iiinova — where your digital self keeps evolving

Omri Ben-Dov

@omribendov.bsky.social

19 followers 41 following 4 posts

PhD student at the Max Planck Institute for Intelligent Systems beomri.github.io

Posts Replies Media

Reposted by Omri Ben-Dov

Johannes Zenn @johanneszenn.bsky.social · 12/03/2026

A new recording of our FridayTalks@Tübingen series is online! Adaptive Symmetrization of the KL Divergence by @omribendov.bsky.social Watch here: youtu.be/VPu1Rd4TmkU

youtu.be

Adaptive Symmetrization of the KL Divergence - [Omri Ben-Dov]

YouTube video by Friday Talks Tübingen

131

Reposted by Omri Ben-Dov

Yatong Chen @yatongchen.bsky.social · 22/09/2025

We (w/ Moritz Hardt, Olawale Salaudeen and @joavanschoren.bsky.social) are organizing the Workshop on the Science of Benchmarking & Evaluating AI @euripsconf.bsky.social 2025 in Copenhagen! 📢 Call for Posters: rb.gy/kyid4f 📅 Deadline: Oct 10, 2025 (AoE) 🔗 More info: rebrand.ly/bg931sf

1217

Omri Ben-Dov @omribendov.bsky.social · 22/08/2025

We also evaluate our methods and theoretically analyze their limitations. Read the full preprint here: arxiv.org/abs/2508.15374 Authors: Omri Ben-Dov, Samira Samadi, @amartyasanyal.bsky.social, @alext2.bsky.social We hope this paper inspires new research into user-side bias mitigation. (4/4)

Our proposed method are more efficient (requiring less label flips) than random flipping to arrive at the same level of fairness

000

Omri Ben-Dov @omribendov.bsky.social · 22/08/2025

How do user-side methods compare with firm-side fair learning? Weakness: User-side generally cannot reach perfect fairness, while firm-side can. Strength: User-side methods have a smaller accuracy cost than firm-side algorithms. (3/4)

100

Omri Ben-Dov @omribendov.bsky.social · 22/08/2025

We show how algorithmic collective action can align with fairness, leading the collective to a relabeling strategy. To approximate the correct labels, we propose three model-agnostic methods. Across several datasets, 20-30% of the minority is enough to achieve the best possible fairness. (2/4)

110

Omri Ben-Dov @omribendov.bsky.social · 22/08/2025

In our new work we ask: Can end-users make a platform’s ML models fairer? Firm-side fair learning often reduces accuracy, discouraging firms from using it. But if a platform relies on user data, can minority users collectively change the data to induce fairness? (1/4)

A classifier has an error of 0.15 and unfairness violation of 0.13, while the same classifier, on data with 6 relabeled samples, have the the same error but 0.03 fairness violation.

112