Adji Bousso Dieng

Adji Bousso Dieng
Assistant Professor of Computer Science
Office Phone
609-258-5935
Email
[email protected]
Office
406 Computer Science
Website
https://vertaix.princeton.edu
CV
dieng_cv.pdf
Education

Ph.D., Statistics, Columbia University, 2020

MS, Applied Statistics, Cornell University, 2013

Diplome D'Ingenieur, Telecom ParisTech, France 2013

Honors and Awards

Outstanding Recent Alumni Award by Columbia University 2023

  • AI2050 Early Career Fellow ($300K) 2022
  • Annie T. Randall Innovator Award 2022
  • Winner of the Savage Award, 2020
  • Rising Star in Machine Learning (University of Maryland), 2019
  • Google PhD Fellowship, 2019

Affiliations

  • Assistant Professor of Computer Science
  • Associated Faculty, Department of Chemical and Biological Engineering
  • Associated Faculty, High Meadows Environmental Institute
  • Associated Faculty, Princeton Materials Institute
  • Associated Faculty, Quantitative and Computational Biology

Research Interests

Vertaix is a research lab at Princeton University led by Professor Adji Bousso Dieng. We work at the intersection of artificial intelligence (AI) and the natural sciences. The models and algorithms we develop are motivated by problems in those domains and contribute to advancing methodological research in AI. We leverage tools in statistical machine learning and deep learning in developing methods for learning with the data, of various modalities, arising from the natural sciences.

Selected Publications
  1. D. Friedman and A. B. Dieng. The Vendi Score: A Diversity Evaluation Metric for Machine Learning. https://arxiv.org/abs/2210.02410
  2. K. Kim, J. Oh, J. R. Gardner, A. B. Dieng, H. Kim. Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients. Neural Information Processing Systems (NeurIPS), 2022. https://arxiv.org/abs/2206.06295
  3. F. L. Ruta, A. J. Sternbach, A. B. Dieng, A. S. McLeod, and D. N. Basov. Quantitative nanoinfrared spectroscopy of anisotropic van der Waals materials. Nano letters, 2021. https://pubs.acs.org/doi/abs/10.1021/acs.nanolett.0c02671
  4. S. Sinha and A. B. Dieng. Consistency Regularization for Variational Auto-Encoders. Neural Information Processing Systems (NIPS), 2021. https://arxiv.org/abs/2105.14859
  5. A. B. Dieng, F. J. R. Ruiz, D. M. Blei, and M. Titsias. Prescribed Generative Adversarial Networks. Link: https://arxiv.org/abs/1910.04302
  6. A. B. Dieng and J. Paisley. Reweighted Expectation Maximization. https://arxiv.org/abs/1906.05850
Research Areas
Complex Materials and Processing
Theory and Computation