Charles Margossian — accepted AI-conference papers

2025

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

Ningyuan Teresa Huang, Richard Stiskalek, Jun-Young Lee, Adrian E. Bayer, Charles Margossian, Christian Kragh Jespersen +3

NeurIPS 2025poster

Cosmological simulations provide a wealth of data in the form of point clouds and directed trees. A crucial goal is to extract insights from this data that shed light on the nature and composition of the Universe. In this paper we introduce CosmoBench, a benchmark dataset curated from state-of-the-a…

Cited by 0 Source ↗Scholar ↗

2025

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

Charles Margossian, Lawrence K. Saul

AISTATS 2025oral

Given an intractable target density $p$, variational inference (VI) attempts to find the best approximation $q$ from a tractable family $\mathcal Q$. This is typically done by minimizing the exclusive Kullback-Leibler divergence, $\text{KL}(q||p)$. In practice, $\mathcal Q$ is not rich enough to con…

Cited by 0 Source ↗code ↗Scholar ↗

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 Blei +1

ICML 2024spotlight

Most leading implementations of black-box variational inference (BBVI) are based on optimizing a stochastic evidence lower bound (ELBO). But such approaches to BBVI often converge slowly due to the high variance of their gradient estimates and their sensitivity to hyperparameters. In this work, we p…

Cited by 7 Source ↗PDF ↗Scholar ↗

2024

EigenVI: score-based variational inference with orthogonal function expansions

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

NeurIPS 2024spotlight

We develop EigenVI, an eigenvalue-based approach for black-box variational inference (BBVI). EigenVI constructs its variational approximations from orthogonal function expansions. For distributions over $\mathbb{R}^D$, the lowest order term in these expansions provides a Gaussian variational approxi…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

Listening to the noise: Blind Denoising with Gibbs Diffusion

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

ICML 2024poster

In recent years, denoising problems have become intertwined with the development of deep generative models. In particular, diffusion models are trained like denoisers, and the distribution they model coincide with denoising priors in the Bayesian picture. However, denoising through diffusion-based p…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Adaptive Tuning for Metropolis Adjusted Langevin Trajectories

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

AISTATS 2023poster

Hamiltonian Monte Carlo (HMC) is a widely used sampler for continuous probability distributions. In many cases, the underlying Hamiltonian dynamics exhibit a phenomenon of resonance which decreases the efficiency of the algorithm and makes it very sensitive to hyperparameter values. This issue can b…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗

2023

Variational Inference with Gaussian Score Matching

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

NeurIPS 2023poster

Variational inference (VI) is a method to approximate the computationally intractable posterior distributions that arise in Bayesian statistics. Typically, VI fits a simple parametric distribution to be close to the target posterior, optimizing an appropriate objective such as the evidence lower b…

Cited by 13 Source ↗PDF ↗Scholar ↗

2020

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

Charles Margossian, Aki Vehtari, Daniel Simpson, Raj Agrawal

NeurIPS 2020poster

Gaussian latent variable models are a key class of Bayesian hierarchical models with applications in many fields. Performing Bayesian inference on such models can be challenging as Markov chain Monte Carlo algorithms struggle with the geometry of the resulting posterior distribution and can be prohi…

Cited by 46 Source ↗PDF ↗Scholar ↗