no code implementations • 29 May 2024 • Prakhar Ganesh, Cuong Tran, Reza Shokri, Ferdinando Fioretto
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.
no code implementations • 28 May 2024 • Saswat Das, Marco Romanelli, Cuong Tran, Zarreen Reza, Bhavya Kailkhura, Ferdinando Fioretto
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.
no code implementations • 6 Dec 2023 • Sree Harsha Nelaturu, Nishaanth Kanna Ravichandran, Cuong Tran, Sara Hooker, Ferdinando Fioretto
In the machine learning ecosystem, hardware selection is often regarded as a mere utility, overshadowed by the spotlight on algorithms and data.
no code implementations • 19 May 2023 • 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 and a "student" model.
no code implementations • 31 Jan 2023 • 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' information to carry out inference.
no code implementations • 21 Nov 2022 • Cuong Tran, Keyu Zhu, Ferdinando Fioretto, Pascal Van Hentenryck
The remarkable performance of deep learning models and their applications in consequential domains (e. g., facial recognition) introduces important challenges at the intersection of equity and security.
no code implementations • 26 May 2022 • Cuong Tran, Ferdinando Fioretto, Jung-eun Kim, Rakshit Naidu
Network pruning is a widely-used compression technique that is able to significantly scale down overparameterized models with minimal loss of accuracy.
no code implementations • 11 Apr 2022 • Cuong Tran, Keyu Zhu, Ferdinando Fioretto, Pascal Van Hentenryck
A key characteristic of the proposed model is to enable the adoption of off-the-selves and non-private fair models to create a privacy-preserving and fair model.
no code implementations • 16 Feb 2022 • Ferdinando Fioretto, Cuong Tran, Pascal Van Hentenryck, Keyu Zhu
This paper surveys recent work in the intersection of differential privacy (DP) and fairness.
no code implementations • NeurIPS 2021 • Cuong Tran, My Dinh, Ferdinando Fioretto
However, it was recently observed that DP learning systems may exacerbate bias and unfairness for different groups of individuals.
no code implementations • 17 Sep 2021 • Cuong Tran, My H. Dinh, Kyle Beiter, Ferdinando Fioretto
The Private Aggregation of Teacher Ensembles (PATE) is an important private machine learning framework.
no code implementations • 4 Jun 2021 • Cuong Tran, My H. Dinh, Ferdinando Fioretto
However, it was recently observed that DP learning systems may exacerbate bias and unfairness for different groups of individuals.
no code implementations • 2 Jun 2021 • Anudit Nagar, Cuong Tran, Ferdinando Fioretto
Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets.
no code implementations • 16 May 2021 • 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.
no code implementations • 26 Sep 2020 • 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.
no code implementations • 26 Jan 2020 • Ferdinando Fioretto, Pascal Van Hentenryck, Terrence WK Mak, Cuong Tran, Federico Baldo, Michele Lombardi
In energy domains, the combination of Lagrangian duality and deep learning can be used to obtain state-of-the-art results to predict optimal power flows, in energy systems, and optimal compressor settings, in gas networks.
no code implementations • 30 Jun 2015 • 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.