Amirali Aghazadeh

Georgia Tech


Coda S1209

Tech Square

Atlanta, GA 30308

I am an Assistant Professor in the School of Electrical and Computer Engineering at the Georgia Institute of Technology, where I am a program faculty of Machine Learning, Bioinformatics, and Bioengineering PhD programs. I also have affiliations with the Institute for Data Engineering and Science (IDEAS). Before joining Georgia Tech, I was a postdoc at Stanford and UC Berkeley and I did my PhD at Rice University.

I am interested in Machine Learning, Signal Processing, Deep Learning, and Computational Biology. My research goal is to advance how Machines can Learn, Predict, and Adapt at scale to solve problems in and inspired by emerging Technologies and Sciences, from biology to chemistry and physics. Current research focus are:

  • ML/AI for Science: generative & language modeling for bioscience
  • Core ML/AI: explainability & robustness in combinatorial spaces
  • Scalable ML/AI: algorithms for fast & efficient training/inference

I pronounce my first name /æmi:r’æli:/ and last name /ægə’zɑdɛ/.


Mar 1, 2023 I am offering a course on generative and geometric deep learning in Fall 2023.
Feb 16, 2023 I am giving a talk in ITA workshop on explaining deep protein models using Fourier analysis.
Feb 1, 2023 We have multiple openings for PhD students!
Oct 21, 2022 Gautham receives the MS Bioinformatics GRA award. Congrats! :sparkles: :smile:
Oct 1, 2022 I am offering ECE 6254: Statistical Machine Learning in Spring 2023.

selected publications

  1. MISSION: Ultra large-scale feature selection using Count Sketches
    Amirali Aghazadeh, Ryan Spring, Daniel LeJeune, Gautam Dasarathy, Anshumali Shrivastava, and 1 more author
    In International Conference on Machine Learning (ICML) 2018
  2. Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
    Amirali Aghazadeh, Hunter Nisonoff, Orhan Ocal, David H Brookes, Yijie Huang, and 3 more authors
    Nature Communications 2021
  3. Spectral Regularization Allows Data-frugal Learning over Combinatorial Spaces
    Amirali Aghazadeh, Nived Rajaraman, Tony Tu, and Kannan Ramchandran
    arXiv:2210.02604 2022