arXiv research

This work improves testing of machine learning model modifications using novel statistical methods.

New method detects RNA modifications without prior training, revealing novel sites.

Proposes simplified SHAP for faster black-box model explanations.

Computational methods that predict differential gene expression from histone modification signals are highly desirable for understanding how histone modifications control the functional heterogeneity of cells through influencing differential gene regulation. Recent studies either failed to capture combinatorial effects…

Behavior modification improves prediction accuracy by nudging user behavior.

Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on improving accuracy and overlook other aspects such as robustness and interpretability. In this paper, we propose adversarial modifications for li…

Paper proposes using pairwise feature comparisons to infer modification costs for user recourse.

In this work we present a modification in the conventional flow of information through a LSTM network, which we consider well suited for RNNs in general. The modification leads to a iterative scheme where the computations performed by the LSTM cell are repeated over a constant input and cell state values, while updatin…

We define an operation on homology ${B}^4$ which we call an $n$-twist annulus modification. We give a new construction of smoothly slice knots and exotically slice knots via $n$-twist annulus modifications. As an application, we present a new example of a smoothly slice knot with non-slice derivatives. Such examples we…

Label smoothing improves model robustness against misspecification.

We present an axiomatic modification of quaternionic quantum mechanics with a possible-worlds semantics capable of predicting essential "nonquantum" features of an observable universe model - the dimensionality and topology of spacetime, the existence, the signature and a specific form of a metric on it, and certain na…

A modification of the confidence screening mechanism based on adaptive weighing of every training instance at each cascade level of the Deep Forest is proposed. The idea underlying the modification is very simple and stems from the confidence screening mechanism idea proposed by Pang et al. to simplify the Deep Forest …

Max-Cut decision tree improves classification accuracy and reduces computation time.

PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at https://github.com/openai/pixel-cnn. Our implementation contains a number of modifications to the original model that both simplify its structure an…

Study of unimodular Sasaki and Vaisman Lie groups, determining all modifications explicitly.

SurvLIME-Inf simplifies explanation of survival models using a linear programming approach.

We study large-scale classification problems in changing environments where a small part of the dataset is modified, and the effect of the data modification must be quickly incorporated into the classifier. When the entire dataset is large, even if the amount of the data modification is fairly small, the computational …

Study shows how to manipulate VAEs for attacks and assess their robustness.

Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability.We propose the fault sneaking attack on DNNs, where the adversary aims to misclassify certain input images into any target lab…

Improved peak detection in ChIP-seq data reduces over-dispersion.

MCD automates counterfactual design searches for multi-modal tasks.

Method explains anomaly detection by generating normal modifications.

New technique explains convergence in ML models with data modifications.

Modified BFGS and LBFGS++ libraries boost performance for non-parallelizable functions.

We study Khovanov homology classes which have state cycle representatives, and examine how they interact with Jacobsson homomorphisms and Lee's map $Φ$. As an application, we describe a general procedure, quasipositive modification, for constructing H-thick knots in rational Khovanov homology. Moreover, we show that sp…

ModHiFi identifies critical components for model modification without gradients or loss function.

Preserves hyperbolicity in link complements with two moves.

Approves updates to machine learning models in healthcare based on accumulating data.

ABRF uses attention weights to improve RF performance.

A new method improves continual learning by replaying pseudo data and using orthogonal weight modification.

Deep Boltzmann machines are in principle powerful models for extracting the hierarchical structure of data. Unfortunately, attempts to train layers jointly (without greedy layer-wise pretraining) have been largely unsuccessful. We propose a modification of the learning algorithm that initially recenters the output of t…

Bayesian method for estimating quantile sets efficiently.

A new method for effective VAE training using calibrated decoders.

We propose a modification of the three-manifold invariant based on the use of Euclidean metric values ascribed to the elements of manifold triangulation. We thus obtain a nontrivial invariant that can, in particular, distinguish non-homeomorphic lens spaces.

We briefly review the approach to optimization of portfolios according to the theory of Markowitz and propose a further modification that can improve the outcome of the optimization process. The modification takes account of the entropic contribution from the time series used to compute the parameters in the Markowitz …

SurvNAM explains survival model predictions using machine learning.

In this paper we suggest a modification of the regression-based variance reduction approach recently proposed in Belomestny et al. This modification is based on the stratification technique and allows for a further significant variance reduction. The performance of the proposed approach is illustrated by several numeri…

ABIForest improves anomaly detection using attention weights.

Kapustin and Witten associate a Hecke modification of a holomorphic bundle over a Riemann surface to a singular monopole on a Riemannian surface times an interval satisfying prescribed boundary conditions. We prove existence and uniqueness of singular monopoles satisfying prescribed boundary conditions for any given He…

In this comment on "Solving Statistical Mechanics Using Variational Autoregressive Networks" by Wu et al., we propose a subtle yet powerful modification of their approach. We show that the inherent sampling error of their method can be corrected by using neural network-based MCMC or importance sampling which leads to a…

For a stratified group $G$, we construct a class of polarised Lie groups, which we call modifications of $G$, that are locally contactomorphic to it. Vice versa, we show that if a polarised group is locally contactomorphic to a stratified group $G$, whose Lie algebra has finite Tanaka prolongation, then it must be a mo…

Proposes new methods for inference in GLMs without assuming model correctness.

A new bias score method optimizes fairness in classification.

We will consider locally conformally balanced manifolds. We prove that a locally conformally balanced condition is not stable under a small deformation. We prove that locally conformally balanced condition is stable under any proper modification. We prove that symmetric products of the Kodaira surface can be resolve to…

Despite the growing popularity of modern machine learning techniques (e.g. Deep Neural Networks) in cyber-security applications, most of these models are perceived as a black-box for the user. Adversarial machine learning offers an approach to increase our understanding of these models. In this paper we present an appr…

In this paper, we consider a proper modification $f : \tilde M \to M$ between complex manifolds, and study when a generalized $p-$Kähler property goes back from $M$ to $\tilde M$. When $f$ is the blow-up at a point, every generalized $p-$Kähler property is conserved, while when $f$ is the blow-up along a submanifold, t…

Thompson Sampling remains differentially private with minimal modifications.

Many proteoforms - arising from alternative splicing, post-translational modifications (PTMs), or paralogous genes - have distinct biological functions, such as histone PTM proteoforms. However, their quantification by existing bottom-up mass-spectrometry (MS) methods is undermined by peptide-specific biases. To avoid …