Charles C. Margossian

According to our database, Charles C. Margossian authored at least 12 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning.

Ningyuan Huang, Richard Stiskalek, Jun-Young Lee, Adrian E. Bayer, Charles C. Margossian, Christian Kragh Jespersen, Lucia A. Perez, Lawrence K. Saul, Francisco Villaescusa-Navarro

CoRR, July, 2025

Variational Inference in Location-Scale Families: Exact Recovery of the Mean and Correlation Matrix.

Charles Margossian, Lawrence K. Saul

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

An Ordering of Divergences for Variational Inference with Factorized Gaussian Approximations.

Charles C. Margossian, Loucas Pillaud-Vivien, Lawrence K. Saul

CoRR, 2024

Amortized Variational Inference: When and Why?

Charles C. Margossian, David M. Blei

Proceedings of the Uncertainty in Artificial Intelligence, 2024

EigenVI: score-based variational inference with orthogonal function expansions.

Diana Cai, Chirag Modi, Charles Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Listening to the noise: Blind Denoising with Gibbs Diffusion.

David Heurtel-Depeiges, Charles Margossian, Ruben Ohana, Bruno Régaldo-Saint Blancard

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Batch and match: black-box variational inference with a score-based divergence.

Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

The Shrinkage-Delinkage Trade-off: an Analysis of Factorized Gaussian Approximations for Variational Inference.

Charles C. Margossian, Lawrence K. Saul

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Variational Inference with Gaussian Score Matching.

Chirag Modi, Robert M. Gower, Charles Margossian, Yuling Yao, David M. Blei, Lawrence K. Saul

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Adaptive Tuning for Metropolis Adjusted Langevin Trajectories.

Lionel Riou-Durand, Pavel Sountsov, Jure Vogrinc, Charles Margossian, Sam Power

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2020

Hamiltonian Monte Carlo using an adjoint-differentiated Laplace approximation: Bayesian inference for latent Gaussian models and beyond.

Charles C. Margossian, Aki Vehtari, Daniel Simpson, Raj Agrawal

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

A review of automatic differentiation and its efficient implementation.

Charles C. Margossian

WIREs Data Mining Knowl. Discov., 2019