About

I am a PhD student in Computer Science at Johns Hopkins University. Previously, I finished my master's in Computational and Mathematical Engineering from Stanford. Before that, I studied applied math at Columbia and did research in development economics.

Research Interests: My main interest lies in developing methods to evaluate the reliability of AI systems, with a primary focus on healthcare and a secondary focus on social sciences. The overarching goal is to ensure that AI systems can be deployed reliably for real-world decision making. In the process, I mainly draw on ideas from machine learning, statistics, and causal inference.

Other Interests: I like reading books, running, biking, and hiking in the mountains. You can read about my outdoor experiences here.

I am originally from Nepal and enjoy discussions on political, economic, and, more recently, technology policy, in the context of both Nepal and developing countries.

Research

Journal Publications

  • T. E. Gibson, S. Acharya, A. Parashar, J. E. Gaudio, and A. Annaswamy, "On the stability of gradient descent with second order dynamics for time-varying cost functions," Transactions on Machine Learning Research, 2025, Journal-to-Conference Certification: Presented at ICLR 2026.
  • T. E. Gibson, Y. Kim, S. Acharya, D. E. Kaplan, N. DiBenedetto, R. Lavin, B. Berger, J. R. Allegretti, L. Bry, and G. K. Gerber, "Learning ecosystem-scale dynamics from microbiome data with mdsine2," Nature Microbiology, vol. 10, no. 10, pp. 2550–2564, 2025.
  • Y. Kim, C. J. Worby, S. Acharya, L. R. van Dijk, D. Alfonsetti, Z. Gromko, P. N. Azimzadeh, K. W. Dodson, G. K. Gerber, S. J. Hultgren, A. M. Earl, B. Berger, and T. E. Gibson, "Longitudinal profiling of low-abundance strains in microbiomes with chronostrain," Nature Microbiology, vol. 10, no. 5, pp. 1184-1197, 2025.

Conferences

  • S. Acharya, T. J. Zhang, A. Kim, R. B. Shrestha, X. Sun, P. Cobben, M. Mordig, J. T. Emmerson, A. Haghighat, F. Danisman, Y. Chen, C. Jose, A. I. Muresanu, J. Cui, J. Liu, Y. Qi, P. S. Pandey, Y. Huang, B. Schölkopf, and Z. Jin, "CauSciBench: Can LLMs automate causal inference in real-world scientific research?," in Forty-third International Conference on Machine Learning, 2026.

Workshops

  • S. Acharya, T. J. Zhang, A. Kim, A. Haghighat, S. Xianlin, R. B. Shrestha, M. Mordig, F. Danisman, C. Jose, Y. Qi, P. Cobben, B. Schölkopf, M. Sachan, and Z. Jin, "Causcibench: Assessing LLM causal reasoning for scientific research," in NeurIPS 2025 Workshop on CauScien: Uncovering Causality in Science, 2025.
  • V. Verma, S. Acharya, S. Simko, D. Bhardwaj, A. Haghighat, D. Janzing, M. Sachan, Z. Jin, and Y. Yang, "Causal AI scientist: Facilitating causal data science with large language models," in NeurIPS 2025 AI for Science Workshop, 2025.
  • Y. Kim, S. Acharya, D. Alfonsetti, G. Gerber, B. Berger, and T. E. Gibson, "Chronostrain: Sequence quality and time-aware strain tracking with shotgun metagenomic data," in ICML Workshop on Computational Biology, 2020.

Preprints

  • T. E. Gibson and S. Acharya, Regret Analysis: A Control Perspective, 2025. arXiv: 2501.04572.

Teaching

  • Teaching Assistant, Math 21: Integral Calculus and Series, Winter and Spring 2025. Stanford University.
  • Course Assistant, CME 106: Introduction to Probability and Statistics for Engineers, Summer 2024. Stanford University.
  • Teaching Assistant, MATH 51: Linear Algebra and Differential Calculus of Several Variables, Autumn 2023 and Winter 2024. Stanford University.
  • Teaching Assistant, APMA E2000: Multivariable Calculus for Engineers, Fall 2017, Spring 2018, Fall 2018, and Winter 2019. Columbia University.

Contact

You can reach me at sachar12@jh.edu.