| CARVIEW |
I am an IFML Postdoctoral Fellow based at UT Austin hosted by Adam Klivans and Raghu Meka. I received my PhD in Computer Science from the University of Wisconsin-Madison, where I was advised by Christos Tzamos. Prior to UW-Madison, I studied Electrical and Computer Engineering at the National Technical University of Athens where I was advised by Dimitris Fotakis.
I work on designing efficient algorithms with provable guarantees for machine learning problems with a focus on dealing with imperfect data (e.g., classification with noisy labels and statistical inference from biased or censored data). I am also interested in analyzing and providing formal guarantees for popular machine learning algorithms (e.g., diffusion models).
I am on the 2024/25 job market. Here is my CV.
News
-
Aug, 22, 2024: I am visiting Simons Institute at Berkeley for the generalization and LLM programs.
-
Jul, 3, 2024: Our work Smoothed Analysis for Learning Concepts of Low Intrinsic Dimension got the best paper award at COLT 2024!!
-
May, 1, 2024: New paper on learning mixtures of Gaussians using diffusion models!
Publications
-
Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
w/ G. Chandrasekaran, A. Klivans, R. Meka, K. Stavropoulos
Best Paper Award COLT 2024
IPAM 2024 Long Talk Video -
Active Learning with Simple Questions
w/ M. Ma, C. Tzamos
COLT 2024 -
Agnostically Learning Multi-index Models with Queries
w/ I. Diakonikolas, D. Kane, C. Tzamos, N. Zarifis
FOCS 2024 -
Super Non-singular Decompositions of Polynomials and their
Application to Robustly Learning Low-degree PTFs
w/ I. Diakonikolas, D M. Kane, S. Liu, N. Zarifis
STOC 2024 -
Efficient Discrepancy Testing for Learning with Distribution Shift
w/ G. Chandrasekaran, A. Klivans, K. Stavropoulos, A. Vasilyan
NeurIPS 2024 -
Active Classification with Few Queries under Misspecification
w/ C. Tzamos, M. Ma
NeurIPS 2024 -
Learning Noisy Halfspaces with a Margin: Massart is no Harder than Random
w/ G. Chandrasekaran, K. Stavropoulos, K. Tian
NeurIPS 2024 -
Optimizing Solution-Samplers for Combinatorial Problems:
The Landscape of Policy Gradient Methods
w/ C. Caramanis, D. Fotakis, A. Kalavasis, C. Tzamos
Selected for Oral Presentation
NeurIPS 2023 -
SLaM: Student-Label Mixing for Distillation with Unlabeled Examples
w/ F. Iliopoulos, K. Trinh, C. Baykal, G. Menghani, V. Erik
NeurIPS 2023 -
The Gain from Ordering in Online Learning
w/ M. Ma, C. Tzamos
NeurIPS 2023 -
Efficient Testable Learning of Halfspaces with Adversarial Label Noise
w/ I. Diakonikolas, D M. Kane, S. Liu, N. Zarifis
NeurIPS 2023 -
Self Directed Linear Classification
w/ I. Diakonikolas, C. Tzamos, N. Zarifis
COLT 2023 -
Weighted Distillation with Unlabeled Examples
w/ F. Iliopoulos, C. Baykal, G. Menghani, K. Trinh, V. Erik
NeurIPS 2022 -
Linear Label Ranking with Bounded Noise
w/ D. Fotakis, A. Kalavasis, C. Tzamos
Selected for Oral Presentation
NeurIPS 2022 -
Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent
w/ I. Diakonikolas, C. Tzamos, N. Zarifis
ICML 2022 -
Learning a Single Neuron with Adversarial Label Noise via Gradient Descent
w/ I. Diakonikolas, C. Tzamos, N. Zarifis
COLT 2022 -
Learning General Halfspaces with General Massart Noise under the Gaussian Distribution
w/ I. Diakonikolas, D. Kane, C. Tzamos, N. Zarifis
STOC 2022 -
A Statistical Taylor Theorem and Extrapolation of Truncated Densities
w/ C. Daskalakis, C. Tzamos, M. Zampetakis
COLT 2021 -
Agnostic Proper Learning of Halfspaces under Gaussian Marginals
w/ I. Diakonikolas, D. Kane, C. Tzamos, N. Zarifis
COLT 2021 -
Efficient Algorithms for Learning from Coarse Labels
w/ D. Fotakis, A. Kalavasis, C. Tzamos
COLT 2021 -
Learning Online Algorithms with Distributional Advice
w/ I. Diakonikolas, C. Tzamos, A. Vakilian, N. Zarifis
ICML 2021 -
A Polynomial Time Algorithm For Learning Halfspaces with Tsybakov Noise
w/ I. Diakonikolas, D. Kane, C. Tzamos, N. Zarifis
STOC 2021 -
Learning Halfspaces with Tsybakov Noise
w/ I. Diakonikolas, C. Tzamos, N. Zarifis
STOC 2021
Conference version merged with the above paper -
Non-Convex SGD Learns Halfspaces with Adversarial Label Noise
w/ I. Diakonikolas, C. Tzamos, N. Zarifis
NeurIPS 2020 -
Learning Halfspaces with Massart Noise Under Structured Distributions
w/ I. Diakonikolas, C. Tzamos, N. Zarifis
COLT 2020 -
Algorithms and SQ Lower Bounds for PAC Learning One-Hidden-Layer ReLU Networks
w/ I. Diakonikolas, D. Kane, N. Zarifis
COLT 2020 -
Efficient Truncated Statistics with Unknown Truncation
w/ C. Tzamos, M. Zampetakis
FOCS 2019 -
Removing Bias in Maching Learning via Truncated Statistics
w/ C. Daskalakis, C. Tzamos, M. Zampetakis
Manuscript -
Opinion Dynamics with Limited Information
w/ D. Fotakis, V. Kandiros, S. Skoulakis
WINE 2018 -
Learning Powers of Poisson Binomial Distributions
w/ D. Fotakis, P. Krysta, P. Spirakis
Manuscript
Service
-
Program Committees: ITCS-2025
-
Reviewer: FOCS (2020, 2021, 2023) , STOC (2020, 2024), COLT (2023), SODA (2019), NeurIPS (2021, 2023), WINE(2018), ICML(2023, 2021, 2020), EC (2022, 2020), MFCS (2018), TCS (2018, 2021), ALT (2021)
Talks
- Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
- Best Paper Award Talk, COLT 2024
- EnCORE Workshop on Computational vs Statistical Gaps in Learning and Optimization, 2024 UCLA IPAM 2024
- Theory Seminar, 2024, University of Southern California
-
Optimizing Solution-Samplers for Combinatorial Problems, NeurIPS 2023 Oral
-
SLaM: Student-Label Mixing for Distillation with Unlabeled Examples, NeurIPS 2023
-
Learning General Halfspaces with General Massart Noise, STOC 2022
-
A Statistical Taylor’s Theorem and Extrapolation of Truncated Densities, COLT 2021
-
Agnostic Proper Learning of Halfspaces under Gaussian Marginals COLT 2021
-
Efficient Algorithms for Learning Halfspaces with Tsybakov Noise, STOC 2021
-
Non-Convex SGD Learns Halfspaces with Adversarial Label Noise, NeurIPS 2020
-
Learning Halfspaces with Massart Noise Under Structured Distributions, COLT 2020
-
Efficient Truncated Statistics with Unknown Truncation, FOCS 2019, Video
-
Learning PBD Powers, ECCO Research Seminar 2017, University of Liverpool
- Learning Theory Study Group, Corelab NTUA, 2017
- Convex Optimization Minicourse, Corelab NTUA, 2017
- Programming with Dependent Types, NTUA, 2015