Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

The University of British Columbia

$55,000.00

Algorithms in randomization, optimization, learning, and privacy

FY 2024-25

Summary
Many sciences and industries have been transformed by the technologies by which computers learn from data. These technologies are used to generate computational models of the world, and to make predictions about future data. To make these technologies as efficient and ethical as possible, it is crucial that computer scientists design them to be computationally efficient, to make effective use of available data, and to be privacy preserving. The long-term objective of this proposal is to create novel technologies for major algorithmic tasks on the pipeline of machine learning, to improve their efficiency and privacy, and to enable their use in numerous application domains. The projects in this proposal are centered on providing trainees with a range of theoretical skills. To ensure that the algorithms of this proposal have impact on the numerous applied domains of machine learning, the development of software implementations is one of its objectives. My recent research with trainees and collaborators has achieved breakthrough results in the design of statistical experiments, developed significant advances in adaptive preconditioning methods in continuous optimization, and proven optimal theoretical bounds on the efficiency of stochastic gradient descent. My recent results and long experience in this area have given me a broad perspective on the current state of research of these problems. To advance this long-term objective, the proposal outlines specific short-term goals, targeted towards student training. I propose specific improvements to our experimental designs, to our optimization methods, and to our online learning algorithms. I also propose outline research goals on fundamental questions about machine learning while ensuring privacy. Through these targeted projects, we will develop new technologies for machine learning and provide trainees with skills that are highly valued in the information technology industry.
Program
Discovery Grants Program - Individual
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2024-06366
Name nom
Harvey, Nicholas
Department département
Computer Science - Computer Science
Organization id
2
Institution établissement
The University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
55000
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
1205
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Mathematical sciences
Area of application fr
Sciences mathématiques
Research subject code
2713
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Algorithms
Research subject fr
Algorithmes
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
Algorithms in randomization, optimization, learning, and privacy
Keywords
algorithms; randomization; optimization; learning theory; differential privacy
Application summary
Many sciences and industries have been transformed by the technologies by which computers learn from data. These technologies are used to generate computational models of the world, and to make predictions about future data. To make these technologies as efficient and ethical as possible, it is crucial that computer scientists design them to be computationally efficient, to make effective use of available data, and to be privacy preserving. The long-term objective of this proposal is to create novel technologies for major algorithmic tasks on the pipeline of machine learning, to improve their efficiency and privacy, and to enable their use in numerous application domains. The projects in this proposal are centered on providing trainees with a range of theoretical skills. To ensure that the algorithms of this proposal have impact on the numerous applied domains of machine learning, the development of software implementations is one of its objectives. My recent research with trainees and collaborators has achieved breakthrough results in the design of statistical experiments, developed significant advances in adaptive preconditioning methods in continuous optimization, and proven optimal theoretical bounds on the efficiency of stochastic gradient descent. My recent results and long experience in this area have given me a broad perspective on the current state of research of these problems. To advance this long-term objective, the proposal outlines specific short-term goals, targeted towards student training. I propose specific improvements to our experimental designs, to our optimization methods, and to our online learning algorithms. I also propose outline research goals on fundamental questions about machine learning while ensuring privacy. Through these targeted projects, we will develop new technologies for machine learning and provide trainees with skills that are highly valued in the information technology industry.