I completed my master’s degree in Mathematics from the National University of Singapore, during which time I gradually moved away from number theory and algebraic geometry and towards theoretical computer science.
I’m primarily interested in working on the theoretical underpinnings of machine learning, so as to help make these tools more reliable and efficient. This could include things as different as looking for differentially private alternatives to existing methods, or a clearer mathematical understanding of when these methods work and when they fail.
I would like to understand why neural networks work as well as they do, and whether we can find more objective principles of neural network design than the heuristics we currently use.
I find it most interesting how solving problems in computer science often requires the use of extremely disparate techniques in mathematics, often ones which I might not have initially expected, given the problem setting.
I’m currently primarily focused on understanding the state of the art in theoretical computer science and machine learning (perhaps with a greater emphasis on topics like optimisation or privacy). Moving forward, I’d like to try and work on problems whose solutions help lead to a fairer and healthier society.
I completed my master’s degree in Mathematics from the National University of Singapore, during which time I gradually moved away from number theory and algebraic geometry and towards theoretical computer science.
I’m primarily interested in working on the theoretical underpinnings of machine learning, so as to help make these tools more reliable and efficient. This could include things as different as looking for differentially private alternatives to existing methods, or a clearer mathematical understanding of when these methods work and when they fail.
I would like to understand why neural networks work as well as they do, and whether we can find more objective principles of neural network design than the heuristics we currently use.
I find it most interesting how solving problems in computer science often requires the use of extremely disparate techniques in mathematics, often ones which I might not have initially expected, given the problem setting.
I’m currently primarily focused on understanding the state of the art in theoretical computer science and machine learning (perhaps with a greater emphasis on topics like optimisation or privacy). Moving forward, I’d like to try and work on problems whose solutions help lead to a fairer and healthier society.