paper-with-me

Papers

High Dimensional Inference with Random Maximum A-Posteriori Perturbations

2016-02-10 · Tamir Hazan, Francesco Orabona, Anand D. Sarwate, Subhransu Maji, Tommi Jaakkola

This paper presents a new approach, called perturb-max, for high-dimensional statistical inference that is based on applying random perturbations followed by optimization. This framework injects randomness to maximum a-posteriori (MAP) predictors by randomly perturbing the potential function for the input. A classic result from extreme value statistics asserts that perturb-max operations generate unbiased samples from the Gibbs distribution using high-dimensional perturbations. Unfortunately, the computational cost of generating so many high-dimensional random variables can be prohibitive. However, when the perturbations are of low dimension, sampling the perturb-max prediction is as efficient as MAP optimization. This paper shows that the expected value of perturb-max inference with low dimensional perturbations can be used sequentially to generate unbiased samples from the Gibbs distribution. Furthermore the expected value of the maximal perturbations is a natural bound on the entropy of such perturb-max models. A measure concentration result for perturb-max values shows that the deviation of their sampled average from its expectation decays exponentially in the number of samples, allowing effective approximation of the expectation.

📄 PDF Abstract BibTeX arXiv:1602.03571

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

On Measure Concentration of Random Maximum A-Posteriori Perturbations

2013-10-15 · Francesco Orabona, Tamir Hazan, Anand D. Sarwate, Tommi Jaakkola

The maximum a-posteriori (MAP) perturbation framework has emerged as a useful approach for inference and learning in high dimensional complex models. By maximizing a randomly perturbed potential function, MAP perturbatio…

Strong replica symmetry for high-dimensional disordered log-concave Gibbs measures

2020-09-27 · Jean Barbier, Dmitry Panchenko, Manuel Sáenz

We consider a generic class of log-concave, possibly random, (Gibbs) measures. We prove the concentration of an infinite family of order parameters called multioverlaps. Because they completely parametrise the quenched G…

Vocal Bursts Intensity Prediction

On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations

2013-09-29 · NeurIPS 2013 12 · Tamir Hazan, Subhransu Maji, Tommi Jaakkola

In this paper we describe how MAP inference can be used to sample efficiently from Gibbs distributions. Specifically, we provide means for drawing either approximate or unbiased samples from Gibbs' distributions by intro…

Statistical Mechanics of High-Dimensional Inference

2016-01-18 · Madhu Advani, Surya Ganguli

To model modern large-scale datasets, we need efficient algorithms to infer a set of $P$ unknown model parameters from $N$ noisy measurements. What are fundamental limits on the accuracy of parameter inference, given fin…

Bayesian Inferencecompressed sensingVocal Bursts Intensity Prediction

Probably Approximately Correct Maximum A Posteriori Inference

2026-01-22 · Matthew Shorvon, Frederik Mallmann-Trenn, David S. Watson arxiv

Computing the conditional mode of a distribution, better known as the $\mathit{maximum\ a\ posteriori}$ (MAP) assignment, is a fundamental task in probabilistic inference. However, MAP estimation is generally intractable…