Portrait de Oussama Boussif

Oussama Boussif

Représentant du laboratoire
Doctorat
Sujets de recherche
Apprentissage de la programmation
Apprentissage profond
Modèles génératifs
Modèles probabilistes
Modélisation moléculaire
Raisonnement

Biographie

Je suis actuellement doctorant dans le laboratoire du professeur Yoshua Bengio. Je travaille actuellement sur la création de modèles interprétables et vérifiables pour accélérer les découvertes scientifiques. Quand je ne fais pas de recherche, vous pouvez me trouver en train de jouer du piano ou du saxophone, ou encore en train de courir sur un terrain de football pour marquer des buts.

Publications

Action abstractions for amortized sampling
Lena Nehale Ezzine
Joseph D Viviano
Michał Koziarski
Moksh J. Jain
Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context
Ghait Boukachab
Dan Assouline
Stefano Massaroli
Tianle Yuan
Solar power harbors immense potential in mitigating climate change by substantially reducing CO…
What if We Enrich day-ahead Solar Irradiance Time Series Forecasting with Spatio-Temporal Context?
Ghait Boukachab
Dan Assouline
Stefano Massaroli
Tianle Yuan
The global integration of solar power into the electrical grid could have a crucial impact on climate change mitigation, yet poses a challen… (voir plus)ge due to solar irradiance variability. We present a deep learning architecture which uses spatio-temporal context from satellite data for highly accurate day-ahead time-series forecasting, in particular Global Horizontal Irradiance (GHI). We provide a multi-quantile variant which outputs a prediction interval for each time-step, serving as a measure of forecasting uncertainty. In addition, we suggest a testing scheme that separates easy and difficult scenarios, which appears useful to evaluate model performance in varying cloud conditions. Our approach exhibits robust performance in solar irradiance forecasting, including zero-shot generalization tests at unobserved solar stations, and holds great promise in promoting the effective use of solar power and the resulting reduction of CO
What if We Enrich day-ahead Solar Irradiance Time Series Forecasting with Spatio-Temporal Context?
Ghait Boukachab
Dan Assouline
Stefano Massaroli
Tianle Yuan
Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
Dianbo Liu
Cristian Meo
Anirudh Goyal
Tianmin Shu
Michael Curtis Mozer
Nicolas Heess
MAgNet: Mesh Agnostic Neural PDE Solver
The computational complexity of classical numerical methods for solving Partial Differential Equations (PDE) scales significantly as the res… (voir plus)olution increases. As an important example, climate predictions require fine spatio-temporal resolutions to resolve all turbulent scales in the fluid simulations. This makes the task of accurately resolving these scales computationally out of reach even with modern supercomputers. As a result, current numerical modelers solve PDEs on grids that are too coarse (3km to 200km on each side), which hinders the accuracy and usefulness of the predictions. In this paper, we leverage the recent advances in Implicit Neural Representations (INR) to design a novel architecture that predicts the spatially continuous solution of a PDE given a spatial position query. By augmenting coordinate-based architectures with Graph Neural Networks (GNN), we enable zero-shot generalization to new non-uniform meshes and long-term predictions up to 250 frames ahead that are physically consistent. Our Mesh Agnostic Neural PDE Solver (MAgNet) is able to make accurate predictions across a variety of PDE simulation datasets and compares favorably with existing baselines. Moreover, MAgNet generalizes well to different meshes and resolutions up to four times those trained on.
Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
Dianbo Liu
Cristian Meo
Anirudh Goyal
Tianmin Shu
Michael Curtis Mozer
Nicolas Heess
In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one a… (voir plus)nother. In this paper, we propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents’ collective performance. To ensure that this facilitator does not become a centralized controller, agents are incentivized to reduce their dependence on the messages it conveys, and the messages can only influence the selection of a policy from a fixed set, not instantaneous actions given the policy. We demonstrate the strength of this architecture over existing baselines on several cooperative MARL environments.