arXiv research

Modeling coating degradation with fewer data points.

Paper uses deep learning to model systems with degrading behavior.

Statistical test detects model degradations in optimized language models.

BNCR-GAN improves GANs to generate clean images from degraded inputs.

Paper uses neural networks to predict NOx emissions from gas turbines.

Framework optimizes battery storage for markets by separating long-term degradation from short-term market dynamics.

Paper develops a hybrid DNN approach for RUL prediction with adaptive drift.

The paper proposes a method to detect relevant model degradations without over-alerting.

Paper proposes a new regularization method to prevent model degradation under distribution shifts.

Measures DNA quality degradation effects.

Deep learning predicts RNA degradation from crowdsourced data.

Diffusion models struggle in high dimensions due to objective function degradation.

Study investigates how errors in reinsurance parameters degrade optimal solutions.

This research improves asset life prediction by integrating deep learning with mixture distributions.

An adversarial process between two deep neural networks is a promising approach to train a robust model. In this paper, we propose an adversarial process using cosine similarity, whereas conventional adversarial processes are based on inverted categorical cross entropy (CCE). When used for training an identification mo…

Proposes a federated learning approach for RUL prediction from nonparametric degradation and failure signals.

Paper presents a probabilistic diagnostic model for identifying and treating supervised learning degradation issues.

A method for inferring ground-truth signals from degraded sensor data.

In industrial applications, nearly half the failures of motors are caused by the degradation of rolling element bearings (REBs). Therefore, accurately estimating the remaining useful life (RUL) for REBs are of crucial importance to ensure the reliability and safety of mechanical systems. To tackle this challenge, model…

This paper improves federated learning for industrial predictive analytics by accommodating client heterogeneity.

Paper predicts bearing degradation stages for pharmaceutical industry maintenance.

The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. Current Video Super-Resolution methods are not robust to mismatch between training and testing degradation models since they are trained against a single…

Sparse Transformers degrade semantic information first, with early layers encoding more.

Analyzes layer-wise quantization effects in neural networks.

Study investigates how machine learning models degrade over time, leading to patient safety issues.

CRC improves multivariate forecasting accuracy without risking performance degradation.

Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity. However, this is difficult because an imperfect dynamics model can degrade the performance of the learning algorithm, and in sufficiently com…

Study optimizes HTL-free PSCs with MWCNTs, improving efficiency and stability.

Improved diffusion sampling for inverse problems with faster and more robust inference.

Theoretical study explains why federated optimization fails to achieve perfect fitting.

This work is attached to the BRICS 2013 competition. We propose a two-stage model for dealing with the temporal degradation of credit scoring models. This methodology produced motivating results in a 1-year horizon. We anticipate that it can be extended to other applications of risk assessment with great success. Futur…

Improved image restoration using frequency-guided sampling.

This work examines how adversarial robustness regularization affects neural network performance.

Develops new bounds for deterministic samplers in diffusion models.

Risk monitoring detects when TTA models degrade at test time.

Smaller actor-critic models lead to performance degradation and overfitting, highlighting the critic's role in value underestimation.

Improves performance of deep GCNs by controlling node feature variance.

Self-supervised method enhances ultrasound images without needing clean targets.

The paper proposes using entropy to assess model confidence.

FIRE method improves model performance in federated learning by penalizing fragmentation-induced covariate shifts.

In this work, we ask two questions: 1. Can we predict the type of community interested in a news article using only features from the article content? and 2. How well do these models generalize over time? To answer these questions, we compute well-studied content-based features on over 60K news articles from 4 communit…

Theoretical framework for neural network compression using sparsity norms.

Study shows integrating acoustic features in financial forecasting models can degrade performance.

Suitability filter detects model performance degradation in real-world deployment.

Paper improves ETF tail-risk monitoring reliability.

SR-NAM maps low-res images to multiple high-res images realistically.

The paper analyzes how synthetic data training degrades diffusion models, providing bounds and characterizing different drift regimes.

Neural network predicts electrochemical cell faults with 53% less error.