Hugging Face Trending Papers
Beyond Wasserstein Proximity: Finding Better Transfer Sources
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Statistics ML
Oct 27
Beyond Wasserstein Proximity: Finding Better Transfer Sources
arXiv:2610.35314v1 Announce Type: new Abstract: Source selection often favors similar data, yet marginal proximity need not identify the most useful pretraining source. We motivate a conditional alte...
Hugging Face Trending Papers
Jun 22
Selective Time Series Forecasting via Metalearning
Deep learning methods have achieved state-of-the-art in time series forecasting, yet their accuracy varies considerably across samples, as some instances remain inherently difficult to predict. Reject option mechanisms, which allow models to abstain from high-risk predictions, are well established in classification and regression but underexplored in forecasting.
arXiv AI
Sep 24
Loss Choice or Model Choice? The Role of Forecast Level in Cryptocurrency Volatility Forecasting
The paper investigates how the choice of loss function versus the choice of forecasting model affects cryptocurrency volatility predictions. By comparing seven loss functions and five models, and aligning forecast levels before evaluation, the study finds that after level adjustment model choice dominates performance differences, while loss-induced variations largely disappear. The work clarifies that apparent loss effects in raw comparisons are largely due to forecast level differences rather than intrinsic model performance.
arXiv Machine Learning
4d ago
A Controlled Comparison of Deep Learning Architectures for Multi-Horizon Financial Forecasting: Evidence from 918 Experiments
The paper presents a controlled benchmark of nine deep‑learning architectures for multi‑horizon financial forecasting, using 918 runs across 12 assets and two forecast horizons. It employs a five‑stage evaluation pipeline that isolates architectural effects from hyperparameter tuning, random seeds, and asset characteristics. Results show ModernTCN and PatchTST consistently outperform others, with ModernTCN achieving the lowest RMSE in 75% of asset‑horizon points and a statistically significant global ranking advantage.
arXiv AI
Oct 21
Parameter-Efficient Adaptation of Time Series Foundation Models for Electrical Load Forecasting
The study evaluates how well time‑series foundation models (TSFMs) can be adapted for electrical load forecasting. It compares pretrained inference, full fine‑tuning, and low‑rank adaptation (LoRA) across four load aggregation levels, using MOIRAI 1.0 Large as the main backbone and Chronos‑2 as a secondary model. LoRA achieves a 7.5% average NMAE reduction on MOIRAI while updating only about 1% of the parameters, offering a strong accuracy‑efficiency trade‑off, though benefits vary in out‑of‑distribution scenarios.
Hugging Face Trending Papers
Oct 25
MetaARIMA: Configuration-Level Transfer Learning for ARIMA Models
Time Series Foundation Models have demonstrated that pretraining on diverse datasets enables effective transfer to new forecasting tasks. Classical methods like ARIMA, however, remain configured and t...