aahlad puli

Logo

CV (as of November 2023)

PhD student, Computer Science, NYU
Email: aahlad [at] nyu [dot] edu

Publications

View My GitHub Profile

About Me


I am on the job market for research positions this year.

I am a PhD candidate in Computer Science at the Courant Institute, NYU. I am fortunate to be advised by Prof. Rajesh Ranganath. I am supported by the Apple Scholars in AI/ML PhD fellowship.

I work on building models that are robust across populations using insights and techniques from causal inference. Earlier, I worked on causal effect estimation when standard assumptions like ignorability and positivity/overlap do not hold and improving calibration in survival models. My primary applied interest is ML for healthcare in particular and science in general.

I’m eternally excited about new ideas and finding good applications for my work! Shoot me an email if you want to chat!

News


  1. Oct 2023: Gave a talk about OOD generalization in health at INFORMS.

  2. Sept 2023: New paper accepted at NeurIPS 2023; link.

  3. July 2023: The second SCIS workshop was a success at ICML 2023; link

  4. April 2023: DIET was published at AISTATS; link.

  5. July 2022: Organized the SCIS workshop at ICML 2022; website.

  6. March 2022, Very happy to be a recipient of the Apple Scholars in AI/ML PhD Fellowship! announcement

  7. March 2022, Updated version of NuRD on arxiv with code and improved results! link

  8. January 2022, NuRD published at ICLR 2022 and work led by Mark Goldstein published at CLeaR 2022; link.

  9. Oct’ 21, Named Rising Star by the Trustworthy ML initiative

  10. June’ 21, New work on arxiv: What sort of predictive models come with performance guarantees under spurious correlations induced by a relationship between the label and some nuisance variables that are correlated on the covariates? Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations

  11. Apr’ 21, Link to work at AISTATS, 2021; Led by Mukund Sudarshan: A new contrarian test statistic to use in CRTs to improve robustness to mis-specified covariate distributions. CONTRA:Contrarian statistics for controlled variable selection

  12. Nov’ 20. Links to my work at NeurIPS 2020 along with punchlines (shoot me an email if these interest you!):

Olds


I was an intern in the summer of 2019 in Adobe Research, San Jose working on bayesian attribution models for ad targeting. Previously, I worked as a Software Developer at DBMI, Columbia University. In 2017, I completed my MS in CS, also at NYU. I was introduced to causal inference in the Clinical Machine Learning group, where I worked with two amazing mentors, Prof. Uri Shalit and Prof. David Sontag. My fateful but fun undergrad was from IIT Madras, where I was enrolled in the EE department.