arXiv research

Android and Facebook provide third-party applications with access to users' private data and the ability to perform potentially sensitive operations (e.g., post to a user's wall or place phone calls). As a security measure, these platforms restrict applications' privileges with permission systems: users must approve th…

Study compares Android malware and benign apps using permissions.

Deep learning models misclassify malware with added benign features.

Role mining tackles the problem of finding a role-based access control (RBAC) configuration, given an access-control matrix assigning users to access permissions as input. Most role mining approaches work by constructing a large set of candidate roles and use a greedy selection strategy to iteratively pick a small subs…

Proposes a falsification framework to test algorithmic discriminant validity.

Proposes a test to ensure predictive algorithms predict intended outcomes better than unintended ones.

We present a pedagogical introduction to the recent advances in the computational geometry, physical implications, and data science of Calabi-Yau manifolds. Aimed at the beginning research student and using Calabi-Yau spaces as an exciting play-ground, we intend to teach some mathematics to the budding physicist, some …

Given a polyhedral surface, assume that it is prohibited to change the shape and size of any face but it is permissible to change the dihedral angles between the faces. A polyhedral surface is said to be flexible if it is possible to change its shape under the above restrictions. We prove that flexible polyhedral surfa…

SMAC3 optimizes machine learning hyperparameters efficiently.

For a certain class of distributions, we prove that the linear programming relaxation of $k$-medoids clustering---a variant of $k$-means clustering where means are replaced by exemplars from within the dataset---distinguishes points drawn from nonoverlapping balls with high probability once the number of points drawn a…

This paper was first written in 1990, but was never published. In it, the author presents a novel approach to the study of constant curvature spacetimes in 2+1 dimensions. A parameterization of flat 2+1-dimensional domains of dependence is given in terms of measured geodesic laminations. There is also an interesting re…

Linear filtration helps delete training data from models.

Hungarian text processing improved with efficient, accurate NLP pipelines.

The Whitehead link exterior lacks most Euler class taut foliations.

HuSpaCy offers an industrial-grade Hungarian NLP toolkit.

Sampling with replacement occurs in many settings in machine learning, notably in the bagging ensemble technique and the .632+ validation scheme. The number of unique original items in a bootstrap sample can have an important role in the behaviour of prediction models learned on it. Indeed, there are uncontrived exampl…

Google Research Football: A new 3D physics-based game for reinforcement learning.

Bayesian approach groups observations with similar effects for better inference.

Private statistics estimation faces a bias, accuracy, and privacy trilemma.

This paper studies the problem of maximizing the expected utility of terminal wealth for a financial agent with an unbounded random endowment, and with a utility function which supports both positive and negative wealth. We prove the existence of an optimal trading strategy within a class of permissible strategies -- t…

We present POLO --- a C++ library for large-scale parallel optimization research that emphasizes ease-of-use, flexibility and efficiency in algorithm design. It uses multiple inheritance and template programming to decompose algorithms into essential policies and facilitate code reuse. With its clear separation between…

Federated learning platform for drug discovery without sharing data.

In this paper, we attempt to improve Statistical Machine Translation (SMT) systems on a very diverse set of language pairs (in both directions): Czech - English, Vietnamese - English, French - English and German - English. To accomplish this, we performed translation model training, created adaptations of training sett…

Develops a minimax optimal estimator for system stability under distribution shift.

Paper finds optimal selling rule for pairs trading with stock constraints.

This paper tackles efficient data deletion from machine learning models.

This study provides a new mathematical structure for Koopman eigenfunctions.

This thesis examines the accuracy of scaling VaR estimates for longer holding periods.

Ever increasing number of Android malware, has always been a concern for cybersecurity professionals. Even though plenty of anti-malware solutions exist, a rational and pragmatic approach for the same is rare and has to be inspected further. In this paper, we propose a novel two-set feature selection approach based on …

tsflex speeds up time series processing and feature extraction.

New estimator improves policy evaluation in resource allocation RCTs.

Machine-learning models have been recently used for detecting malicious Android applications, reporting impressive performances on benchmark datasets, even when trained only on features statically extracted from the application, such as system calls and permissions. However, recent findings have highlighted the fragili…

Pattern recognition and machine learning are becoming integral parts of algorithms in a wide range of applications. Different algorithms and approaches for machine learning include different tradeoffs between performance and computation, so during algorithm development it is often necessary to explore a variety of diff…

We make several improvements to the mean-variance framework for optimal pre-trade algorithmic execution, by working with volume measures and generic price dynamics. Volume measures are the continuum analogies for discrete volume profiles commonly implemented in the execution industry. Execution then becomes an absolute…

New credit attribution methods for machine learning models using relaxed stability guarantees.

The paper explores how information theory aids in statistical learning models.

Unified framework for complex financial networks using lattice theory.

Private mean estimation with multiple samples requires a certain number of people to maintain privacy.

Paper shows spectral filters can transfer between different graphs discretizing the same space.

Gradient-based explanations correlate with Android malware classifier robustness.

Proposes a flexible framework for implied volatility surfaces with random parameters.

Building behavior profiles of Android applications (apps) with holistic, rich and multi-view information (e.g., incorporating several semantic views of an app such as API sequences, system calls, etc.) would help catering downstream analytics tasks such as app categorization, recommendation and malware analysis signifi…

We quantify the sensitivity of the Eisenberg-Noe clearing vector to estimation errors in the bilateral liabilities of a financial system in a stylized setting. The interbank liabilities matrix is a crucial input to the computation of the clearing vector. However, in practice central bankers and regulators must often es…

Paper develops malware detection methods using Hamming distance.

In a recent paper, it is shown that the LASSO algorithm exhibits "near-ideal behavior," in the following sense: Suppose $y = Az + η$ where $A$ satisfies the restricted isometry property (RIP) with a sufficiently small constant, and $\Vert η\Vert_2 \leq ε$. Then minimizing $\Vert z \Vert_1$ subject to $\Vert y - Az \Ver…

COF algorithm minimizes cost in multi-armed bandits with known costs and reward constraints.

The goal of this book is to characterize algebraically the closed 4-manifolds that fibre nontrivially or admit geometries in the sense of Thurston, or which are obtained by surgery on 2-knots, and to provide a reference for the topology of such manifolds and knots. The first chapter is purely algebraic. The rest of the…

New examples show limits of physical link isotopies.