45 citations · 81 across the 15 of their papers we have counts for
17 papers
The Data Minimization Principle in Machine Learning
Prakhar Ganesh, Cuong Tran, Reza Shokri +1
The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches. R…
Low-rank finetuning for LLMs: A fairness perspective
Saswat Das, Marco Romanelli, Cuong Tran +3
Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models (LLMs) due to their reduced computational and memory requirements. This pa…
On The Fairness Impacts of Hardware Selection in Machine Learning
Sree Harsha Nelaturu, Nishaanth Kanna Ravichandran, Cuong Tran +2
In the machine learning ecosystem, hardware selection is often regarded as a mere utility, overshadowed by the spotlight on algorithms and data. This oversight is particularly prob…
Data Minimization at Inference Time
Cuong Tran, Ferdinando Fioretto
In domains with high stakes such as law, recruitment, and healthcare, learning models frequently rely on sensitive user data for inference, necessitating the complete set of featur…
On the Fairness Impacts of Private Ensembles Models
Cuong Tran, Ferdinando Fioretto
The Private Aggregation of Teacher Ensembles (PATE) is a machine learning framework that enables the creation of private models through the combination of multiple "teacher" models…
Personalized Privacy Auditing and Optimization at Test Time
Cuong Tran, Ferdinando Fioretto
A number of learning models used in consequential domains, such as to assist in legal, banking, hiring, and healthcare decisions, make use of potentially sensitive users' informati…
Fairness Increases Adversarial Vulnerability
Cuong Tran, Keyu Zhu, Ferdinando Fioretto +1
The remarkable performance of deep learning models and their applications in consequential domains (e.g., facial recognition) introduces important challenges at the intersection of…
Pruning has a disparate impact on model accuracy
Cuong Tran, Ferdinando Fioretto, Jung-Eun Kim +1
Network pruning is a widely-used compression technique that is able to significantly scale down overparameterized models with minimal loss of accuracy. This paper shows that prunin…
SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles
Cuong Tran, Keyu Zhu, Ferdinando Fioretto +1
A critical concern in data-driven processes is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure no…
Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey
Ferdinando Fioretto, Cuong Tran, Pascal Van Hentenryck +1
This paper surveys recent work in the intersection of differential privacy (DP) and fairness. It reviews the conditions under which privacy and fairness may have aligned or contras…
A Fairness Analysis on Private Aggregation of Teacher Ensembles
Cuong Tran, My H. Dinh, Kyle Beiter +1
The Private Aggregation of Teacher Ensembles (PATE) is an important private machine learning framework. It combines multiple learning models used as teachers for a student model th…
A Privacy-Preserving and Trustable Multi-agent Learning Framework
Anudit Nagar, Cuong Tran, Ferdinando Fioretto
Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets. While this setting ensures some level of privacy, it has b…
Decision Making with Differential Privacy under a Fairness Lens
Ferdinando Fioretto, Cuong Tran, Pascal Van Hentenryck
Agencies, such as the U.S. Census Bureau, release data sets and statistics about groups of individuals that are used as input to a number of critical decision processes. To conform…
Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach
Cuong Tran, Ferdinando Fioretto, Pascal Van Hentenryck
A critical concern in data-driven decision making is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ens…
Lagrangian Duality for Constrained Deep Learning
Ferdinando Fioretto, Pascal Van Hentenryck, Terrence WK Mak +3
This paper explores the potential of Lagrangian duality for learning applications that feature complex constraints. Such constraints arise in many science and engineering domains,…
Unsupervised Domain Adaptation with Copula Models
Cuong D. Tran, Ognjen Rudovic, Vladimir Pavlovic
We study the task of unsupervised domain adaptation, where no labeled data from the target domain is provided during training time. To deal with the potential discrepancy between t…
Gaussian Process for Noisy Inputs with Ordering Constraints
Cuong Tran, Vladimir Pavlovic, Robert Kopp
We study the Gaussian Process regression model in the context of training data with noise in both input and output. The presence of two sources of noise makes the task of learning…