Hello World

17 March, 2023

In this blog, I will be sharing insights into my various computer science projects. Over the next few weeks, I'll be writing six posts covering the following topics (the order may vary):

• Sampling from a Multivariate Generalized Gaussian:
  In this post, I'll describe a cool sampling algorithm I adapted to sample from a very special distribution.
• Regularization and Noise Injection:
  Here, I'll be talking about my masters thesis and about how to regularize neural networks by injecting noise.
• New Data Structure:
  I'll be sharing details about a new data structure that I've been working on and how it can be used in practice.
• Datajuicer:
  I'll discuss my library for caching and parallelization of dynamic computing tasks.
• Epistemic approach to formal cryptography:
  I have some ideas about how to talk directly about who knows what in a cryptographic protocol.
• Benchmark for reward hacking:
  My flatmate and I have been working on a way to measure the 'gullibility' of AI models with a possible application in AI alignment.

I'm grateful for the mentorship I've received along the way, and I'm always eager to learn more. So, if you notice that I'm doing something obviously stupid, please don't hesitate to reach out and let me know.

Stay tuned!

P.S.

If you are wondering how I made my (current) favicon , the command is:
$\mathfrak{F}\mkern-16mu\mathfrak{F}$