Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

Université Laval

$29,000.00

PAC-Bayesian transfer learning: theory and algorithms

EF 2024-25

Résumé
The PAC-Bayesian theory, initiated by David McAllester (1999), is a statistical approach to machine learning. It provides guarantees on predictor accuracy, expressed by probabilistic upper bounds on the generalization error. The main assumption of the classical PAC-Bayesian results is that the observed training set contains independently and identically distributed (iid) observations generated by a (fixed and unknown) data distribution, and that the learned predictor is to be used on observations generated by the very same data distribution. This assumption does not hold for many real-life machine learning tasks, as the data distribution is prone to evolve with time and environment. To avoid retraining a machine learning from scratch for every new data distribution - which requires a proper training set for the new task(s) - several transfer learning methods have been developed. The transfer learning framework encompasses all methods reusing the "knowledge" learned by solving a first task in order to solve a second task (different but related to the first one). In a favorable context, only few training observations might be necessary to adapt the predictor to the new task. Note that there exist several transfer learning approaches, according to the problem characteristics: domain adaptation, multitask learning, meta-learning, etc. A framework of interest is the representation learning one, which has been popularized by the recent deep neural networks advances. This research proposal focuses on leveraging the PAC-Bayesian theory to study a variety of transfer learning approaches, divided into two main research axes. A fist axis will be to study the unsupervised representation learning framework into the PAC-Bayesian paradigm. A promising research direction is the rigorous theoretical formalization of "contrastive" representation learning proposed recently by Arora et al. (2019). It gives a solid basis from which one can mathematically study the problem at hand. The resulting analysis will be used for learning representation with neural networks, but also other methods as kernel ones. A second axis will be to build on the domain adaptation algorithm of Germain et al. (2016), named DALC. Although efficient on small datasets, this algorithm, as other classical kernel methods, cannot be used on large datasets due to its algorithmic complexity. A well-known method to accelerate kernel methods is the approximation by random Fourier features (Rahimi and Recht, 2007), that we revisited from a PAC-Bayesian perspective (Letarte et al., 2019). Another strategy will be to develop a PAC-Bayesian optimal transport approach to domain adaptation.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2020-07223
Name nom
Germain, Pascal
Department département
Département d'informatique et de génie logiciel
Organization id
51
Institution établissement
Université Laval
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2020
Award amount
29000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2805
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Learning and inference theories
Research subject fr
Théories de l'apprentissage et l'inférence
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
PAC-Bayesian transfer learning: theory and algorithms
Keywords
machine learning; statistical learning; transfer learning; representation learning; domain adaptation; neural networks; kernel methods; pac-bayesian theory
Application summary
The PAC-Bayesian theory, initiated by David McAllester (1999), is a statistical approach to machine learning. It provides guarantees on predictor accuracy, expressed by probabilistic upper bounds on the generalization error. The main assumption of the classical PAC-Bayesian results is that the observed training set contains independently and identically distributed (iid) observations generated by a (fixed and unknown) data distribution, and that the learned predictor is to be used on observations generated by the very same data distribution. This assumption does not hold for many real-life machine learning tasks, as the data distribution is prone to evolve with time and environment. To avoid retraining a machine learning from scratch for every new data distribution - which requires a proper training set for the new task(s) - several transfer learning methods have been developed. The transfer learning framework encompasses all methods reusing the "knowledge" learned by solving a first task in order to solve a second task (different but related to the first one). In a favorable context, only few training observations might be necessary to adapt the predictor to the new task. Note that there exist several transfer learning approaches, according to the problem characteristics: domain adaptation, multitask learning, meta-learning, etc. A framework of interest is the representation learning one, which has been popularized by the recent deep neural networks advances. This research proposal focuses on leveraging the PAC-Bayesian theory to study a variety of transfer learning approaches, divided into two main research axes. A fist axis will be to study the unsupervised representation learning framework into the PAC-Bayesian paradigm. A promising research direction is the rigorous theoretical formalization of "contrastive" representation learning proposed recently by Arora et al. (2019). It gives a solid basis from which one can mathematically study the problem at hand. The resulting analysis will be used for learning representation with neural networks, but also other methods as kernel ones. A second axis will be to build on the domain adaptation algorithm of Germain et al. (2016), named DALC. Although efficient on small datasets, this algorithm, as other classical kernel methods, cannot be used on large datasets due to its algorithmic complexity. A well-known method to accelerate kernel methods is the approximation by random Fourier features (Rahimi and Recht, 2007), that we revisited from a PAC-Bayesian perspective (Letarte et al., 2019). Another strategy will be to develop a PAC-Bayesian optimal transport approach to domain adaptation.