Skip to main content
Vai all'homepage della Commissione europea (si apre in una nuova finestra)
italiano it
CORDIS - Risultati della ricerca dell’UE
CORDIS

Statistical Optimality and Computational Efficiency: batch and sequential unsupervised learning under additional structure and sampling constraints

Descrizione del progetto

Precisione e velocità nell’IA

L’apprendimento non supervisionato consente all’intelligenza artificiale di scoprire modelli nascosti nei dati senza la guida dell’uomo. A tal fine, cerca modelli nei dati non etichettati, come ad esempio il raggruppamento dei clienti in base alle preferenze. Tuttavia, i metodi attuali richiedono una potenza di calcolo eccessiva. In alcuni casi, piccoli cambiamenti in un modello possono rompere le vecchie ipotesi. Il progetto SOCE, finanziato dal CER, intende affrontare questi limiti. Studierà i compromessi fondamentali tra accuratezza statistica ed efficienza computazionale, in problemi come il raggruppamento robusto e la classificazione. Andando oltre le impostazioni batch, SOCE esaminerà l’apprendimento attivo e sequenziale con vincoli di campionamento. Sviluppando nuovi strumenti matematici e algoritmi, l’obiettivo è chiarire cosa si può e cosa non si può imparare da dati complessi.

Obiettivo

Unsupervised learning is a key problem of artificial intelligence, at the crossroad of statistics and machine learning. The aim is to infer patterns from unlabelled data, by providing learning algorithms that are computationally efficient - i.e. polynomial time - and statistically performant - i.e. minimising an error criterion - and by characterising the fundamental limits for learning.

In the last decade, deep and important phenomena of statistical-computational trade-offs have been unveiled: for some canonical vanilla problems, it is now admitted that no algorithm is both statistically optimal and computationally efficient. However, and somewhat surprisingly, many extensions of these commonly admitted conjectures to other models that present slight variations have been recently proven wrong. The reason is that these model variations give rise to additional structure. This could be a blessing if it can be exploited by a well chosen computationally efficient algorithm, or a curse if it confuses any such algorithm. So that many
fundamental unsupervised learning problems, like robust or hierarchical clustering as well as ordering models like ranking or seriation, are poorly understood.

Beyond this, in modern applications like recommender systems, unsupervised learning is often done in a sequential active way, as a complement to batch learning. Yet, efficient algorithms and the understanding of their limits are also vastly lacking, in particular in the presence of additional structure. And active learning is often done under sampling constraints, which adds a layer of model variations with respect to batch learning.

In SOCE, I will tackle these complex unsupervised learning problems, which are not well understood despite their importance. I will go from batch to active unsupervised learning, and study their interface through sampling constraints. I will develop new mathematical tools and algorithms that will be instrumental for a systematic study of these problems.

Campo scientifico (EuroSciVoc)

Parole chiave

Programma(i)

Argomento(i)

Meccanismo di finanziamento

HORIZON-ERC - HORIZON ERC Grants

Vedi tutti i progetti finanziati nell’ambito di questo schema di finanziamento

Invito a presentare proposte

(si apre in una nuova finestra) ERC-2025-COG

Vedi tutti i progetti finanziati nell’ambito del bando

Istituzione ospitante

UNIVERSITAET POTSDAM
Contributo netto dell'UE
€ 1 979 797,00
Indirizzo
AM NEUEN PALAIS 10
14469 Potsdam
Germania
Regione
Brandenburg Brandenburg Potsdam
Tipo di attività
Higher or Secondary Education Establishments
Collegamenti
Costo totale
€ 1 979 797,00

Beneficiari (1)