15 citations · 16 across the 10 of their papers we have counts for
11 papers
Decision-Sufficient Posterior Approximation
Sean Plummer
We investigate the consequences of requiring a posterior approximation to preserve a specified downstream decision problem. A target posterior and loss determine a regret geome…
Observable Geometry of Singular Statistical Models
Sean Plummer
Singular statistical models arise whenever different parameter values induce the same distribution, leading to non-identifiability and a breakdown of classical asymptotic theory. W…
Functional Bias and Tangent-Space Geometry in Variational Inference
Sean Plummer
Variational inference approximates Bayesian posterior distributions by projecting onto a tractable family of distributions. While most theoretical analyses evaluate the quality of…
Thermodynamic Response Functions in Singular Bayesian Models
Sean Plummer
Singular statistical models-including mixtures, matrix factorization, and neural networks-violate regular asymptotics due to parameter non-identifiability and degenerate Fisher geo…
Hypothesis Testing over Observable Regimes in Singular Models
Sean Plummer
Hypothesis testing in singular statistical models is often regarded as inherently problematic due to non-identifiability and degeneracy of the Fisher information. We show that the…
Feasibility Preservation under Monotone Retrieval Truncation
Sean Plummer
Retrieval-based systems approximate access to a corpus by exposing only a truncated subset of available evidence. Even when relevant information exists in the corpus, truncation ca…
From Tail Universality to Bernstein-von Mises: A Unified Statistical Theory of Semi-Implicit Variational Inference
Sean Plummer
Semi-implicit variational inference (SIVI) constructs approximate posteriors of the form , where the conditional kernel is parameterized and the mixing b…
Singular Fluctuation as Specific Heat in Bayesian Learning
Sean Plummer
Singular learning theory characterizes Bayesian models with non-identifiable parameterizations through two central quantities: the real log canonical threshold (RLCT), which govern…
Statistical Guarantees for Transformation Based Models with Applications to Implicit Variational Inference
Sean Plummer, Shuang Zhou, Anirban Bhattacharya +2
Transformation-based methods have been an attractive approach in non-parametric inference for problems such as unconditional and conditional density estimation due to their unique…
Evidence bounds in singular models: probabilistic and variational perspectives
Anirban Bhattacharya, Debdeep Pati, Sean Plummer
The marginal likelihood or evidence in Bayesian statistics contains an intrinsic penalty for larger model sizes and is a fundamental quantity in Bayesian model comparison. Over the…
Dynamics of coordinate ascent variational inference: A case study in 2D Ising models
Sean Plummer, Debdeep Pati, Anirban Bhattacharya
Variational algorithms have gained prominence over the past two decades as a scalable computational environment for Bayesian inference. In this article, we explore tools from the d…