A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
INN method refines clean labeled data from noisy labels.
AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing
Data augmentation has been widely applied as an effective methodology to improve generalization in particular when training deep neural networks. Recently, researchers proposed a few intensive data augmentation techniques, which indeed improved accuracy, yet we notice that these methods augment data have also caused a …
Label aggregation makes learning robust to noisy labels.
Neural networks learn clean data patterns first, then noisy data, leading to improved performance initially but deteriorating later.
IterefinE combines KG refinement with embeddings to improve KG quality.
PClean automates Bayesian data cleaning for specific datasets.
R package tsrobprep cleans and prepares time series data robustly.
The graph-based semi-supervised label propagation algorithm has delivered impressive classification results. However, the estimated soft labels typically contain mixed signs and noise, which cause inaccurate predictions due to the lack of suitable constraints. Moreover, available methods typically calculate the weights…
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using…
Adversarial training leads to clean data generalization with significant robust overfitting gap.
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervis…
Study improves resilience against adversarial clean-label attacks in real and noisy settings.
Self-supervised method predicts clean signal and noise distribution from noisy images.
SSMs can be poisoned with clean labels, leading to generalization failure.
Cincer cleans both new and past data by identifying and relabeling suspicious and counter-examples.
Enhances deep learning robustness to noise without sacrificing clean data accuracy.
In this paper, we propose a refined multi-stage multi-task training strategy to improve the performance of online attention-based encoder-decoder (AED) models. A three-stage training based on three levels of architectural granularity namely, character encoder, byte pair encoding (BPE) based encoder, and attention decod…
The US Census Bureau corrupts data to protect privacy, but we show how to clean and analyze it effectively.
New method generates clean data from corrupted observations.
CLSVAE repairs systematic errors in images with minimal labeled data.
Image classification problems are typically addressed by first collecting examples with candidate labels, second cleaning the candidate labels manually, and third training a deep neural network on the clean examples. The manual labeling step is often the most expensive one as it requires workers to label millions of im…
Study proposes a clustering and logistic regression algorithm for PU classification under Non-SCAR.
TS-Fault benchmarks TSF models against structural faults.
New method improves false-/true-positive-rate estimation in fraud detection with noisy labels.
Game theory helps machine learn better from adversarial queries.
Efficient method for training deep learning models with human validation and statistical analysis.
Method cleans noisy training labels for biomedical data.
Data quality issues have attracted widespread attention due to the negative impacts of dirty data on data mining and machine learning results. The relationship between data quality and the accuracy of results could be applied on the selection of the appropriate algorithm with the consideration of data quality and the d…
The paper cleans label noise in supervised classification using Bernoulli sampling.
MetaPoison poisons neural networks by learning to craft imperceptible changes to training data.
The report presents the theory of harmonic maps from Kähler manifolds.
Improved language models using ratio-matching and KL divergence.
Historical (Stressed-) Value-at-Risk ((S)VAR), and Expected Shortfall (ES), are widely used risk measures in regulatory capital and Initial Margin, i.e. funding, computations. However, whilst the definitions of VAR and ES are unambiguous, they depend on input distributions that are data-cleaning- and Data-Model-depende…
EntProp increases entropy of clean samples to generate out-of-distribution data for better DNN performance.
Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model, so the model behaves according to the adversary's objective if the input contain…
In unsupervised domain adaptation (UDA), classifiers for the target domain (TD) are trained with clean labeled data from the source domain (SD) and unlabeled data from TD. However, in the wild, it is difficult to acquire a large amount of perfectly clean labeled data in SD given limited budget. Hence, we consider a new…
Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural networks (DNNs) by inserting a backdoor pattern in the training images. The resulting…
New method tackles label noise on imbalanced datasets by considering class-specific uncertainty.
New method denoises and fills in missing image data without clean training data.
It is known that evaluating a certain approximation to the Jones polynomial for the plat closure of a braid is a BQP-complete problem. That is, this problem exactly captures the power of the quantum circuit model. The one clean qubit model is a model of quantum computation in which all but one qubit starts in the maxim…
PrIU optimizes machine learning model updates after data cleaning.
When considering answering important questions with data, unsupervised data offers extensive insight opportunity and unique challenges. This study considers student survey data with a specific goal of clustering students into like groups with underlying concept of identifying different poverty levels. Fuzzy logic is co…
Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the most popular robust training method in the literature, adversarial training: Advers…
A new algorithm reduces imbalanced data classification errors in multi-class settings.
Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks that succeed without access to the victim network's outputs, architecture, or (i…
Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have led to improved accuracy, building robust models remains challenging. Prior work has argued that there is an inherent trade-off between robu…
Paper cleans option price datasets by removing outliers.