About

I’m Sid, a CS PhD student in the USC Theory Group, where I am fortunate to be advised by the wonderful Vatsal Sharan and Aleksandra Korolova. I am broadly interested in (1) trustworthy, fair, and robust AI; and (2) theoretical machine learning. I am grateful to have my research supported by a National Defense Science and Engineering Graduate (NDSEG) Fellowship.

During Fall 2024, I will be a visitor at the Simons institute modern paradigms in generalization research program. Happy to chat with anyone in the area! I was lucky to intern with Gaurush Hiranandani at Amazon during Summer 2024, working on black-box metric optimization for vision and language models. Here is my CV (Nov. 2023).

I completed my undergraduate degrees in math and CS at The University of Texas at Dallas (UTD), where I explored research in networking, theory, optimization, and reinforcement learning. Along the way, I was extremely fortunate to be advised by these amazing professors: Nick Ruozzi, Jason Jue, Brendan Juba, and Ben Raichel.

If you are a prospective PhD applicant, I am happy to help in any way I can. Please feel free to reach out over email.

Publications and Preprints

(αβ) indicates alphabetical order, standard in theoretical computer science.
(*) indicates equal contribution.

• When is Multicalibration Post-Processing Necessary?
  Dutch Hansen*, Siddartha Devic*, Preetum Nakkiran, Vatsal Sharan
  Neural Information Processing Systems (Neurips 2024)
  [arxiv]

• Transductive Learning Is Compact
  (αβ) Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng
  Neural Information Processing Systems (Neurips 2024)
  [arxiv]

• Regularization and Optimal Multiclass Learning
  (αβ) Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng
  Conference on Learning Theory (COLT 2024)
  [arxiv] [slides] [twitter thread]

• Stability and Multigroup Fairness in Ranking with Uncertain Predictions
  Siddartha Devic, Aleksandra Korolova, David Kempe, Vatsal Sharan
  International Conference on Machine Learning (ICML 2024)
  Non-archival at Symposium on Foundations of Responsible Computing (FORC 2024)
  [arxiv] [video]

• Fairness in Matching under Uncertainty
  Siddartha Devic, David Kempe, Vatsal Sharan, Aleksandra Korolova
  International Conference on Machine Learning (ICML 2023)
  Non-archival at ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO 23)
  [arxiv] [poster] [slides] [twitter thread] [video]

• Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions
  (αβ) Zihao Deng, Siddartha Devic, Brendan Juba
  International Conference on Artificial Intelligence and Statistics (AISTATS 2022)
  Also appeared at Neurips 2021 Workshop on Ecological Theory of Reinforcement Learning
  [arxiv]

• Dynamic Bandwidth Allocation for PON Slicing with Performance-Guaranteed Online Convex Optimization
  Genya Ishigaki, Siddartha Devic, Riti Gour, Jason P. Jue
  IEEE GLOBECOM 2021
  [arxiv] [poster]

• DeepPR: Progressive Recovery for Interdependent VNFs with Deep Reinforcement Learning
  Genya Ishigaki, Siddartha Devic, Riti Gour, Jason P. Jue
  IEEE Journal on Selected Areas in Communications, 2020
  Also appeared at IEEE GLOBECOM 2019
  [arxiv]

Workshop Papers and Other

• Open Problem: Can Local Regularization Learn All Multiclass Problems?
  (αβ) Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng
  COLT 2024 Open Problem
  [pdf]

• Failout: Achieving Failure-Resilient Inference in Distributed Neural Networks
  Ashkan Yousefpour, Brian Q Nguyen, Siddartha Devic, Guanhua Wang, Aboudy Kreidieh, Hans Lobel, Alexandre M Bayen, Jason P. Jue
  ICML 2020 Workshop on Federated Learning for User Privacy and Data Confidentiality
  [arxiv]

Mentorship

• Dutch Hansen - Multicalibration of neural networks.
  Undergrad, Jan. 2023 - Present.
• Anish Jayant - Multicalibration of neural networks.
  Undergrad, Jan. 2023 - May 2023.
• Jayron Martinez - Bias in Machine Learning Algorithms.
  High school senior, summer 2022. Part of the USC SHINE program.
  [poster]

Service

Reviewer: Neurips 2024, ICLR 2025.

Student Activities

The first year of my PhD, I served as a CS department senator within the USC Viterbi Graduate Student Association (VGSA), where I was able to bring goats to campus (amongst other things).

I served as President / VP for my undergrad’s ACM chapter, where I am most proud to have established a perpetual $30k endowed scholarship with club funds. Importantly, the scholarship may also grant eligible students an in-state tuition waiver! Students can apply here.

I also served as the undergrad representative on the UTD CS department head search committee during the 2020-2021 academic year.

If you are a UTD student interested in pursuing a PhD, you may find the grad school section I wrote of this guide helpful. Also check out this research internship / REU masterlist which I put together.

Fun

In my free time I enjoy climbing/bouldering, surfing, hiking, and skiing (the latter two less frequently!). I have (at some point in the past) also attempted the following: learning art, running, calisthenics progressions, playing classical piano, swimming, and binging npr tiny desk concerts.

Some other stuff from undergrad:

• Clustering in hyperbolic space (with Mike Skinner)
• Short notes on statistical learning (with Dipnil Chakraborty)
• Point packing in hypercubes
• Coarse classification of russian troll tweets

Rejections

Here is a list of some of my rejections (e.g. jobs, fellowships, etc.) to help normalize the fact that most things don't work out :D

Give, even if you only have a little.

-Siddhartha Gautama