Konstantinos Stavropoulos

Konstantinos Stavropoulos (Kostas)

Ph.D. Student

University of Texas at Austin

About me

I am currently a fourth-year Ph.D. student in Computer Science at UT Austin. I am fortunate to be advised by Prof. Adam Klivans. Before that, I studied Electrical and Computer Engineering at the National Technical University of Athens, where I was fortunate to work with Prof. Dimitris Fotakis. I am grateful to be supported by the 2025 Apple Scholars in AI/ML Fellowship.

I expect to complete my PhD during the 2025–2026 academic year and am actively looking for postdoctoral opportunities starting Fall 2026.

Summer 2025: I am in the Bay Area for a research internship at Apple MLR, working with Parikshit Gopalan.

My research is in the intersection of machine learning and theoretical computer science. I am particularly interested in designing efficient learning algorithms with provable guarantees that do not rely on the strong assumptions typically made in learning theory, especially in challenging scenarios like learning with distribution shift and/or noise.

My CV can be found here (last update: May 2025).

    [email protected]

Publications
(alphabetical author order)

Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan (2025). Learning Constant-Depth Circuits in Malicious Noise Models. COLT 2025.

PDF Cite URL

Gautam Chandrasekaran, Adam Klivans, Lin Lin Lee, Konstantinos Stavropoulos (2025). Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees. ICLR 2025.

PDF Cite URL

Gautam Chandrasekaran, Vasilis Kontonis, Konstantinos Stavropoulos, Kevin Tian (2024). Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random. NeurIPS 2024 Spotlight.

PDF Cite URL

Surbhi Goel, Abhishek Shetty, Konstantinos Stavropoulos, Arsen Vasilyan (2024). Tolerant Algorithms for Learning with Arbitrary Covariate Shift. NeurIPS 2024 Spotlight.

PDF Cite URL

Gautam Chandrasekaran, Adam Klivans, Vasilis Kontonis, Konstantinos Stavropoulos, Arsen Vasilyan (2024). Efficient Discrepancy Testing for Learning with Distribution Shift. NeurIPS 2024.

PDF Cite URL

Gautam Chandrasekaran, Adam Klivans, Vasilis Kontonis, Raghu Meka, Konstantinos Stavropoulos (2024). Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension. COLT 2024 Best Paper.

PDF Cite URL

Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan (2024). Learning Intersections of Halfspaces with Distribution Shift: Improved Algorithms and SQ Lower Bounds. COLT 2024.

PDF Cite URL

Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan (2024). Testable Learning with Distribution Shift. COLT 2024.

PDF Cite URL

Aravind Gollakota, Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan (2024). An Efficient Tester-Learner for Halfspaces. ICLR 2024.

PDF Cite URL

Aravind Gollakota, Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan (2023). Tester-Learners for Halfspaces: Universal Algorithms. NeurIPS 2023 Oral.

PDF Cite URL

Aravind Gollakota, Parikshit Gopalan, Adam Klivans, Konstantinos Stavropoulos (2023). Agnostically Learning Single-Index Models using Omnipredictors. NeurIPS 2023.

PDF Cite URL

Alkis Kalavasis, Konstantinos Stavropoulos, Emmanouil Zampetakis (2022). Learning and Covering Sums of Independent Random Variables with Unbounded Support. NeurIPS 2022 Oral.

PDF Cite URL

Dimitris Fotakis, Alkis Kalavasis, Konstantinos Stavropoulos (2021). Aggregating Incomplete and Noisy Rankings. AISTATS 2021.

PDF Cite URL

Manuscripts

Adam Klivans, Konstantinos Stavropoulos, Kevin Tian, Arsen Vasilyan (2025). The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination. Under review.

PDF Cite URL

Surbhi Goel, Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan (2025). Testing Noise Assumptions of Learning Algorithms. Under review.

PDF Cite URL

Awards and Achievements

  2025 Apple Scholars in AI/ML PhD fellowship
I was selected as an Apple Scholar in AI/ML.
2025


   Best paper award at Conference on Learning Theory (COLT) 2024
Our paper on Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension won the best paper award at COLT.
Jun 2024


  Oral presentations at NeurIPS 2022 and 2023
Our paper Tester-Learners for Halfspaces: Universal Algorithms was selected for oral presentation at NeurIPS 2023 (top 0.54% of all submissions). In NeurIPS 2022, the paper Learning and Covering Sums of Independent Random Variables with Unbounded Support was selected for oral presentation as well (top 1.76% of all submissions).
Dec 2022, 2023


  Scholarships from Bodossaki and Leventis Foundations and scholarship award from the Hellenic Professional Society of Texas
My Ph.D. studies are generously supported by scholarships from Bodossaki and Leventis foundations. In, May 2022, I received a scholarship award from HPST in recognition of academic excellence.
Sep 2022 - Aug 2025, May 2022


   Award from State Scholarships Foundation and “Thomaideio” Award from NTUA
Upon graduating from the ECE department of NTUA, I received the Award of Excellence from the State Scholarships Foundation of Greece for graduating first in my cohort within the nominal period of studies. During my studies, I was awarded for having the highest GPA among all undergraduate students of the ECE department during the academic year 2018-2019.
2019, 2020

Reviewing

COLT 2025, ICLR 2024, ICML 2024, NeurIPS 2023