Prof. Christina Fragouli, Electrical and Computer Engineering Department at UCLA, to speak at ECE-NTUA on October 15, 2024 at 13:00
Το Ελληνικό Παράρτημα Υπολογιστικής Νοημοσύνης του διεθνούς Ινστιτούτου Ηλεκτρολόγων και Ηλεκτρονικών Μηχανικών (ΙΕΕΕ) και το Εργαστήριο Συστημάτων Τεχνητής Νοημοσύνης και Μάθησης (AILS Lab) της Σχολής Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών του Εθνικού Μετσόβιου Πολυτεχνείου σας προσκαλούν στη διάλεξη της Prof. Christina Fragouli, IEEE Fellow, Department of Electrical & Computer Engineering, University of California, Los Angeles, USA.
με θέμα: “Solving Stochastic Contextual Bandits with Linear Bandits Algorithms”
Η εκδήλωση θα πραγματοποιηθεί την Τρίτη 15 Οκτωβρίου 2024 στις 13:00, στην Αίθουσα Συνεδριάσεων της Σχολής Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών, Νέα Κτήρια, Πολυτεχνειούπολη Ζωγράφου.
Η διάλεξη θα δοθεί στα αγγλικά.
Abstract: Linear bandit and contextual linear bandit problems have recently attracted extensive attention as they enable to support impactful active learning applications through elegant formulations. In linear bandits, a learner at each round plays an action from a fixed action space and receives a reward that is specified by the inner product of the action and an unknown parameter vector plus noise. Contextual linear bandits add another layer of complexity by enabling at each round the action space to be different, to capture context. The goal is to design an algorithm that learns to play as close as possible to the unknown optimal policy after a number of action plays. The contextual problem is considered more challenging than the linear bandit problem, which can be viewed as a contextual bandit problem with a fixed context. Surprisingly, in this talk, we show that the stochastic contextual problem can be solved as if it is a linear bandit problem. In particular, we establish a novel reduction framework that converts every stochastic contextual linear bandit instance to a linear bandit instance. Our reduction framework opens up a new way to approach stochastic contextual linear bandit problems, and enables significant savings in communication cost in distributed setups. Furthermore, it yields improved regret bounds in a number of instances. This talk is based on joint work with Osama Hanna and Lin Yang.
Short CV: Christina Fragouli is a Professor in the Electrical and Computer Engineering Department at UCLA. She received the B.S. degree in Electrical Engineering from the National Technical University of Athens, Athens, Greece, and the M.Sc. and Ph.D. degrees in Electrical Engineering from the University of California, Los Angeles. She has worked at the Information Sciences Center, AT\&T Labs, Florham Park New Jersey, and also visited Bell Laboratories, Murray Hill, NJ, and DIMACS, Rutgers University. Between 2006--2015 she was an Assistant and Associate Professor in the School of Computer and Communication Sciences, EPFL, Switzerland. She is an IEEE fellow, she served as the 2022 President of the IEEE Information Theory Society (currently serving as Senior Past President), and has served in several IEEE-wide and Information Theory Society Committees as member or Chair. She has also served as TPC Chair in several conferences including the IEEE Information Theory Symposium in 20204, as an Information Theory Society Distinguished Lecturer, and as an Associate Editor for IEEE Communications Letters, for Elsevier Journal on Computer Communication, for IEEE Transactions on Communications, for IEEE Transactions on Information Theory, and for IEEE Transactions on Mobile Communications. She has received numerous awards including the Okawa Foundation Award, the European Research Council (ERC) Starting Investigator Grant, and the Zonta Price. Her research interests are in the intersection of coding techniques, machine learning and information theory, with a wide range of applications that include network information flow, network security and privacy, compression, wireless networks and bioinformatics.