3 papers
cs.LG2026
Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification
Emil Hardarson, Luka Biedebach, Ómar Bessi Ómarsson +3
Applying machine learning to sensitive time-series data is often bottlenecked by the iteration loop: Performance depends strongly on preprocessing and architecture, yet training of…
cs.LG2025
Chaos into Order: Neural Framework for Expected Value Estimation of Stochastic Partial Differential Equations
Ísak Pétursson, María Óskarsdóttir
Stochastic partial differential equations (SPDEs) describe the evolution of random processes over space and time, but their solutions are often analytically intractable and computa…
q-fin.ST2024
Generalized Distribution Prediction for Asset Returns
Ísak Pétursson, María Óskarsdóttir
We present a novel approach for predicting the distribution of asset returns using a quantile-based method with Long Short-Term Memory (LSTM) networks. Our model is designed in two…