Portrait de Michel Côté

Michel Côté

Membre académique associé
Université de Montréal
Sujets de recherche
Modélisation moléculaire
Physique computationnelle
Physique de la matière condensée
Google Scholar

Étudiants actuels

Olivier Nadeau
Postdoctorat - UdeM
Dounia Shaaban Kabakibo
Doctorat - UdeM
Co-superviseur⋅e :
Alex Hernández-García
Github
Google Scholar
Surya Prasad Timilsina
Doctorat - UdeM
Google Scholar

Publications

Bayesian Last Layer for Neural Force Fields
David Nitchi
Daniel T. Levy
Michel Côté
Siamak Ravanbakhsh
Reliable uncertainty quantification is essential for deploying Machine Learning Interatomic Potentials (MLIPs), also known as Neural Force F… (voir plus)ields, especially when molecular dynamics or materials simulations encounter configurations outside the training distribution. Deep ensembles remain the strongest practical baseline for MLIP uncertainty, but training and storing several copies of a modern pretrained model is often prohibitively expensive. We show that Bayesian Linear Last Layers (BLLs) provide a scalable alternative for MLIPs: a single pretrained backbone supplies atomic features, while exact Bayesian inference over the final force-prediction layer gives predictive uncertainties. BLL is known to underestimate the uncertainties. We provide an in-depth analysis that shows two sources of miscalibration and introduce a simple post-hoc recalibration to address the issue. On MPtrj and rMD17 benchmarks, including both in-distribution tests and increasingly out-of-distribution regimes, BLLs that are recalibrated on in-distribution examples produce uncertainty estimates competitive with ensembles, while using only one base model.
2026-05-29
AI4Science @ International Conference on Machine Learning (poster)
openreview.net
openreview.net
Magnetic phases of the anisotropic triangular Hubbard model from the ghost-Gutzwiller approximation in the rotating spin-frame
Azin Kazemi-Moridani
Samuele Giuli
Tsung-Han Lee
A. -M. S. Tremblay
Michel Côté
Nicola Lanatà
Olivier Gingras
We investigate the magnetic phase diagram of the half-filled Hubbard model on the anisotropic triangular lattice using the Gutzwiller approx… (voir plus)imation (GA) and its ghost generalization (ghost-GA). By combining a rotating spin-frame formulation with high-resolution momentum grids, we determine magnetic ground states through direct total-energy minimization over the ordering wavevector. We benchmark standard GA and ghost-GA against dynamical mean-field theory (DMFT) and dual-fermion results. We show that GA already captures the qualitative structure of the phase diagram, but systematically overestimates the stability of magnetic order due to the absence of dynamical fluctuations. We find that introducing a small number of auxiliary ''ghost'' orbitals is sufficient to recover most dynamical effects and significantly improves quantitative agreement with DMFT. Exploring the full Brillouin zone, we obtain a phase diagram comprising paramagnetic and various magnetic phases. In contrast to ladder dual-fermion susceptibility-based predictions, we find that the one-dimensional antiferromagnetic phase is never stabilized, despite being the leading instability in certain regimes. Our results establish ghost-GA as an efficient and systematically improvable framework for studying magnetism in frustrated systems, capable of achieving near-DMFT accuracy at a fraction of the computational cost. They also highlight that standard GA performs qualitatively well for capturing the general phase diagram, enabling the investigation of incommensurate magnetic orders in more complex systems.
2026-04-26
arXiv (inconnu)
doi.org
arxiv.org
A Comparative Study of Molecular Dynamics Approaches for Simulating Ionic Conductivity in Solid Lithium Electrolytes
Dounia Shaaban Kabakibo
Félix Therrien
Yoshua Bengio
Michel Côté
Hongyu Guo
Homin Shin
Alex Hernández-García
Accurate prediction of ionic conductivity is critical for the design of highperformance solid-state electrolytes in next-generation batterie… (voir plus)s. We benchmark molecular dynamics (MD) approaches for computing ionic conductivity in 21 lithium solid electrolytes for which experimental ionic conductivity has been previously reported in the literature. Specifically, we compare simulations driven by density functional theory (DFT) and by universal machine-learning interatomic potentials (uMLIPs), namely a MACE foundation model. Our results suggest comparable performance between DFT and MACE, with MACE requiring only a fraction of the computational cost. The framework developed here is designed to enable systematic comparisons with additional uMLIPs and fine-tuned models in future work.
2026-03-01
AI4Mat @ International Conference on Learning Representations (poster)
openreview.net
openreview.net
Opposite impact of thermal expansion and phonon anharmonicity on the phonon-limited resistivity of elemental metals from first principles
Ao Wang
Junwen Yin
Félix Antoine Goudreault
Michel Côté
Olle Hellman
Samuel Poncé
Understanding electrical resistivity in metals remains a central challenge in quantifying charge transport at finite temperature. Current fi… (voir plus)rst-principles calculations based on the Boltzmann transport equation often match experiments, yet they almost always neglect the effect of thermal expansion and phonon anharmonicity. We show that both effects exert an opposite impact on electron-phonon coupling and on electrical resistivity. Thermal expansion enhances the coupling and leads to overestimation of resistivity, whereas anharmonic effects reduce it. By explicitly incorporating both effects, we establish a more complete description of resistivity in elemental metals, demonstrated here for Pb, Nb, and Al.
2026-02-01
Physical Review B (publié)
doi.org
arxiv.org
Large scale Raman spectrum calculations in defective 2D materials using deep learning
Olivier Malenfant-Thuot
Dounia Shaaban Kabakibo
Simon Blackburn
Bruno Rousseau
Michel Côté
We introduce a machine learning prediction workflow to study the impact of defects on the Raman response of 2D materials. By combining the u… (voir plus)se of machine-learned interatomic potentials, the Raman-active Γ-weighted density of states method and splitting configurations in independant patches, we are able to reach simulation sizes in the tens of thousands of atoms, with diagonalization now being the main bottleneck of the simulation. We apply the method to two systems, isotopic graphene and defective hexagonal boron nitride, and compare our predicted Raman response to experimental results, with good agreement. Our method opens up many possibilities for future studies of Raman response in solid-state physics.
2024-12-17
Journal of Physics: Condensed Matter (publié)
doi.org
arxiv.org