[CS] [masters-presentation] Pan/MS Presentation/Nov 19, 2020

[Tricia Baclawski]

This is an announcement of Horace Pan's MS Presentation.


https://uchicago.zoom.us/j/92782297156?pwd=MDBrRkdqcjdGYzEwbW5odmRqQldJdz09
Password: 378348

------------------------------------------------------------------------------
Date:  Thursday, November 19, 2020

Time:  4:00 PM

Place:  via zoom

M.S. Candidate:  Horace Pan

M.S. Paper Title: Fourier Bases for Solving Permutation Puzzles

Abstract:
Traditionally, permutation puzzles such as the Rubik’s Cube were often
solved by heuristic search likeA∗-search and value based
reinforcement learning methods. Both heuristic searchand Q-learning
approaches to solving these puzzles can be reduced to learning a
heuristic/valuefunction to decide what puzzle move to make at each
step. We propose learning a valuefunction using the irreducible
representations basis (which we will also call the Fourier basis)of
the puzzle’s underlying group. Classical Fourier analysis on real
valued functions tells us we can approximate smooth functions with low
frequency basis functions. Similarly, smooth functions on finite
groups can be represented by the analogous low frequency Fourier basis
functions. We demonstrate the effectiveness of learning a value
function in the Fourier basisfor solving various permutation puzzles
and show that it outperforms standard deep learning methods. Both
heuristic search and Q-learning approaches to solving these puzzles
can be reduced to learning a heuristic/value function to decide what
puzzle move to make at each step. We propose learning a value function
using the irreducible representations basis (which we will also call
the Fourier basis) of the puzzle’s underlying group. Classical Fourier
analysis on real valued functions tells us we can approximate smooth
functions with low frequency basis functions. Similarly, smooth
functions on finite groups can be represented by the analogous low
frequency Fourier basis functions. We demonstrate the effectiveness of
learning a value function in the Fourier basis for solving various
permutation puzzles and show that it outperforms standard deep
learning methods.

Horace's advisor is Prof. Risi Kondor

Login to the Computer Science Department website for details:
 https://newtraell.cs.uchicago.edu/phd/ms_announcements#hopan

=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Tricia Baclawski
Student Affairs Administrator
Computer Science Department
5730 S. Ellis - Room 350
Chicago, IL 60637
pbaclawski at uchicago.edu
(773) 702-6854
/pronouns: she, her, hers/
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=