no code implementations • 1 Apr 2024 • Ethan King, James Kotary, Ferdinando Fioretto, Jan Drgona
Recent work has shown a variety of ways in which machine learning can be used to accelerate the solution of constrained optimization problems.
no code implementations • 6 Mar 2024 • James Kotary, Ferdinando Fioretto
Learning to Optimize (LtO) is a problem setting in which a machine learning (ML) model is trained to emulate a constrained optimization solver.
no code implementations • 12 Feb 2024 • My H Dinh, James Kotary, Ferdinando Fioretto
Many decision processes in artificial intelligence and operations research are modeled by parametric optimization problems whose defining parameters are unknown and must be inferred from observable data.
no code implementations • 7 Feb 2024 • My H. Dinh, James Kotary, Ferdinando Fioretto
Learning to Rank (LTR) is one of the most widely used machine learning applications.
no code implementations • 6 Feb 2024 • Saswat Das, Marco Romanelli, Ferdinando Fioretto
Ensuring privacy-preserving inference on cryptographically secure data is a well-known computational challenge.
no code implementations • 5 Feb 2024 • Jacob K Christopher, Stephen Baek, Ferdinando Fioretto
Generative diffusion models excel at robustly synthesizing coherent content from raw noise through a sequential process.
no code implementations • 28 Dec 2023 • James Kotary, Jacob Christopher, My H Dinh, Ferdinando Fioretto
The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks.
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 • 22 Nov 2023 • James Kotary, Vincenzo Di Vito, Jacob Christopher, Pascal Van Hentenryck, Ferdinando Fioretto
This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by predictive models.
no code implementations • 2 Aug 2023 • Vladimir Dvorkin, Ferdinando Fioretto
While deep learning gradually penetrates operational planning, its inherent prediction errors may significantly affect electricity prices.
1 code implementation • 25 Jul 2023 • Jayanta Mandi, James Kotary, Senne Berden, Maxime Mulamba, Victor Bucarey, Tias Guns, Ferdinando Fioretto
Decision-focused learning (DFL) is an emerging paradigm in machine learning which trains a model to optimize decisions, integrating prediction and optimization in an end-to-end system.
no code implementations • 25 May 2023 • Khang Tran, Ferdinando Fioretto, Issa Khalil, My T. Thai, NhatHai Phan
This paper introduces FairDP, a novel mechanism designed to achieve certified fairness with differential privacy (DP).
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 • 28 Jan 2023 • Keyu Zhu, Ferdinando Fioretto, Pascal Van Hentenryck, Saswat Das, Christine Task
The results show that, contrary to popular beliefs, traditional differential privacy techniques may be superior in terms of accuracy and fairness to differential private counterparts of widely used DA mechanisms.
no code implementations • 28 Jan 2023 • James Kotary, My H. Dinh, Ferdinando Fioretto
A central challenge in this setting is backpropagation through the solution of an optimization problem, which typically lacks a closed form.
no code implementations • 28 Jan 2023 • My H. Dinh, Ferdinando Fioretto
The remarkable ability of language models (LMs) has also brought challenges at the interface of AI and security.
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.
1 code implementation • 1 Nov 2022 • James Kotary, Vincenzo Di Vito, Ferdinando Fioretto
Model selection is a strategy aimed at creating accurate and robust models.
no code implementations • 21 Jun 2022 • Mostafa Mohammadian, Kyri Baker, Ferdinando Fioretto
The application of deep learning methods to speed up the resolution of challenging power flow problems has recently shown very encouraging results.
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 • 10 Feb 2022 • Sawinder Kaur, Ferdinando Fioretto, Asif Salekin
The ability of Deep Neural Networks to approximate highly complex functions is key to their success.
no code implementations • 25 Jan 2022 • Lesia Mitridati, Emma Romei, Gabriela Hug, Ferdinando Fioretto
Sector coordination between heat and electricity systems has been identified has an energy-efficient and cost-effective way to transition towards a more sustainable energy system.
no code implementations • 24 Jan 2022 • Keyu Zhu, Ferdinando Fioretto, Pascal Van Hentenryck
Post-processing immunity is a fundamental property of differential privacy: it enables arbitrary data-independent transformations to differentially private outputs without affecting their privacy guarantees.
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 • 22 Nov 2021 • My H. Dinh, Ferdinando Fioretto, Mostafa Mohammadian, Kyri Baker
Optimal Power Flow (OPF) is a fundamental problem in power systems.
no code implementations • 21 Nov 2021 • James Kotary, Ferdinando Fioretto, Pascal Van Hentenryck, Ziwei Zhu
The end-to-end SPOFR framework includes a constrained optimization sub-model and produces ranking policies that are guaranteed to satisfy fairness constraints while allowing for fine control of the fairness-utility tradeoff.
no code implementations • 12 Oct 2021 • James Kotary, Ferdinando Fioretto, Pascal Van Hentenryck
The Jobs shop Scheduling Problem (JSP) is a canonical combinatorial optimization problem that is routinely solved for a variety of industrial purposes.
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 • NeurIPS 2021 • James Kotary, Ferdinando Fioretto, Pascal Van Hentenryck
Optimization problems are ubiquitous in our societies and are present in almost every segment of the economy.
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 • 30 Mar 2021 • James Kotary, Ferdinando Fioretto, Pascal Van Hentenryck, Bryan Wilder
This paper surveys the recent attempts at leveraging machine learning to solve constrained optimization problems.
no code implementations • 11 Jan 2021 • Terrence W. K. Mak, Ferdinando Fioretto, Pascal VanHentenryck
The AC Optimal Power Flow (AC-OPF) problem is a core building block in electrical transmission system.
no code implementations • 9 Oct 2020 • Keyu Zhu, Pascal Van Hentenryck, Ferdinando Fioretto
Moreover, when the feasible region is convex, a widely adopted class of post-processing steps is also guaranteed to improve accuracy.
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 • 29 Jun 2020 • Minas Chatzos, Ferdinando Fioretto, Terrence W. K. Mak, Pascal Van Hentenryck
It is non-convex and NP-hard, and computationally challenging for large-scale power systems.
BIG-bench Machine Learning Vocal Bursts Intensity Prediction
no code implementations • 28 Jun 2020 • Ferdinando Fioretto, Pascal Van Hentenryck, Keyu Zhu
To address them, this paper presents a novel differential-privacy mechanism for releasing hierarchical counts of individuals.
1 code implementation • 22 Jun 2020 • Vladimir Dvorkin, Ferdinando Fioretto, Pascal Van Hentenryck, Jalal Kazempour, Pierre Pinson
This paper develops a novel differentially private framework to solve convex optimization problems with sensitive optimization data and complex physical or operational constraints.
no code implementations • 26 Jan 2020 • Terrence W. K. Mak, Ferdinando Fioretto, Pascal Van Hentenryck
This paper studies how to apply differential privacy to constrained optimization problems whose inputs are sensitive.
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 • 19 Sep 2019 • Ferdinando Fioretto, Terrence W. K. Mak, Pascal Van Hentenryck
The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems.
no code implementations • 23 May 2019 • Ferdinando Fioretto, Terrence W. K. Mak, Pascal Van Hentenryck
The paper studies how to release data about a critical infrastructure network (e. g., the power network or a transportation network) without disclosing sensitive information that can be exploited by malevolent agents, while preserving the realism of the network.
1 code implementation • 21 Jan 2019 • Ferdinando Fioretto, Terrence W. K. Mak, Pascal Van Hentenryck
To address these concerns, this paper presents a novel differential privacy mechanism that guarantees AC-feasibility and largely preserves the fidelity of the obfuscated network.
no code implementations • 6 Aug 2018 • Ferdinando Fioretto, Pascal Van Hentenryck
Then, the perturbation module adds noise to the sampled data points to guarantee privacy.
no code implementations • 22 Feb 2017 • Ferdinando Fioretto, Agostino Dovier, Enrico Pontelli, William Yeoh, Roie Zivan
The field of Distributed Constraint Optimization has gained momentum in recent years, thanks to its ability to address various applications related to multi-agent cooperation.
no code implementations • 22 Feb 2017 • William Kluegel, Muhammad Aamir Iqbal, Ferdinando Fioretto, William Yeoh, Enrico Pontelli
The field of Distributed Constraint Optimization has gained momentum in recent years thanks to its ability to address various applications related to multi-agent cooperation.
1 code implementation • 18 Aug 2016 • Ferdinando Fioretto, Enrico Pontelli, William Yeoh, Rina Dechter
Discrete optimization is a central problem in artificial intelligence.
no code implementations • 20 Feb 2016 • Ferdinando Fioretto, Enrico Pontelli, William Yeoh
The field of Multi-Agent System (MAS) is an active area of research within Artificial Intelligence, with an increasingly important impact in industrial and other real-world applications.