arXiv research

Estimates set overlap and similarity using random samples.

The two-sample hypothesis testing problem is studied for the challenging scenario of high dimensional data sets with small sample sizes. We show that the two-sample hypothesis testing problem can be posed as a one-class set classification problem. In the set classification problem the goal is to classify a set of data …

The paper sets sample complexity bounds for identifying LTI systems from a finite set.

An algorithm solves optimization problems with large sample sets, improving worst-case complexity.

Novel approach for SEM in small samples with $p>n$.

An axiomatic approach to signal reconstruction is formulated, involving a sample consistent set and a guiding set, describing desired reconstructions. New frame-less reconstruction methods are proposed, based on a novel concept of a reconstruction set, defined as a shortest pathway between the sample consistent set and…

The paper examines how sampling data affects the performance of submodular maximization.

New framework compares credal sets for hypothesis testing with epistemic uncertainty.

Big data sets must be carefully partitioned into statistically similar data subsets that can be used as representative samples for big data analysis tasks. In this paper, we propose the random sample partition (RSP) data model to represent a big data set as a set of non-overlapping data subsets, called RSP data blocks,…

A new method to understand neural networks by sampling the 'inverse set' of a neuron.

A new algorithm improves credit scoring accuracy for imbalanced data.

The paper introduces a sampling theory for graphons with a Poincaré inequality and proves consistency.

Sampling is a fundamental topic in graph signal processing, having found applications in estimation, clustering, and video compression. In contrast to traditional signal processing, the irregularity of the signal domain makes selecting a sampling set non-trivial and hard to analyze. Indeed, though conditions for graph …

The paper identifies a 'small' set of functions containing Gaussian process samples.

Efficient algorithm for estimating target mean under known sampling distribution.

Boosting with unlabeled data achieves optimal sample complexity in agnostic settings.

Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we address this problem by providing a finite-sample analysis for decentralized batch MARL with networked agents…

This paper proposes a method to use deep neural networks as end-to-end open-set classifiers. It is based on intra-class data splitting. In open-set recognition, only samples from a limited number of known classes are available for training. During inference, an open-set classifier must reject samples from unknown class…

Improved bounds for function approximation in nonlinear sets.

Develops a new method for sampling from Bayesian credible sets using deep generative quantile learning.

Extends conformal prediction to contrastive learning for better coverage of positive samples.

Algorithm identifies Pareto set in bandits with contaminated feedback.

New method for identifying best designs in vector optimization with uncertain feedback.

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

Efficiently estimate Boolean product distribution parameters from truncated samples.

Paper proposes PSIPS for identifying Pareto set with correlated objectives.

Higher bootstrap rates than 1.0 improve random forest performance.

Enhanced Sampling Scheme improves masked generative modeling.

Paper introduces PCP for efficient, reliable predictive inference.

Deep adaptive sampling improves surrogate modeling for complex systems.

This paper proposes asal, a new GAN based active learning method that generates high entropy samples. Instead of directly annotating the synthetic samples, ASAL searches similar samples from the pool and includes them for training. Hence, the quality of new samples is high and annotations are reliable. To the best of o…

Develops asymptotic analysis for RandNLA sampling estimators in least-squares problems.

Unified data representation learning improves non-parametric two-sample testing.

Neural networks compress and sample WDN contamination dynamics efficiently.

The paper improves methods for estimating set size using samples.

We consider the problem of estimating the mean of a symmetric log-concave distribution under the constraint that only a single bit per sample from this distribution is available to the estimator. We study the mean squared error as a function of the sample size (and hence the number of bits). We consider three settings:…

The level sets of neural networks represent fundamental properties such as decision boundaries of classifiers and are used to model non-linear manifold data such as curves and surfaces. Thus, methods for controlling the neural level sets could find many applications in machine learning. In this paper we present a simpl…

Efficiently samples conformal boundaries in high dimensions using flows.

Curriculum Labeling improves semi-supervised learning with pseudo-labeling, achieving high accuracy with minimal labeled data.

We study the problem of semi-supervised singing voice separation, in which the training data contains a set of samples of mixed music (singing and instrumental) and an unmatched set of instrumental music. Our solution employs a single mapping function g, which, applied to a mixed sample, recovers the underlying instrum…

Study approximates unknown function levels with queries.

The paper tackles sampling biases by ensuring minority groups are adequately represented in training data.

Paper reviews and compares methods for handling imbalanced data.

Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical understanding of the relationships between these two kinds of methodology, and limited unde…

Study improves treatment effect estimation using unlabeled covariates.

A new method selects training samples for fine-tuning using validation set inference.

The study examines property testing and estimation under non-identically distributed samples, finding necessary and sufficient sample complexities.

We study the problem of estimating the parameters of a Gaussian distribution when samples are only shown if they fall in some (unknown) subset $S \subseteq \R^d$. This core problem in truncated statistics has long history going back to Galton, Lee, Pearson and Fisher. Recent work by Daskalakis et al. (FOCS'18), provide…