arXiv research

Estimates proportions of LLM-generated text in mixed documents.

New learning rules achieve optimal sample complexity for weakly supervised classification.

Study on estimating Gumbel--Max watermark proportions in edited documents.

We propose an adaptive sampling approach for multiple testing which aims to maximize statistical power while ensuring anytime false discovery control. We consider $n$ distributions whose means are partitioned by whether they are below or equal to a baseline (nulls), versus above the baseline (actual positives). In addi…

Positive-Unlabeled (PU) learning is an analog to supervised binary classification for the case when only the positive sample is clean, while the negative sample is contaminated with latent instances of positive class and hence can be considered as an unlabeled mixture. The objectives are to classify the unlabeled sampl…

Resampling outperforms reweighting for correcting biased data in machine learning models.

Optimal tuning for estimating ECC in proportional asymptotics.

Aioli unifies language model data mixing methods and improves performance.

DSDE improves OoD detection by estimating model library proportions.

The paper provides high-probability bounds on false discovery proportions in conformal inference.

This work introduces a new sampling method to approximate an optimal design problem in ridge regression.

We study the optimal design problems where the goal is to choose a set of linear measurements to obtain the most accurate estimate of an unknown vector in $d$ dimensions. We study the $A$-optimal design variant where the objective is to minimize the average variance of the error in the maximum likelihood estimate of th…

Study ridge ensembles in proportional feature-to-sample size regime, proving risk equivalence and GCV consistency.

Learning from Label Proportions (LLP) is a learning setting, where the training data is provided in groups, or "bags", and only the proportion of each class in each bag is known. The task is to learn a model to predict the class labels of the individual instances. LLP has broad applications in political science, market…

We study binary classification in the setting where the learner is presented with multiple corrupted training samples, with possibly different sample sizes and degrees of corruption, and introduce an approach based on minimizing a weighted combination of corruption-corrected empirical risks. We establish a generalizati…

New framework for weakly supervised learning from label proportions.

This work efficiently learns linear threshold functions from label proportions using Gaussian distributions.

The paper explores learning from label proportions, showing differences in efficiency between LLP and PAC learning.

Mixture proportion estimation (MPE) is the problem of estimating the weight of a component distribution in a mixture, given samples from the mixture and component. This problem constitutes a key part in many "weakly supervised learning" problems like learning with positive and unlabelled samples, learning with label no…

Given $n$ samples from a population of individuals belonging to different types with unknown proportions, how do we estimate the probability of discovering a new type at the $(n+1)$-th draw? This is a classical problem in statistics, commonly referred to as the missing mass estimation problem. Recent results by Ohannes…

Positive--unlabeled (PU) learning considers two samples, a positive set P with observations from only one class and an unlabeled set U with observations from two classes. The goal is to classify observations in U. Class mixture proportion estimation (MPE) in U is a key step in PU learning. Blanchard et al. [2010] showe…

ETM models improve efficiency in semi-supervised logistic regression.

New research shows fixed-budget best-arm identification cannot match static oracle performance.

Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by investigating the dimensionality of the deep representation subspace of training samples. …

Optimal best-arm identification in linear bandits reduces sampling budget.

In this paper, we consider the problem of column subset selection. We present a novel analysis of the spectral norm reconstruction for a simple randomized algorithm and establish a new bound that depends explicitly on the sampling probabilities. The sampling dependent error bound (i) allows us to better understand the …

Paper develops methods for estimating GLMs and SNR under proportional asymptotics.

A censored transformed model for proportional outcomes with boundary mass and an application to loss given default modeling.

To better understand the interplay of censoring and sparsity we develop finite sample properties of nonparametric Cox proportional hazard's model. Due to high impact of sequencing data, carrying genetic information of each individual, we work with over-parametrized problem and propose general class of group penalties s…

Enhanced metrics improve generative model evaluation reliability.

This article studies the achievable guarantees on the error rates of certain learning algorithms, with particular focus on refining logarithmic factors. Many of the results are based on a general technique for obtaining bounds on the error rates of sample-consistent classifiers with monotonic error regions, in the real…

OP-GFNs sample candidates in order-preserving proportion to a learned reward function.

In dynamic topic modeling, the proportional contribution of a topic to a document depends on the temporal dynamics of that topic's overall prevalence in the corpus. We extend the Dynamic Topic Model of Blei and Lafferty (2006) by explicitly modeling document level topic proportions with covariates and dynamic structure…

The problem of developing binary classifiers from positive and unlabeled data is often encountered in machine learning. A common requirement in this setting is to approximate posterior probabilities of positive and negative classes for a previously unseen data point. This problem can be decomposed into two steps: (i) t…

New approach predicts generalization of deep neural networks in proportional-width regime.

A new algorithm reconstructs population dynamics from coarse samples.

New method for cross-validation in high-dimensional data with dependent or heavy-tailed covariates.

Enhances topic-metadata relationship modeling using Bayesian methods.

The paper analyzes data augmentation for precision matrix estimation in high dimensions.

New research shows that binary classification can be done with noisy data, but only if there are clean samples available.

New MCMC method samples from lattice distributions efficiently.

We study the top-$K$ ranking problem where the goal is to recover the set of top-$K$ ranked items out of a large collection of items based on partially revealed preferences. We consider an adversarial crowdsourced setting where there are two population sets, and pairwise comparison samples drawn from one of the populat…

New linear denoiser outperforms standard Wiener filter in noisy data.

We propose a sampling scheme suitable for reducing a data set prior to selecting a hypothesis with minimum empirical risk. The sampling only considers a subset of the ultimate (unknown) hypothesis set, but can nonetheless guarantee that the final excess risk will compare favorably with utilizing the entire original dat…

This work tackles robust multi-source domain adaptation under label shift.

ALO-CV approximates leave-one-out error in proportional regime.

A method for logistic regression inference using both internal and external data.

New algorithm samples matrix rows proportional to their ℓ_p norm in a turnstile data stream.