arXiv research

Unified Bayesian model for multi-modal, small sample size biomedical data classification.

Regularized EM algorithm improves clustering performance with small sample sizes.

Study evaluates synthetic data augmentation for small datasets, highlighting inconsistencies in traditional metrics.

Proposes a new signal model for high-dimensional, small-sample-size data.

Simple private estimators for mean and covariance outperform existing methods.

Develops a method for manifold learning with small sample size datasets.

Adversarial training can hurt robust accuracy in small sample size scenarios.

Algorithm recovers large causal tree from small samples.

SPREV simplifies visualization of complex labeled datasets.

The paper revisits and improves on a Bayesian relevance vector machine method for small sample sizes.

SFCNeXt estimates brain age from small MRI datasets.

A new test improves statistical inference in bandit algorithms without sacrificing adaptiveness.

We present a novel Metropolis-Hastings method for large datasets that uses small expected-size minibatches of data. Previous work on reducing the cost of Metropolis-Hastings tests yield variable data consumed per sample, with only constant factor reductions versus using the full dataset for each sample. Here we present…

Deep networks and forests perform differently with small samples.

Proposes a VAE for HDLSS data augmentation.

New method selects better graphs for GGM inference in small sample sizes.

Estimates neural representation dimensionality from small sample sizes.

The study proves sampling-based GNNs can approximate training on full graphs with small subgraphs.

In statistical connectomics, the quantitative study of brain networks, estimating the mean of a population of graphs based on a sample is a core problem. Often, this problem is especially difficult because the sample or cohort size is relatively small, sometimes even a single subject. While using the element-wise sampl…

Learnable multiclass hypothesis classes don't always have a sample compression scheme of fixed size.

Binary classification improves with a small fraction of corrupted labels.

A new method for averaging model predictions using minimum divergence.

New algorithm groups variables by ancestral relationships to improve causal graph estimation accuracy.

Differentiable learning via SGD and GD can simulate various learning problems, depending on precision and minibatch size.

FedFaiREE addresses fairness in decentralized learning with small samples.

State-of-the-art implementations of boosting, such as XGBoost and LightGBM, can process large training sets extremely fast. However, this performance requires that the memory size is sufficient to hold a 2-3 multiple of the training set size. This paper presents an alternative approach to implementing the boosted trees…

Improved SVMs learn from few samples with composition and multiple scales.

Bob predicts a future observation based on a sample of size one. Alice can draw a sample of any size before issuing her prediction. How much better can she do than Bob? Perhaps surprisingly, under a large class of loss functions, which we refer to as the Cover-Hart family, the best Alice can do is to halve Bob's risk. …

In biospectroscopy, suitably annotated and statistically independent samples (e. g. patients, batches, etc.) for classifier training and testing are scarce and costly. Learning curves show the model performance as function of the training sample size and can help to determine the sample size needed to train good classi…

The study reveals a transition in neural network performance from infinite-width to variance-limited behavior as dataset size increases.

New summary measures reveal geometric structure in weighted measures on manifolds.

Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. More recently, having outperformed all conventional methods, deep learning based models have shown a great promise. These methods are however …

New method reduces ensemble size for linear bandits, achieving near optimal regret.

A new algorithm for robust causal discovery in small sample sizes.

SLdisco uses supervised learning to discover causal models from observational data.

New SDP algorithm recovers large clusters in SBM with small clusters of any size.

Privacy affects how much data is needed for CVaR optimization.

Feature selection from wide datasets leads to misleading results.

Scalable methods integrate multiview data for clinical outcomes.

A new method improves AI fairness assessment by estimating performance across intersectional subgroups.

Transfer learning improves causal model estimates in small samples.

Predictive models ground many state-of-the-art developments in statistical brain image analysis: decoding, MVPA, searchlight, or extraction of biomarkers. The principled approach to establish their validity and usefulness is cross-validation, testing prediction on unseen data. Here, I would like to raise awareness on e…

Datasets containing large samples of time-to-event data arising from several small heterogeneous groups are commonly encountered in statistics. This presents problems as they cannot be pooled directly due to their heterogeneity or analyzed individually because of their small sample size. Bayesian nonparametric modellin…

We investigate the problems of identity and closeness testing over a discrete population from random samples. Our goal is to develop efficient testers while guaranteeing Differential Privacy to the individuals of the population. We describe an approach that yields sample-efficient differentially private testers for the…

We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate efficiently the spectrum of the Hessian of modern deepnets, with tens of millions of parameters, trained on real data. Our results corroborate previous findings, based on small-scale networks, that the Hessian exhibits "s…

This paper explores how effective sample size, dimensionality, and model performance are related in covariate shift adaptation.

We formulate and analyze a graphical model selection method for inferring the conditional independence graph of a high-dimensional nonstationary Gaussian random process (time series) from a finite-length observation. The observed process samples are assumed uncorrelated over time and having a time-varying marginal dist…

Delayed rejection HMC improves sampling efficiency for multiscale distributions.