I was BS student in Physics department at Korea Advanced Institute of Science and Technology (KAIST). Moreover I was MS student in Electrical Engineering department at Korea Advanced Institute of Science and Technology (KAIST) and I studied about Quantum information theory. Now I am PhD Candidates in Mathematical Science department in KAIST. I studied on the measurement based algorithm which is strongly related to the quantum adiabatic evolution algorithm. Measurement based algorithm is the method that with time independent perturbation theory, we want to maintain or capture the ground state of the Hamiltonian during the computation. In Grover problem (unstructured search problem), I suggest that if we have a prior, then the time complexity of searching is decreasing and the probability to get proper result will be increasing.
I am interested in mathematical approach to Machine Learning and Deep Learning, i.e. Loss Landscape Analysis, Diffusion model and so on. Especially I am studying about "Benign Overfitting" in deep learning area. Benign overfitting is the phenomenon that the deep neural network have a good generalization performance even though they memorize all data points. It seems to contradict with the classical statistical theory which is called bias-variance tradeoff. There are several results that benign overfitting can be characterized by the model parameter and so on.
One of my goal is to adapt this phenomenon to some specific area, that is health care.
Quantum Information Theory
Quantum adiabatic evolution to compute search problem.
Quantum measurement based algorithm to compute search problem
Quantum Machine Learning : kernel method and beyond
Data embedding with unitary operators
Equivalence between quantum machine learning method and Kernel Method
Statistical Limit of Quantum Learning
Non-classical Kernel : with squeezed states
Barren Plateus Phenomenon
Machine Learning
Deep Learning Theory : Benign property "No bad(spurious) local valleys", Statistical Limit of Neural Networks, Diffusion Model.
Mail : rlarhwh2@kaist.ac.kr or physicist456@gmail.com
Analysis1,2 - 2018
Elementary Probability Theory - 2018
Probability and Statistics - 2014
Mathematical Physics - 2017
Linear Algebra - 2017
Differential Equations and Applications - 2015
Calculus & Introduction to Linear Algebra - 2014
Lebesgue Integral Theory - 2019
Topics in Mathematics - Mathematical Foundations for Artificial Intelligence
Topics in Mathematics - Advanced Intelligence
Topics in Mathematics - Random Matrix Theory and its application
Complex Variables1
Individual Study - topics : introduction to random matrix theory
Quantum Mechanics 1,2 - 2016
Thermodynamics & Statistical Physics - 2016
Mathematical method in Physics 1,2 - 2015, 2016
Advanced Physics 1 & General Physics 2
Classical Electromagnetism 1,2 - 2015
Classical Mechanics 1,2 - 2015
Optics - 2016
Physics. LAB 1, 3
Special topics on Particle Physics - 2017
URP group study : Quantum computer and Entanglement
Individual Study - topics :
Path integral theorem for condensed matter physics
An introduction to Modern Astrophysics
Finding FIMS and GALLEX using Deep Learning
Machine Learning - CS
Quantum Information and Computing - EE
Individual Study - topics :
Quantum Information Theory
Reinforcement Learning
Probability Theory
Probability and Statistics
Real Analysis
Quantum Machine Learning
Introduction to Quantum information processing
Information Theory