Daksh Aggarwal

I am a third-year math Ph.D. student at Brown University. I am fortunate to be advised by Prof. Isabel Vogt.

Additionally, I like using my math and CS background in studying generative modeling, and am also currently doing research in the PALM AI lab.

Earlier, I studied mathematics and computer science at Grinnell College, Iowa, advised by Prof. Jennifer Paulhus and Prof. Nicole Eikmeier. I also spent my senior year in the Budapest Semesters in Math program, and I highly recommend it.

My publications and preprints can be found here. My email is [first_name]_[last_name]@brown.edu.

news

Oct 29, 2024	Our arXiv preprint proposes a new neural network layer, the Fourier head, which learns a continuous probability density function using Fourier series, and returns a discrete approximation of it. When to use it? Large language models are often adapted to model non-linguistic tokens. If these tokens have an underlying continuous structure, then replacing the linear classification head with the Fourier head can boost downstream performance. Project page
Oct 28, 2024	I will be attending AGNES at Dartmouth!

Oct 29, 2024

Our arXiv preprint proposes a new neural network layer, the Fourier head, which learns a continuous probability density function using Fourier series, and returns a discrete approximation of it. When to use it? Large language models are often adapted to model non-linguistic tokens. If these tokens have an underlying continuous structure, then replacing the linear classification head with the Fourier head can boost downstream performance. Project page

Oct 28, 2024

I will be attending AGNES at Dartmouth!