Publications

Ex Post Conditions for the Exactness of Optimal Power Flow Conic Relaxations
Jean-Luc Lupien
Antoine Lesage-Landry
Convex relaxations of the optimal power flow (OPF) problem provide an efficient alternative to solving the intractable alternating current (… (see more)AC) optimal power flow. The conic subset of OPF convex relaxations, in particular, greatly accelerate resolution while leading to high-quality approximations that are exact in several scenarios. However, the sufficient conditions guaranteeing exactness are stringent, e.g., requiring radial topologies. In this short communication, we present two equivalent ex post conditions for the exactness of any conic relaxation of the OPF. These rely on obtaining either a rank-1 voltage matrix or self-coherent cycles. Instead of relying on sufficient conditions a priori, satisfying one of the presented ex post conditions acts as an exactness certificate for the computed solution. The operator can therefore obtain an optimality guarantee when solving a conic relaxation even when a priori exactness requirements are not met. Finally, we present numerical examples from the MATPOWER library where the ex post conditions hold even though the exactness sufficient conditions do not, thereby illustrating the use of the conditions.
2025-01-01
Electric Power Systems Research (published)
doi.org
arxiv.org
A stochastic integer programming approach to reserve staff scheduling with preferences
Carl Perreault‐Lafleur
Margarida Carvalho
Guy Desaulniers
2025-01-01
Int. Trans. Oper. Res. (published)
doi.org
arxiv.org
Combining supervised learning and local search for the multicommodity capacitated fixed-charge network design problem
Charly Robinson La Rocca
Jean-François Cordeau
Emma Frejinger
The multicommodity capacitated fixed-charge network design problem has been extensively studied in the literature due to its wide range of a… (see more)pplications. Despite the fact that many sophisticated solution methods exist today, finding high-quality solutions to large-scale instances remains challenging. In this paper, we explore how a data-driven approach can help improve upon the state of the art. By leveraging machine learning models, we attempt to reveal patterns hidden in the data that might be difficult to capture with traditional optimization methods. For scalability, we propose a prediction method where the machine learning model is called at the level of each arc of the graph. We take advantage of off-the-shelf models trained via supervised learning to predict near-optimal solutions. Our experimental results include an algorithm design analysis that compares various integration strategies of predictions within local search algorithms. We benchmark the ML-based approach with respect to the state-of-the-art heuristic for this problem. The findings indicate that our method can outperform the leading heuristic on sets of instances sampled from a uniform distribution.
2024-12-01
Transportation Research Part E: Logistics and Transportation Review (published)
doi.org
arxiv.org
SpeechBrain-MOABB: An open-source Python library for benchmarking deep neural networks applied to EEG signals
Davide Borra
Francesco Paissan
Mirco Ravanelli
2024-11-01
Computers in Biology and Medicine (published)
doi.org
Structured Pruning of Neural Networks for Constraints Learning
Matteo Cacciola
Antonio Frangioni
Andrea Lodi
In recent years, the integration of Machine Learning (ML) models with Operation Research (OR) tools has gained popularity across diverse app… (see more)lications, including cancer treatment, algorithmic configuration, and chemical process optimization. In this domain, the combination of ML and OR often relies on representing the ML model output using Mixed Integer Programming (MIP) formulations. Numerous studies in the literature have developed such formulations for many ML predictors, with a particular emphasis on Artificial Neural Networks (ANNs) due to their significant interest in many applications. However, ANNs frequently contain a large number of parameters, resulting in MIP formulations that are impractical to solve, thereby impeding scalability. In fact, the ML community has already introduced several techniques to reduce the parameter count of ANNs without compromising their performance, since the substantial size of modern ANNs presents challenges for ML applications as it significantly impacts computational efforts during training and necessitates significant memory resources for storage. In this paper, we showcase the effectiveness of pruning, one of these techniques, when applied to ANNs prior to their integration into MIPs. By pruning the ANN, we achieve significant improvements in the speed of the solution process. We discuss why pruning is more suitable in this context compared to other ML compression techniques, and we identify the most appropriate pruning strategies. To highlight the potential of this approach, we conduct experiments using feed-forward neural networks with multiple layers to construct adversarial examples. Our results demonstrate that pruning offers remarkable reductions in solution times without hindering the quality of the final decision, enabling the resolution of previously unsolvable instances.
2024-11-01
Operations Research Letters (published)
doi.org
arxiv.org
In-Simulation Testing of Deep Learning Vision Models in Autonomous Robotic Manipulators
Dmytro Humeniuk
Houssem Ben Braiek
Thomas Reid
Foutse Khomh
2024-10-27
Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (published)
doi.org
Multi-agent cooperation through learning-aware policy gradients
Alexander Meulemans
Seijin Kobayashi
Johannes von Oswald
Nino Scherrer
Eric Elmoznino
Blake Richards
Guillaume Lajoie
Blaise Agüera y Arcas
João Sacramento
Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation… (see more) among self-interested, independent learning agents? Promising recent work has shown that in certain tasks cooperation can be established between learning-aware agents who model the learning dynamics of each other. Here, we present the first unbiased, higher-derivative-free policy gradient algorithm for learning-aware reinforcement learning, which takes into account that other agents are themselves learning through trial and error based on multiple noisy trials. We then leverage efficient sequence models to condition behavior on long observation histories that contain traces of the learning dynamics of other agents. Training long-context policies with our algorithm leads to cooperative behavior and high returns on standard social dilemmas, including a challenging environment where temporally-extended action coordination is required. Finally, we derive from the iterated prisoner's dilemma a novel explanation for how and when cooperation arises among self-interested learning-aware agents.
2024-10-24
ArXiv (preprint)
arxiv.org
arxiv.org
Structure Language Models for Protein Conformation Generation
Jiarui Lu
Xiaoyin Chen
Stephen Zhewen Lu
Chence Shi
Hongyu Guo
Yoshua Bengio
Jian Tang
2024-10-24
ArXiv (preprint)
arxiv.org
arxiv.org
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
Michael Noukhovitch
Shengyi Huang
Sophie Xhonneux
Arian Hosseini
Rishabh Agarwal
Aaron Courville
The dominant paradigm for RLHF is online and on-policy RL: synchronously generating from the large language model (LLM) policy, labelling wi… (see more)th a reward model, and learning using feedback on the LLM's own outputs. While performant, this paradigm is computationally inefficient. Inspired by classical deep RL literature, we propose separating generation and learning in RLHF. This enables asynchronous generation of new samples while simultaneously training on old samples, leading to faster training and more compute-optimal scaling. However, asynchronous training relies on an underexplored regime, online but off-policy RLHF: learning on samples from previous iterations of our model. To understand the challenges in this regime, we investigate a fundamental question: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? Among several RLHF algorithms we tested, we find that online DPO is most robust to off-policy data, and robustness increases with the scale of the policy model. We study further compute optimizations for asynchronous RLHF but find that they come at a performance cost, giving rise to a trade-off. Finally, we verify the scalability of asynchronous RLHF by training LLaMA 3.1 8B on an instruction-following task 40% faster than a synchronous run while matching final performance.
2024-10-23
ArXiv (preprint)
arxiv.org
arxiv.org
Multilingual Hallucination Gaps in Large Language Models
Cl'ea Chataigner
Afaf Taïk
Golnoosh Farnadi
Large language models (LLMs) are increasingly used as alternatives to traditional search engines given their capacity to generate text that … (see more)resembles human language. However, this shift is concerning, as LLMs often generate hallucinations, misleading or false information that appears highly credible. In this study, we explore the phenomenon of hallucinations across multiple languages in freeform text generation, focusing on what we call multilingual hallucination gaps. These gaps reflect differences in the frequency of hallucinated answers depending on the prompt and language used. To quantify such hallucinations, we used the FactScore metric and extended its framework to a multilingual setting. We conducted experiments using LLMs from the LLaMA, Qwen, and Aya families, generating biographies in 19 languages and comparing the results to Wikipedia pages. Our results reveal variations in hallucination rates, especially between high and low resource languages, raising important questions about LLM multilingual performance and the challenges in evaluating hallucinations in multilingual freeform text generation.
2024-10-23
ArXiv (preprint)
arxiv.org
arxiv.org
Stick-breaking Attention
Shawn Tan
Yikang Shen
Songlin Yang
Aaron Courville
Rameswar Panda
2024-10-23
ArXiv (preprint)
arxiv.org
arxiv.org
FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptation
Rohan Sukumaran
Aarash Feizi
Adriana Romero-Sorian
Golnoosh Farnadi
2024-10-22
ArXiv (preprint)
arxiv.org
arxiv.org