Amirali Aghazadeh

Georgia Tech

prof_pic.jpg

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. I serve as program faculty for the Machine Learning, Bioinformatics, and Bioengineering Ph.D. programs. I am also affiliated with the Institute for Data Engineering and Science (IDEAS) and the Parker H. Petit Institute for Bioengineering and Bioscience. Prior to Georgia Tech, I was a postdoctoral researcher at Stanford and UC Berkeley, and earned my Ph.D. at Rice University.

My research interests lie at the intersection of Machine Learning, Signal Processing, Deep Learning, and Computational Biology. I aim to develop scalable algorithms that enable machines to learn, predict, and adapt to solve complex problems—especially those arising from the natural sciences, including biology, chemistry, and physics.

Our group draws from and contributes to foundational areas in mathematics, statistics, and computer science, including optimization, harmonic analysis, sketching and streaming algorithms, and high-dimensional statistics.

Our current research focuses include:

  • ML/AI for Science: Generative & Geometric Modeling for Sciences
  • Core ML/AI: Explainability & Robustness in Combinatorial Spaces
  • Scalable ML/AI: Learning and Inference in Massive Scale

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

Watch my talk on Sparsity, Epistasis, and Models of Fitness Functions at Broad Institute: Models, Inference and Algorithm (MIA)

news

May 02, 2025 Check out the story of our work on developing AI Scientists for hypothesis generation about Origins of Life in journal Nature. Many thanks to Celest Biever for covering this!
Apr 25, 2025 Tom gave a presenation on mutant effect prediction with AI in EYE CONNECT AI Learning at Emory. Also congrats on passing the qualification exams!
Mar 12, 2025 I am giving a talk at APS on Explaining High-order Interactions in Protein Language Models
Mar 10, 2025 Huge congrats to Daniel Saeedi for his work being accepted for an oral presentation in ICLR 2025 Workshop on Towards Agentic AI for Science: Hypothesis Generation, Comprehension, Quantification, and Validation. Stay tuned for the preprint!
Feb 13, 2025 I am giving a talk at ITA on Scaling Explainability: Fast Algorithms to Decode Ever-Growing ML Models

selected publications

  1. AstroAgents.png
    AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data
    Daniel Saeedi, Denise Buckner, José Aponte, and 1 more author
    International Conference on Learning Representation (ICLR) Workshop on Towards Agentic AI for Science: Hypothesis Generation, Comprehension, Quantification, and Validation, 2025
  2. fourier.jpg
    Efficient Algorithm for Sparse Fourier Transform of Generalized q-ary Functions
    Darin Tsui, Kunal Talreja, and Amirali Aghazadeh
    arXiv preprint arXiv:2501.12365, 2025
  3. SHAPzero.jpg
    SHAP zero Explains Genomic Models with Near-zero Marginal Cost for Future Queried Sequences
    Darin Tsui, Aryan Musharaf, Yigit Efe Erginbas, and 2 more authors
    arXiv preprint arXiv:2410.19236, 2024