arXiv research

New algorithm reduces online learning regret for bounded recall games.

Framework for precise recall control in spatial conflation tasks.

LLMs can memorize economic data and recall exact values before their training cutoff.

Transformers recall from long distributions with statistical guarantees.

New method estimates model performance bounds without ground truth labels.

This paper introduces a new method to train normalizing flows using precision-recall divergences.

We introduce a technique to compute probably approximately correct (PAC) bounds on precision and recall for matching algorithms. The bounds require some verified matches, but those matches may be used to develop the algorithms. The bounds can be applied to network reconciliation or entity resolution algorithms, which i…

For an ancient solution of the mean curvature flow, we show that each time slice M_t is contained in an affine subspace with dimension bounded in terms of the density and the dimension of the evolving submanifold. Recall that an ancient solution is a family M_t that evolves under mean curvature flow for all negative ti…

The study examines how class imbalance affects precision-recall curves.

The study formalizes temporal precision and recall for anomaly detection in sequences.

Transformers learn to recall with non-orthogonal embeddings in realistic settings.

For information retrieval and binary classification, we show that precision at the top (or precision at k) and recall at the top (or recall at k) are maximised by thresholding the posterior probability of the positive class. This finding is a consequence of a result on constrained minimisation of the cost-sensitive exp…

Unified and extended precision-recall metrics for generative models.

Transformers can store facts efficiently using associative memories.

Recalls intrinsically harmonic forms and open problems.

Paper tackles imbalanced binary classification by optimizing precision and recall directly.

In this article we revisit the definition of Precision-Recall (PR) curves for generative models proposed by Sajjadi et al. (arXiv:1806.00035). Rather than providing a scalar for generative quality, PR curves distinguish mode-collapse (poor recall) and bad quality (poor precision). We first generalize their formulation …

Proposes a method to evaluate classifiers with missing labels using multiple imputation.

RAGuard improves safety in LLMs for offshore wind maintenance.

Paper proposes a human-algorithm approach to reduce medical device recall risk and workload.

A new method for generating replay samples on the fly, optimizing for not forgetting.

Proposes a new tree-based algorithm for class-imbalanced data.

We prove curvature-free versions of the celebrated Margulis Lemma. We are interested by both the algebraic aspects and the geometric ones, with however an emphasis on the second and we aim at giving quantitative (computable) estimates of some important invariants. Our goal is to get rid of the pointwise curvature assum…

Algorithm learns NE in imperfect information games with imperfect feedback.

The paper critiques and expands on common evaluation metrics in machine learning.

Study certifies missed relevant items in candidate generation with audit labels.

New findings show tool-augmented models can recall unlimited facts, outperforming purely memorized models.

Modern retrieval systems are often driven by an underlying machine learning model. The goal of such systems is to identify and possibly rank the few most relevant items for a given query or context. Thus, such systems are typically evaluated using a ranking-based performance metric such as the area under the precision-…

The optimal ranking score between precision and recall is rarely F1 and can be found using specific methods.

Recalls and refines the concept of algebraically rectifiable curves.

Recall that Federer-Fleming defined the notion of flat convergence of submanifolds of Euclidean space to solve the Plateau problem. Here we prove the upper semicontinuity of Neumann eigenvalues of the submanifolds when they converge in the flat sense without losing volume. With an additional condition on the boundaries…

Improved algorithm reduces excess risk in selective learning.

DIAL learns embeddings to maximize recall and accuracy for entity resolution.

Improves interpretability of neural network intermediate layers by making concept activations more robust and effective.

Short sales are regarded as negative purchases in textbook asset pricing theory. In reality, however, the symmetry between purchases and short sales is broken by a variety of costs and risks peculiar to the latter. We formulate an optimal stopping model in which the decision to cover a short position is affected by two…

Mobile app improves speech recognition of names with user feedback.

Despite the tremendous progress in the estimation of generative models, the development of tools for diagnosing their failures and assessing their performance has advanced at a much slower pace. Recent developments have investigated metrics that quantify which parts of the true distribution is modeled well, and, on the…

The random cluster model is used to define an upper bound on a distance measure as a function of the number of data points to be classified and the expected value of the number of classes to form in a hybrid K-means and regression classification methodology, with the intent of detecting anomalies. Conditions are given …

Enhanced anomaly detection using PRC-RF with autoencoders.

LLMs can be tricked into recalling facts based on context clues.

The paper analyzes the generalizability of linear autoencoders and multivariate linear regression.

Evaluation often aims to reduce the correctness or error characteristics of a system down to a single number, but that always involves trade-offs. Another way of dealing with this is to quote two numbers, such as Recall and Precision, or Sensitivity and Specificity. But it can also be useful to see more than this, and …

Although a great methodological effort has been invested in proposing competitive solutions to the class-imbalance problem, little effort has been made in pursuing a theoretical understanding of this matter. In order to shed some light on this topic, we perform, through a novel framework, an exhaustive analysis of the …

Unified framework for sequence models using test-time regression.

In this second part of a series of papers on the long-time behavior of Ricci flows with surgery, we establish a bound on the evolution of the infimal area of simplicial complexes inside a 3-manifold under the Ricci flow. This estimate generalizes an area estimate of Hamilton, which we will recall in the first part of t…

New method detects novel node categories in graphs with distribution shifts.

KATA improves associative recall by optimizing feature maps derived from nonnegative attention weights.

New metrics improve reliability of image generation evaluation.