classifiers.

Our research tackles robustness to multiple perturbations in adversarial training.

Meta framework generates noise to improve multi-attack robustness.

Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations and achieve high standard test accuracy. However, this is contrary to the stand…

We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial perturbation that can easily fool the classifier network by using a gradient of each imag…

State-of-the-art machine learning models frequently misclassify inputs that have been perturbed in an adversarial manner. Adversarial perturbations generated for a given input and a specific classifier often seem to be effective on other inputs and even different classifiers. In other words, adversarial perturbations s…

New method defends against multiple perturbation models in adversarial attacks.

New attack reveals adversarial training's inability to handle both $\ell_2$ and $\ell_\infty$ norms.

We investigate the continuity of expected exponential utility maximization with respect to perturbation of the Sharpe ratio of markets. By focusing only on continuity, we impose weaker regularity conditions than those found in the literature. Specifically, we require, in addition to the $V$-compactness hypothesis of La…

We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a two-player zero-sum game. In this new formulation, both players simultaneously play the s…

Paper introduces input perturbation for privacy in machine learning models.

Paper defends deep learning classifiers against channel-aware adversarial attacks.

New attack tricks certifiably robust models into mislabeling images.

The paper improves SVM and localized SVM stability under triple perturbations.

Optimal reinsurance strategy found to minimize financial risk.

Adversarial training purifies hidden weights to remove small perturbations.

Proposes a defense method against multiple adversarial video types.

This study tackles offline RL with perturbed data sources, deriving a lower bound and proposing an optimal algorithm.

The paper analyzes stability and asymptotic behavior of hedging strategies in binomial and trinomial models.

A method to learn robust policies for environments with model mismatches.

DRO-Augment framework enhances deep neural network robustness.

This work analyzes how different forms of compressibility affect adversarial robustness in neural networks.

This paper explores the trade-off between spatial and adversarial robustness in neural networks.

The study assesses how financial networks resist simultaneous price shocks and calculates the worst-case loss.

CCE improves anomaly detection metrics by measuring both confidence and consistency.

The problem of recovering the asymptotics of a short range perturbation of the Euclidean metric on R^n from fixed energy scattering data is studied. It is shown that if two such metrics, g1, g2, have scattering data at some fixed energy which are equal up to smoothing, then there exists a diffeomorphism ψ`fixing infini…

We consider the problem of approximate joint triangularization of a set of noisy jointly diagonalizable real matrices. Approximate joint triangularizers are commonly used in the estimation of the joint eigenstructure of a set of matrices, with applications in signal processing, linear algebra, and tensor decomposition.…

We are focusing on bound constrained global optimization problems, whose objective functions are computationally expensive black-box functions and have multiple local minima. The recently popular Metric Stochastic Response Surface (MSRS) algorithm proposed by \cite{Regis2007SRBF} based on adaptive or sequential learnin…

Study learns optimal auctions from corrupted or perturbed bidder valuation samples.

Efficient method defends deep learning models from adversarial attacks.

This manuscript presents the following: (1) an improved version of the Binary Simultaneous Perturbation Stochastic Approximation (SPSA) Method for feature selection in machine learning (Aksakalli and Malekipirbazari, Pattern Recognition Letters, Vol. 75, 2016) based on non-monotone iteration gains computed via the Barz…

Paper proposes a privacy-preserving DML framework using local randomization and ADMM perturbation.

DualVDT improves time-series forecasting with a novel dual reparametrized structure.

Paper tackles robust graph matching in dense graphs with AMP type algorithm.

Generalised Degrees of Freedom (GDF), as defined by Ye (1998 JASA 93:120-131), represent the sensitivity of model fits to perturbations of the data. As such they can be computed for any statistical model, making it possible, in principle, to derive the number of parameters in machine-learning approaches. Defined origin…

Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion. During this iterative process the leakage of data privacy a…

This article is the second part of the article we promised to write at the end of Section 1 of [FOOO15] (arXiv:1209.4410). (Part I appeared in [Part I] (arXiv:1503.07631).) We discuss the foundation of the virtual fundamental chain and cycle technique, especially its version that appeared in [FOn] and also in Section A…

Can we manipulate multiple deep neural networks simultaneously?