archimedes-Artificial Intelligence, Data Science, Algorithms-greece

 
Artificial Intelligence
 
Data Science
 
Algorithms

[Archimedes Talks Series]Efficiently Certifiable Guarantees for Learning with Distribution Shift

Dates
2025-01-08 14:30 - 16:00
Venue
Artemidos 1 - Amphitheater
TITLE: Efficiently Certifiable Guarantees for Learning with Distribution Shift

SPEAKER: Kostas Stavropoulos (Ph.D. student in Computer Science at UT Austin)

ABSTRACT: Learning in the presence of distribution shift remains a major and challenging problem in machine learning. In this setting, the learner is trained on some labeled training distribution, but evaluated on some other, potentially adversarial, test distribution for which the learner only has unlabeled examples. A long series of works in the past twenty years has focused on giving bounds for the test error in terms of appropriate notions of distance between the training and test distributions. Such distances, however, typically involve enumerations and no efficient algorithms for estimating or even testing such distances are available.

In this talk, we present a new model called testable learning with distribution shift, where the learner is allowed to reject, but only if distribution shift is detected. If the learner accepts, then the output hypothesis is guaranteed to have low test error. In this framework, we provide the first efficient algorithms for learning several fundamental concept classes in the presence of distribution shift under standard assumptions on the training marginal distribution. The classes we capture include halfspace intersections, decision trees and, in general, any class that admits low-degree sandwiching approximators.

REFERENCES: https://arxiv.org/abs/2311.15142 , https://arxiv.org/abs/2404.02364 , https://arxiv.org/abs/2406.09373 , https://arxiv.org/abs/2406.02742 

SHORT BIO: Kostas Stavropoulos ( https://www.kstavrop.com ) is currently a fourth-year Ph.D. student in Computer Science at UT Austin. He is fortunate to be advised by Prof. Adam Klivans. Before that, he studied Electrical and Computer Engineering at the National Technical University of Athens, where he was fortunate to work with Prof. Dimitris Fotakis. His research is in the intersection of machine learning and theoretical computer science. He is 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.


________________________________________________________________________________
Microsoft Teams Need help?
Join the meeting now
Meeting ID: 364 928 182 762
Passcode: w24fHy
________________________________________________________________________________

 
 

Vision

To position Greece as a leading player in AI and Data Science

image
image

Mission

To build an AI Excellence Hub in Greece where the international research community can connect, groundbreaking ideas can thrive, and the next generation of scientists emerges, shaping a brighter future for Greece and the world

 

ARCHIMEDES IMPACT

Research

Education

Figures as of October 2026

HIGHLIGHTS

ERC Grant: Christos Papadimitriou will lead the NEAGT project (starting 2026) on strategic interactions and computational decision-making, opening new directions for algorithmic game theory
Archimedes Talks: Michael I. Jordan (Inria Paris; UC Berkeley) on “Nonnegative Supermartingales, Sequential Testing, and Statistical Contract Theory”, 10 February 2026
Archimedes Talks: Paul Goldberg (University of Oxford) on “Complexity of Unambiguous Problems in Σ₂ᴾ”, 4 February 2026
ERC Grant: Christos Tzamos leads the COMFORMAL project (launched 2025) on rigorous foundations for robust and efficient machine learning algorithms
Archimedes Talks: Mark Girolami (The Alan Turing Institute; University of Cambridge) on “Statistical Finite Element Methods”, 7 November 2025
Archimedes Talks: Mihalis Yannakakis (Columbia University) on “Computing a Fixed Point of Contraction Maps in Polynomial Queries”, 25 June 2025

Highlights will be added soon.

 

NEWS

 
Archimedes at NeurIPS 2026

Archimedes at NeurIPS 2026

9 October 2026

Archimedes members will present 23 papers at the Conference on Neural Information Processing Systems (NeurIPS 2026), one of the world’s leading AI conferences: one oral, three spotlights and 19 posters.

Archimedes at ECCV 2026

Archimedes at ECCV 2026

9 October 2026

Archimedes members presented five papers at the European Conference on Computer Vision (ECCV 2026), held on 8–12 September 2026 in Malmö, Sweden: four in the main conference and one oral presentation at a workshop. Archimedes researchers also helped co-organize two workshops.

Archimedes at Greeks in AI 2026

Archimedes at Greeks in AI 2026

9 October 2026

Archimedes took part in Greeks in AI 2026, the annual symposium that brings together distinguished Greek AI scientists from around the world to exchange ideas, share their work and strengthen connections across the global AI community. The symposium was held on 15–17 July 2026 at the Eugenides Foundation in Athens.

Six Medals for the Greek National AI Team at EUROAI and IOAI 2026

Six Medals for the Greek National AI Team at EUROAI and IOAI 2026

9 October 2026

The Greek national team achieved outstanding results at the European Olympiad in Artificial Intelligence (EUROAI) and the International Olympiad in Artificial Intelligence (IOAI) 2026, winning six medals in total. The team was supported by Archimedes and the Greek Olympiad in Artificial Intelligence (PDTN).

More news items here
 
 

The project “ARCHIMEDES Unit: Research in Artificial Intelligence, Data Science and Algorithms” with code OPS 5154714 is implemented by the National Recovery and Resilience Plan “Greece 2.0” and is funded by the European Union – NextGenerationEU.

Greece 2.0 – Funded by the European Union – NextGenerationEU

 

 

Stay connected! Subscribe to our mailing list by emailing sympa@lists.athenarc.gr
with the subject "subscribe archimedes-news Firstname LastName"
(replace with your details)