In this thesis many risk-based asset allocation models are compared, focusing particularly on the Risk Parity strategy. Risk Parity is an allocation method used to build diversified portfolios that does not rely on any assumptions of expected returns, thus placing
Do not waste past computations: Learning and Optimization for Optimal Circle Packing
A simple task: use machine learning in order to avoid useless local searches to be started. Try to find new putative optimal configurations learning from past trials. Skill required: just python – most numerical experiments in circle packing have already been
Cardinality constrained problems: an augmented Lagrangian approach
The aim of this thesis is to apply an Augmented Lagrangian approach to cardinality constrained problems reformulated as standard nonlinear programs with complementarity-type constraints. Applications include portfolio management, signal processing and subset selection problems in regression. Candidate: Tommaso Levato Start
Generalized Nash Equilibrium Problems: a superlinear Trust-Region approach
The aim of this thesis is to obtain a Trust-Region algorithm to solve Generalized Nash Equilibrium Problems (GNEPs). The requested properties of the method are both global and local fast convergence, which have to be achieved under local Error
Semi supervised learning by continuous optimization methods
Training an SVM when many (most) data are unlabeled. This thesis considers an approach based on a continuous differentiable formulation of the problem. Candidate: Andrea Boddi Start: January 2016 Image credits: http://inverseprobability.com/ncnm/
Sii-mobility
Sistema Interoperabile Integrato per la mobilità Web site: https://webgol.dinfo.unifi.it/SiiMobility Kickoff meeting: 19.1.2016 Inizio progetto: 1.1.2016 – Fine progetto: M30 Attività GOL: Algoritmi di ottimizzazione per percorsi multimodali, multi-obiettivo, dinamici. GOL studierà i modelli e gli algoritmi di ottimizzazione più adatti