EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
2281. ML-based Adaptive Risk Parameters Tuning for Robust Optimization
Invited abstract in session TB-35: Risk Averse and Contextual Stochastic Optimization, stream Stochastic, Robust and Distributionally Robust Optimization.
Tuesday, 10:30-12:00Room: 44 (building: 303A)
Authors (first author is the speaker)
| 1. | Emanuele Pizzari
|
| Istituto di analisi dei sistemi ed informatica "Antonio Ruberti" (IASI), Consiglio Nazionale delle Ricerche (CNR) | |
| 2. | Marco Boresta
|
| Istituto di analisi dei sistemi ed informatica "Antonio Ruberti" (IASI), Consiglio Nazionale delle Ricerche (CNR) | |
| 3. | Diego Maria Pinto
|
| Istituto di Analisi dei Sistemi ed Informatica "Antonio Ruberti", Consiglio Nazionale delle Ricerche |
Abstract
This paper introduces a novel approach that integrates Robust Optimization with Machine Learning (ML) to dynamically estimate optimal risk parameter' values for uncertain environments. By leveraging historical data and engineering informative features, we train an ML model to predict risk protection values tailored to each instance's characteristics. Unlike static approaches, our method offers adaptability and enhances decision-making in uncertain domains. Through experimentation, we demonstrate the efficacy of our approach in improving robustness and performance.
Keywords
- Robust Optimization
- Machine Learning
- Risk Analysis and Management
Status: accepted
Back to the list of papers