arXiv research

Value selection reduces model size while maintaining accuracy.

Training of one-vs.-rest SVMs can be parallelized over the number of classes in a straight forward way. Given enough computational resources, one-vs.-rest SVMs can thus be trained on data involving a large number of classes. The same cannot be stated, however, for the so-called all-in-one SVMs, which require solving a …

The study reduces a personality measurement instrument to 10 features with minimal loss of accuracy.

RS-NN predicts belief functions for classification, improving accuracy and uncertainty estimation.

Bayesian method improves few-shot classification accuracy.

We extend quantization-aware training to extreme model compression.

We show the rank (i.e. minimal size of a generating set) of lattices cannot grow faster than the volume.

Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However, progress faces a major roadblock, as models trained with large batches often do not ge…

Deep learning classifies autism vs controls with high accuracy using large fMRI dataset.

Improved recommendation systems using multi-layer embeddings reduce model size while maintaining accuracy.

Ensembles of deep neural networks significantly improve generalization accuracy. However, training neural network ensembles requires a large amount of computational resources and time. State-of-the-art approaches either train all networks from scratch leading to prohibitive training cost that allows only very small ens…

Wireless traffic prediction is a fundamental enabler to proactive network optimisation in beyond 5G. Forecasting extreme demand spikes and troughs due to traffic mobility is essential to avoiding outages and improving energy efficiency. Current state-of-the-art deep learning forecasting methods predominantly focus on o…

Our work focuses on the problem of predicting the transfer of pediatric patients from the general ward of a hospital to the pediatric intensive care unit. Using data collected over 5.5 years from the electronic health records of two medical facilities, we develop classifiers based on adaptive boosting and gradient tree…

A new L2D system produces calibrated probabilities of expert correctness without sacrificing accuracy.

CoroNet detects COVID-19 from chest X-rays with high accuracy.

New theorem bounds group quotient size to subgroups index.

Many of the best statistical classification algorithms are binary classifiers that can only distinguish between one of two classes. The number of possible ways of generalizing binary classification to multi-class increases exponentially with the number of classes. There is some indication that the best method will depe…

Time series forecasting is one of the most active research topics. Machine learning methods have been increasingly adopted to solve these predictive tasks. However, in a recent work, these were shown to systematically present a lower predictive performance relative to simple statistical methods. In this work, we counte…

This paper presents a novel unifying framework of bilinear LSTMs that can represent and utilize the nonlinear interaction of the input features present in sequence datasets for achieving superior performance over a linear LSTM and yet not incur more parameters to be learned. To realize this, our unifying framework allo…

Study error bounds and optimal schedules for Masked Diffusions with factorized approximations.

This paper analyzes data-driven Newsvendor problems and finds a wide range of possible regrets.

We propose an end-to-end deep learning learning model for graph classification and representation learning that is invariant to permutation of the nodes of the input graphs. We address the challenge of learning a fixed size graph representation for graphs of varying dimensions through a differentiable node attention po…

This paper reviews methods to create compact neural networks for IoT applications.

Robust cancer screening model using pre-trained ensembles for biomarkers.

Neural network quantization procedure is the necessary step for porting of neural networks to mobile devices. Quantization allows accelerating the inference, reducing memory consumption and model size. It can be performed without fine-tuning using calibration procedure (calculation of parameters necessary for quantizat…

Paper designs optimal ECOCs using IP for robust multiclass classification.

New linear algorithms improve wSVMs for multiclass probability estimation.

CAP adapts optimization to class attributes for better fairness.

Any given classification problem can be modeled using multi-class or One-vs-All (OVA) architecture. An OVA system consists of as many OVA models as the number of classes, providing the advantage of asynchrony, where each OVA model can be re-trained independent of other models. This is particularly advantageous in setti…

Recently, Sogge-Zelditch and Colding-Minicozzi gave new power law lower bounds on the size of the nodal sets of eigenfunctions. The purpose of this short note is to point out a third method to obtain a power law lower bound on the volume of the nodal sets. Our method is based on the Donnelly-Fefferman growth bound for …

Hybrid quantum-classical model boosts S&P 500 prediction accuracy to 60.14%.

Simple model uses time series momentum to outperform benchmarks in equity and bond markets.

In recent years, the number of papers on Alzheimer's disease classification has increased dramatically, generating interesting methodological ideas on the use machine learning and feature extraction methods. However, practical impact is much more limited and, eventually, one could not tell which of these approaches are…

A common method of generalizing binary to multi-class classification is the error correcting code (ECC). ECCs may be optimized in a number of ways, for instance by making them orthogonal. Here we test two types of orthogonal ECCs on seven different datasets using three types of binary classifier and compare them with t…

Study reveals how initialization scale affects training accuracy in linear networks.

Donor-aware scRNA-seq benchmarks improve classification accuracy in inflammatory bowel disease.

Bayesian deep learning ensemble improves pneumonia diagnosis accuracy.

Proposes a new adversarial model to avoid accuracy vs. adversarial accuracy tradeoff.

Single deep model detects out-of-distribution data with single forward pass.

New model improves histopathology classification across magnifications.

VR game data for P300 BCI with raccoon vs demon stimuli.

Convolutional neural networks (CNNs) are commonly trained using a fixed spatial image size predetermined for a given model. Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps.…

This paper proposes a method for multi-class classification problems, where the number of classes K is large. The method, referred to as Candidates vs. Noises Estimation (CANE), selects a small subset of candidate classes and samples the remaining classes. We show that CANE is always consistent and computationally effi…

FinCARE combines financial data and AI reasoning to improve causal analysis of financial performance.

Momentum affects optimization differently at small vs large batch sizes near instability.

New methods show robustness and accuracy can coexist.

CPR models complex decision processes by breaking them into context-specific policies, improving interpretability and accuracy.

To the best of our knowledge, this paper presents the first large-scale study that tests whether network categories (e.g., social networks vs. web graphs) are distinguishable from one another (using both categories of real-world networks and synthetic graphs). A classification accuracy of $94.2\%$ was achieved using a …