arXiv research

Optimal algorithm for contextual bandits with unknown context distributions.

Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed identically to the testing data. In many real-world applications, however, some potential …

New algorithm reduces online learning error for unknown feature distributions.

This paper introduces the first asymptotically optimal strategy for a multi armed bandit (MAB) model under side constraints. The side constraints model situations in which bandit activations are limited by the availability of certain resources that are replenished at a constant rate. The main result involves the deriva…

New mixture models for clustering and density estimation of unknown distributions.

Analyzes generalization error in distributed linear regression.

The problem of detecting data anomaly is considered. Under the null hypothesis that models anomaly-free data, measurements are assumed to be from an unknown distribution with some authenticated historical samples. Under the composite alternative hypothesis, measurements are from an unknown distribution positive distanc…

The paper proposes a method for distribution-free prediction sets that adapt to unknown temporal changes.

This paper addresses the problem of identifying a lower dimensional space where observed data can be sparsely represented. This under-complete dictionary learning task can be formulated as a blind separation problem of sparse sources linearly mixed with an unknown orthogonal mixing matrix. This issue is formulated in a…

Develops robust MDPs for unknown disturbances with performance guarantees.

Bayes classifier cannot be learned from noisy labels without knowing noise distribution.

Bayesian neural networks' performance varies with prior choice, affecting their ability to identify unknowns.

Framework LiLY recovers latent causal variables from time-series data under distribution shifts.

CGDL improves open set recognition by learning conditional Gaussian distributions.

Optimal pricing strategy for unknown valuation models with noisy feedback.

Bayesian method adapts to unknown distribution shifts in online learning.

We give a highly efficient "semi-agnostic" algorithm for learning univariate probability distributions that are well approximated by piecewise polynomial density functions. Let $p$ be an arbitrary distribution over an interval $I$ which is $τ$-close (in total variation distance) to an unknown probability distribution $…

RTSCV detects unknown unknowns to improve model performance.

Paper tackles SMPC for linear systems with unknown noise distribution.

This paper studies clustering of data sequences using the k-medoids algorithm. All the data sequences are assumed to be generated from \emph{unknown} continuous distributions, which form clusters with each cluster containing a composite set of closely located distributions (based on a certain distance metric between di…

Study clusters distributions with known or unknown clusters using distribution testing.

Study uncovers statistical optimality of nonconvex tensor completion methods.

Paper develops PAC-Bayes bounds for unknown linear systems.

Generative adversarial networks sample unknown high-dimensional conditional distributions.

Estimates unknown population sizes using the hypergeometric distribution.

New method for fair resource allocation in AI-aware networks with unknown utility functions.

New trade-off found in bandit problems with unknown range.

Paper presents a method to reduce prediction variance of DNNs for unknown systems.

The paper solves the problem of optimal portfolio choice when the parameters of the asset returns distribution, like the mean vector and the covariance matrix are unknown and have to be estimated by using historical data of the asset returns. The new approach employs the Bayesian posterior predictive distribution which…

Study noisy rewards in online decision-making with unknown distributions.

Study optimal offline RL with uncertainty sets and distribution shifts.

New algorithms estimate parameters of Gaussian and non-Gaussian distributions from truncated samples.

New method splits unknown covariance Gaussians into independent parts.

Develops a robust learning method for unknown context distributions.

We study the quantification of uncertainty of Convolutional Neural Networks (CNNs) based on gradient metrics. Unlike the classical softmax entropy, such metrics gather information from all layers of the CNN. We show for the EMNIST digits data set that for several such metrics we achieve the same meta classification acc…

Nonparametric adaptive robust control tackles model uncertainty in stochastic processes.

In many important machine learning applications, the training distribution used to learn a probabilistic classifier differs from the testing distribution on which the classifier will be used to make predictions. Traditional methods correct the distribution shift by reweighting the training data with the ratio of the de…

We develop efficient algorithms for estimating low-degree moments of unknown distributions in the presence of adversarial outliers. The guarantees of our algorithms improve in many cases significantly over the best previous ones, obtained in recent works of Diakonikolas et al, Lai et al, and Charikar et al. We also sho…

Paper tackles unknown variances in best-arm identification.

Proposes a differentiable hypergeometric distribution for learning group importance.

A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and analyze a distributionally robust stochastic optimization (DRO) framework that lea…

This work investigates the case of a network of agents that attempt to learn some unknown state of the world amongst the finitely many possibilities. At each time step, agents all receive random, independently distributed private signals whose distributions are dependent on the unknown state of the world. However, it m…

Consider a noisy linear observation model with an unknown permutation, based on observing $y = Π^* A x^* + w$, where $x^* \in \mathbb{R}^d$ is an unknown vector, $Π^*$ is an unknown $n \times n$ permutation matrix, and $w \in \mathbb{R}^n$ is additive Gaussian noise. We analyze the problem of permutation recovery in a …

We present a novel family of nonparametric omnibus tests of the hypothesis that two unknown but estimable functions are equal in distribution when applied to the observed data structure. We developed these tests, which represent a generalization of the maximum mean discrepancy tests described in Gretton et al. [2006], …

Study identifies components of unknown interventions in a mixture.

We study statistical detection of grayscale objects in noisy images. The object of interest is of unknown shape and has an unknown intensity, that can be varying over the object and can be negative. No boundary shape constraints are imposed on the object, only a weak bulk condition for the object's interior is required…

Model identifies causal structure from paired observational and interventional data with unknown soft interventions.

New algorithm detects changes quickly without knowing parameters, near optimally.