Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
eachro
on Jan 24, 2018
|
parent
|
context
|
favorite
| on:
Non-Convex Optimization for Machine Learning
Super curious, what kind of problems do you mean when you say "signal recovery over the action of compact groups"?
Xcelerate
on Jan 24, 2018
[–]
Consider an object. Now duplicate that object many times, add random noise to each object, and give it a random rotation in space (over the rotation group SO(3)). The goal is to recover the original object from the noisy, rotated copies of it.
Consider applying for YC's Fall 2026 batch!
Applications
are open till July 27.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
