Arsen Vasilyan
Scholar

Arsen Vasilyan

Google Scholar ID: hLseRm8AAAAJ
UT Austin
Theoretical Computer ScienceLearning TheorySublinear Algorithms
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
162
 
H-index
8
 
i10-index
6
 
Publications
20
 
Co-authors
0
 
Contact
CVOpen ↗GitHubOpen ↗
Publications
5 items
Learning $\mathsf{AC}^0$ Under Graphical Models
2026
Cited
0
Sandwiching Polynomials for Geometric Concepts with Low Intrinsic Dimension
2026
Cited
0
A Fully Polynomial-Time Algorithm for Robustly Learning Halfspaces over the Hypercube
2025
Cited
0
The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination
2025
Cited
0
Testing Noise Assumptions of Learning Algorithms
2025
Cited
0
Resume (English only)
Academic Achievements
  • - Publications:
  • - "The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination", NeurIPS 2025
  • - "Robust learning of halfspaces under log-concave marginals", NeurIPS 2025
  • - "Learning Constant-Depth Circuits in Malicious Noise Models", COLT 2025
  • - "Local Lipschitz Filters for Bounded-Range Functions", SODA 2025
  • - "Tolerant Algorithms for Learning with Arbitrary Covariate Shift", NeurIPS 2024
  • - "Efficient Discrepancy Testing for Learning with Distribution Shift", NeurIPS 2024
  • - "Plant-and-Steal: Truthful Fair Allocations via Predictions", NeurIPS 2024
  • - "Learning Intersections of Halfspaces with Distribution Shift: Improved Algorithms and SQ Lower Bounds", COLT 2024
  • - "Testable Learning with Distribution Shift", COLT 2024
  • - "An Efficient Tester-Learner for Halfspaces", ICLR 2024
  • - "Tester-Learners for Halfspaces: Universal Algorithms", NeurIPS 2023
  • - "Agnostic Proper Learning of Monotone Functions: Beyond the Black-box Correction Barrier", FOCS 2023
  • - "Testing Distributional Assumptions of Learning Algorithms", STOC 2023
  • - "Properly Learning Monotone Functions via Local Reconstruction", FOCS 2022
  • - "Monotone Probability Distributions over the Boolean Cube Can Be Learned with Sublinear Samples", incomplete information
Research Experience
  • - Postdoctoral Fellow: Institute for Foundations of Machine Learning (UT Austin)
  • - Research Fellow: The Simons Institute for the Theory of Computing
Education
  • - PhD: Massachusetts Institute of Technology, advised by Jonathan Kelner and Ronitt Rubinfeld
  • - Undergraduate: Massachusetts Institute of Technology, major in Computer Science, double minor in Physics and Philosophy
Background
  • - Research interests: Computational learning theory, computational statistics, distribution learning and testing
  • - Professional field: Computer Science
  • - Brief introduction: Currently a postdoctoral fellow at the Institute for Foundations of Machine Learning (UT Austin). Previously, a research fellow at The Simons Institute for the Theory of Computing.
Miscellany
  • - Personal interests: Competed in the International Physics Olympiad (IPhO)
Co-authors
0 total
Co-authors: 0 (list not available)