AIConfPaper
← Search

Ivan Brugere

8 accepted papers

2026

MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems

Zachary Lazri, Anirudh Nakra, Ivan Brugere, Danial Dervovic, Antigoni Polychroniadou, Furong Huang +2
ICML 2026poster

Algorithmic fairness is often studied in static or single-agent settings, yet many real-world decision-making systems involve multiple interacting entities whose multi-stage actions jointly influence long-term outcomes. Existing fairness methods applied at isolated decision points frequently fail to…

Cited by 0Source ↗Scholar ↗
2026

Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

Yvonne Zhou, Mingyu Liang, Ivan Brugere, Danial Dervovic, Yue Guo, Antigoni Polychroniadou +2
ICML 2026poster

We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training algorithm tailored to encrypted computation. Our approach improves computational efficiency over standard differentially p…

Cited by 0Source ↗Scholar ↗
2025

Calibrating LLM Confidence by Probing Perturbed Representation Stability

Reza Khanmohammadi, Erfan Miahi, Mehrsa Mardikoraem, Simerjot Kaur, Ivan Brugere, Charese Smiley +2
EMNLP 2025

Miscalibration in Large Language Models (LLMs) undermines their reliability, highlighting the need for accurate confidence estimation. We introduce CCPS (Calibrating LLM Confidence by Probing Perturbed Representation Stability), a novel method analyzing internal representational stability in LLMs. C

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

Wenzhuo Tang, Haitao Mao, Danial Dervovic, Ivan Brugere, Saumitra Mishra, Yuying Xie +1
NeurIPS 2025poster

Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the effectiveness of large-scale pre-training on vast amounts of data. However, current graph pre-training methods struggle…

Cited by 0Source ↗code ↗Scholar ↗
2025

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples

Hsiang Hsu, Pradeep Niroula, Zichang He, Ivan Brugere, Freddy Lecue, Chun-Fu Chen
NeurIPS 2025poster

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained models, these guarantees do not naturally extend to model ou…

Cited by 0Source ↗Scholar ↗
2024

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data

Yvonne Zhou, Mingyu Liang, Ivan Brugere, Danial Dervovic, Antigoni Polychroniadou, Min Wu +1
ICML 2024poster

The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset. To prevent leakage of sensitive data, we consider using differentially- private (DP), synthetic training data instead of real…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting

Hsiang Hsu, Ivan Brugere, Shubham Sharma, Freddy Lecue, Chun-Fu Chen
NeurIPS 2024poster

The Rashomon effect is a mixed blessing in responsible machine learning. It enhances the prospects of finding models that perform well in accuracy while adhering to ethical standards, such as fairness or interpretability. Conversely, it poses a risk to the credibility of machine decisions through pr…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions

Leonidas Tsepenekas, Ivan Brugere, Freddy Lecue, Daniele Magazzeni
NeurIPS 2023poster

Similarity functions measure how comparable pairs of elements are, and play a key role in a wide variety of applications, e.g., notions of Individual Fairness abiding by the seminal paradigm of Dwork et al., as well as Clustering problems. However, access to an accurate similarity function should no…

Cited by 1Source ↗PDF ↗Scholar ↗