This thesis covers some algorithmic aspects of online machine learning and optimization. In Chapter 1 we design algorithms with state-of-the-art regret guarantees for the problem dynamic pricing. In Chapter 2 we move on to an asynchronous online learning setting in which only some of the agents in the network are active at each time step. We show that when information is shared among neighbors, knowledge about the graph structure might have a significantly different impact on learning rates depending on how agents are activated. In Chapter 3 we investigate the online problem of multivariate non-concave maximization under weak assumptions on the regularity of the objective function. In Chapter 4 we introduce a new performance measure and design an efficient algorithm to learn optimal policies in repeated A/B testing.

ALGORITHMS, LEARNING, AND OPTIMIZATION / T.r. Cesari ; supervisor: N. A. CESA BIANCHI ; phd coordinator: P. Boldi. DIPARTIMENTO DI INFORMATICA "Giovanni Degli Antoni", 2020 Jan 31. 32. ciclo, Anno Accademico 2019. [10.13130/cesari-tommaso-renato_phd2020-01-31].

ALGORITHMS, LEARNING, AND OPTIMIZATION

T.R. Cesari
2020

Abstract

This thesis covers some algorithmic aspects of online machine learning and optimization. In Chapter 1 we design algorithms with state-of-the-art regret guarantees for the problem dynamic pricing. In Chapter 2 we move on to an asynchronous online learning setting in which only some of the agents in the network are active at each time step. We show that when information is shared among neighbors, knowledge about the graph structure might have a significantly different impact on learning rates depending on how agents are activated. In Chapter 3 we investigate the online problem of multivariate non-concave maximization under weak assumptions on the regularity of the objective function. In Chapter 4 we introduce a new performance measure and design an efficient algorithm to learn optimal policies in repeated A/B testing.
31-gen-2020
Settore INF/01 - Informatica
machine learning theory; online learning; online optimization; cooperative learning; dynamic pricing; posted price
CESA BIANCHI, NICOLO' ANTONIO
CESA BIANCHI, NICOLO' ANTONIO
BOLDI, PAOLO
Doctoral Thesis
ALGORITHMS, LEARNING, AND OPTIMIZATION / T.r. Cesari ; supervisor: N. A. CESA BIANCHI ; phd coordinator: P. Boldi. DIPARTIMENTO DI INFORMATICA "Giovanni Degli Antoni", 2020 Jan 31. 32. ciclo, Anno Accademico 2019. [10.13130/cesari-tommaso-renato_phd2020-01-31].
File in questo prodotto:
File Dimensione Formato  
phd_unimi_R11657.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Tesi di dottorato completa
Dimensione 1.11 MB
Formato Adobe PDF
1.11 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/699354
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact