arXiv research

BinConv improves time series forecasting by preserving ordinal information in a classification framework.

We propose a probabilistic graphical model realizing a minimal encoding of real variables dependencies based on possibly incomplete observation and an empirical cumulative distribution function per variable. The target application is a large scale partially observed system, like e.g. a traffic network, where a small pr…

Binary encoding enables neural networks to extrapolate periodic functions.

Paper introduces Laplace-HDC for better binary hyperdimensional computing.

Study infers tree topology from customer data using contrastive learning.

Efficient binary sampling method for global optimization of univariate functions with low regret.

The goal of Ordinal Regression is to find a rule that ranks items from a given set. Several learning algorithms to solve this prediction problem build an ensemble of binary classifiers. Ranking by Projecting uses interdependent binary perceptrons. These perceptrons share the same direction vector, but use different bia…

Geometric analysis of ROC and PR curves for binary classification.

New algorithms achieve near-optimal cumulative loss in nonparametric online learning and games.

BEGIN network models binary data without parametric assumptions.

We present a binary code for spinors and Clifford multiplication using non-negative integers and their binary expressions, which can be easily implemented in computer programs for explicit calculations. As applications, we present explicit descriptions of the triality automorphism of $Spin(8)$, explicit representations…

LxCIM metric improves binary classification performance evaluation.

Regularized target encoding beats traditional methods for high cardinality features in ML.

A new method for binary ICA using non-stationary sources.

Enhances quantum machine learning models using Fock states.

SplitWise enhances stepwise regression by adaptively encoding numeric predictors into binary features.

Cubic predicts stock market indices by fusing stock latent embeddings and converting to binary classification.

Improves deep learning robustness by considering task and model.

An attractive approach for fast search in image databases is binary hashing, where each high-dimensional, real-valued image is mapped onto a low-dimensional, binary vector and the search is done in this binary space. Finding the optimal hash function is difficult because it involves binary constraints, and most approac…

Estimates causal effects using machine learning for binary treatment and mediator.

CausalEGM estimates causal effects by encoding confounders, improving performance in high-dimensional settings.

New hashing method improves document retrieval precision.

We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits. Among all possible algorithms that use this information, ours finds the autoencoder that reconstructs its inputs with worst-case optimal loss. The optimal decode…

We investigate a PL topology question: which circle bundles can be triangulated over a given triangulation of the base? The question got a simple answer emphasizing the role of minimal triangulations encoded by local systems of circular permutations of vertices of the base simplices. The answer is based on an experimen…

New methods improve estimation accuracy in noisy settings.

Extends graph encoder embedding to weighted graphs and matrices.

Study robust learning of Lipschitz functions under corrupted binary signals.

Machine learning helps create accurate models of neutron star postmerger signals.

New exact tests detect changepoints in binary and count data, especially when normal approximations fail.

Matrix factorization is a key tool in data analysis; its applications include recommender systems, correlation analysis, signal processing, among others. Binary matrices are a particular case which has received significant attention for over thirty years, especially within the field of data mining. Dictionary learning …

Neural networks learn faster with correlated latent variables.

The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.

EagleEye detects localized density anomalies in multivariate data.

We design a new nonparametric method that allows one to estimate the matrix of integrated kernels of a multivariate Hawkes process. This matrix not only encodes the mutual influences of each nodes of the process, but also disentangles the causality relationships between them. Our approach is the first that leads to an …

Binary hashing is a well-known approach for fast approximate nearest-neighbor search in information retrieval. Much work has focused on affinity-based objective functions involving the hash functions or binary codes. These objective functions encode neighborhood information between data points and are often inspired by…

We propose a stochastic process driven by memory effect with novel distributions including both exponential and leptokurtic heavy-tailed distributions. A class of distribution is analytically derived from the continuum limit of the discrete binary process with the renormalized auto-correlation and the closed form momen…

To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable augmentation, REINFORCE, and reparameterization, the ARM estimator achieves adaptive variance reducti…

Hashing techniques, also known as binary code learning, have recently gained increasing attention in large-scale data analysis and storage. Generally, most existing hash clustering methods are single-view ones, which lack complete structure or complementary information from multiple views. For cluster tasks, abundant p…

New method predicts wave height exceedance probabilities.

HFformer outperforms LSTM in high-frequency trading with multiple signals.

New algorithm reduces regret in combinatorial causal bandits without graph structure.

In the economic literature, geographic distances are considered fundamental factors to be included in any theoretical model whose aim is the quantification of the trade between countries. Quantitatively, distances enter into the so-called gravity models that successfully predict the weight of non-zero trade flows. Howe…

Symmetry in neural networks affects generalization, as shown by CLT and RG transformations.

We propose a stochastic process driven by the memory effect with novel distributions which include both exponential and leptokurtic heavy-tailed distributions. A class of the distributions is analytically derived from the continuum limit of the discrete binary process with the renormalized auto-correlation. The moment …

For a product of interest, we propose a search method to surface a set of reference products. The reference products can be used as candidates to support downstream modeling tasks and business applications. The search method consists of product representation learning and fingerprint-type vector searching. The product …

The study explores the compressive power of Boolean threshold autoencoders, finding that seven layers are necessary but three are not.

A new control chart detects shifts in binary data streams quickly and reliably.

The mesoscopic organization of complex systems, from financial markets to the brain, is an intermediate between the microscopic dynamics of individual units (stocks or neurons, in the mentioned cases), and the macroscopic dynamics of the system as a whole. The organization is determined by "communities" of units whose …