Zobrazeno 1 - 10
of 136 669
pro vyhledávání: '"Noisy Data"'
Curriculum learning has been used to improve the quality of text generation systems by ordering the training samples according to a particular schedule in various tasks. In the context of data-to-text generation (DTG), previous studies used various d
Externí odkaz:
http://arxiv.org/abs/2412.13484
Subdivision schemes are iterative processes that recursively refine data by applying subdivision rules. This paper introduces linear subdivision rules tailored to handle noisy data. A key innovation lies in determining the rule coefficients by solvin
Externí odkaz:
http://arxiv.org/abs/2412.01287
Autor:
Shapira, Chen, Rosenbaum, Dan
Models that adapt their predictions based on some given contexts, also known as in-context learning, have become ubiquitous in recent years. We propose to study the behavior of such models when data is contaminated by noise. Towards this goal we use
Externí odkaz:
http://arxiv.org/abs/2411.01670
Autor:
Churina, Svetlana, Jaidka, Kokil
The incivility in social media discourse complicates the deployment of automated text generation models for politically sensitive content. Fine-tuning and prompting strategies are critical, but underexplored, solutions to mitigate toxicity in such co
Externí odkaz:
http://arxiv.org/abs/2411.16813
This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders (SAE), to improve investment strategy performance. Using the Sharpe and Information Ratios, it specifically e
Externí odkaz:
http://arxiv.org/abs/2411.12753
Autor:
Graham-Knight, John Brandon, Fayyad, Jamil, Bayasi, Nourhan, Lasserre, Patricia, Najjaran, Homayoun
Class imbalance and label noise are pervasive in large-scale datasets, yet much of machine learning research assumes well-labeled, balanced data, which rarely reflects real world conditions. Existing approaches typically address either label noise or
Externí odkaz:
http://arxiv.org/abs/2411.02281
Autor:
Fok, Ting Yan, Ye, Nong
A knee point on a curve is the one where the curve levels off after an increase. In a computer system, it marks the point at which the system's performance is no longer improving significantly despite adding extra resources. Thus a knee point often r
Externí odkaz:
http://arxiv.org/abs/2409.15608
In this work, an adaptive predictive control scheme for linear systems with unknown parameters and bounded additive disturbances is proposed. In contrast to related adaptive control approaches that robustly consider the parametric uncertainty, the pr
Externí odkaz:
http://arxiv.org/abs/2409.01955
"Accuracy-on-the-line" is a widely observed phenomenon in machine learning, where a model's accuracy on in-distribution (ID) and out-of-distribution (OOD) data is positively correlated across different hyperparameters and data configurations. But whe
Externí odkaz:
http://arxiv.org/abs/2406.19049
Ensuring high-quality data is paramount for maximizing the performance of machine learning models and business intelligence systems. However, challenges in data quality, including noise in data capture, missing records, limited data production, and c
Externí odkaz:
http://arxiv.org/abs/2405.19210