13 citations · 40 across the 16 of their papers we have counts for
19 papers
Black-Box Inference of LLM Architectural Properties with Restrictive API Access
Christopher Ellis, Shreyas Chaudhari, Mei-Yu Wang +3
In practice, most commercial LLM providers do not publicly release details of underlying LLM architectures. However, prior work has shown that given limited API access to an LLM (n…
Sub-Gaussian Concentration and Entropic Normality of the Maximum Likelihood Estimator
Leighton P. Barnes, Alex Dytso
It is well known that, under standard regularity conditions, the maximum likelihood estimator (MLE) satisfies a central limit theorem and converges in distribution to a Gaussian ra…
Functional uniqueness and stability of Gaussian priors in optimal L1 estimation
Leighton Barnes, Alex Dytso
We study when optimal Bayesian estimators under Gaussian noise are approximately linear, and what this implies about the underlying prior distribution. Consider the classical model…
Linearity-Inducing Priors for Poisson Parameter Estimation Under Loss
Leighton P. Barnes, Alex Dytso, H. Vincent Poor
We study prior distributions for Poisson parameter estimation under loss. Specifically, we construct a new family of prior distributions whose optimal Bayesian estimators (th…
On Unbiased Low-Rank Approximation with Minimum Distortion
Leighton Pate Barnes, Stephen Cameron, Benjamin Howard
We describe an algorithm for sampling a low-rank random matrix that best approximates a fixed target matrix in the following sense: is unbiased…
Efficient Unbiased Sparsification
Leighton Barnes, Stephen Cameron, Timothy Chow +6
An unbiased -sparsification of a vector is a random vector with mean that has at most nonzero coordinates. Unbiased sparsificat…