arXiv subjects

Brandon T. Willard

Publications and source records attributed to Brandon T. Willard.

6 recordsLinked to original sources

arXiv2023

Efficient Guided Generation for Large Language Models

In this article we show how the problem of neural text generation can be constructively reformulated in terms of transitions between the states of a finite-state machine. This framework leads to an efficient approach to guiding text generation with regular expressions and context-free grammars by allowing the construction of an index over a language model's vocabulary. The approach is model agnostic, allows one to enforce domain-specific knowledge and constraints, and enables the construction of reliable interfaces by guaranteeing the structure of the generated text. It adds little overhead to the token sequence generation process and significantly outperforms existing solutions. An implementation is provided in the open source Python library Outlines

cs.CL↗

arXiv2020

miniKanren as a Tool for Symbolic Computation in Python

In this article, we give a brief overview of the current state and future potential of symbolic computation within the Python statistical modeling and machine learning community. We detail the use of miniKanren as an underlying framework for term rewriting and symbolic mathematics, as well as its ability to orchestrate the use of existing Python libraries. We also discuss the relevance and potential of relational programming for implementing more robust, portable, domain-specific "math-level" optimizations--with a slight focus on Bayesian modeling. Finally, we describe the work going forward and raise some questions regarding potential cross-overs between statistical modeling and programming language theory.

cs.PL↗

arXiv2019

Lasso Meets Horseshoe : A Survey

The goal of this paper is to contrast and survey the major advances in two of the most commonly used high-dimensional techniques, namely, the Lasso and horseshoe regularization. Lasso is a gold standard for predictor selection while horseshoe is a state-of-the-art Bayesian estimator for sparse signals. Lasso is fast and scalable and uses convex optimization whilst the horseshoe is non-convex. Our novel perspective focuses on three aspects: (i) theoretical optimality in high dimensional inference for the Gaussian sparse model and beyond, (ii) efficiency and scalability of computation and (iii) methodological development and performance.

stat.ME↗

arXiv2016

Default Bayesian analysis with global-local shrinkage priors

We provide a framework for assessing the default nature of a prior distribution using the property of regular variation, which we study for global-local shrinkage priors. In particular, we demonstrate the horseshoe priors, originally designed to handle sparsity, also possess regular variation and thus are appropriate for default Bayesian analysis. To illustrate our methodology, we solve a problem of non-informative priors due to Efron (1973), who showed standard flat non-informative priors in high-dimensional normal means model can be highly informative for nonlinear parameters of interest. We consider four such problems and show global-local shrinkage priors such as the horseshoe and horseshoe+ perform as Efron (1973) requires in each case. We find the reason for this lies in the ability of the global-local shrinkage priors to separate a low-dimensional signal embedded in high-dimensional noise, even for nonlinear functions.

stat.ME↗

arXiv2015

A Statistical Theory of Deep Learning via Proximal Splitting

In this paper we develop a statistical theory and an implementation of deep learning models. We show that an elegant variable splitting scheme for the alternating direction method of multipliers optimises a deep learning objective. We allow for non-smooth non-convex regularisation penalties to induce sparsity in parameter weights. We provide a link between traditional shallow layer statistical models such as principal component and sliced inverse regression and deep layer models. We also define the degrees of freedom of a deep learning predictor and a predictive MSE criteria to perform model selection for comparing architecture designs. We focus on deep multiclass logistic learning although our methods apply more generally. Our results suggest an interesting and previously under-exploited relationship between deep learning and proximal splitting techniques. To illustrate our methodology, we provide a multi-class logit classification analysis of Fisher's Iris data where we illustrate the convergence of our algorithm. Finally, we conclude with directions for future research.

stat.ML↗

arXiv2015

Proximal Algorithms in Statistics and Machine Learning

In this paper we develop proximal methods for statistical learning. Proximal point algorithms are useful in statistics and machine learning for obtaining optimization solutions for composite functions. Our approach exploits closed-form solutions of proximal operators and envelope representations based on the Moreau, Forward-Backward, Douglas-Rachford and Half-Quadratic envelopes. Envelope representations lead to novel proximal algorithms for statistical optimisation of composite objective functions which include both non-smooth and non-convex objectives. We illustrate our methodology with regularized Logistic and Poisson regression and non-convex bridge penalties with a fused lasso norm. We provide a discussion of convergence of non-descent algorithms with acceleration and for non-convex functions. Finally, we provide directions for future research.

stat.ML↗