Log-Concave Coupling for Sampling Neural Net Posteriors

• URL: http://arxiv.org/abs/2407.18802v1
• Date: Fri, 26 Jul 2024 15:05:41 GMT
• Title: Log-Concave Coupling for Sampling Neural Net Posteriors
• Authors: Curtis McDonald, Andrew R Barron,
• Abstract summary: We present a sampling algorithm for single hidden layer neural networks. The algorithm is based on a coupling of the posterior density for $w$ with an auxiliary random variable $xi$. The score of the marginal density of the auxiliary random variable $xi$ is determined by an expectation over $w|xi$.
• Score: 0.4604003661048266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we present a sampling algorithm for single hidden layer neural networks. This algorithm is built upon a recursive series of Bayesian posteriors using a method we call Greedy Bayes. Sampling of the Bayesian posterior for neuron weight vectors $w$ of dimension $d$ is challenging because of its multimodality. Our algorithm to tackle this problem is based on a coupling of the posterior density for $w$ with an auxiliary random variable $\xi$. The resulting reverse conditional $w|\xi$ of neuron weights given auxiliary random variable is shown to be log concave. In the construction of the posterior distributions we provide some freedom in the choice of the prior. In particular, for Gaussian priors on $w$ with suitably small variance, the resulting marginal density of the auxiliary variable $\xi$ is proven to be strictly log concave for all dimensions $d$. For a uniform prior on the unit $\ell_1$ ball, evidence is given that the density of $\xi$ is again strictly log concave for sufficiently large $d$. The score of the marginal density of the auxiliary random variable $\xi$ is determined by an expectation over $w|\xi$ and thus can be computed by various rapidly mixing Markov Chain Monte Carlo methods. Moreover, the computation of the score of $\xi$ permits methods of sampling $\xi$ by a stochastic diffusion (Langevin dynamics) with drift function built from this score. With such dynamics, information-theoretic methods pioneered by Bakry and Emery show that accurate sampling of $\xi$ is obtained rapidly when its density is indeed strictly log-concave. After which, one more draw from $w|\xi$, produces neuron weights $w$ whose marginal distribution is from the desired posterior.

Related papers

• Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models [65.71506381302815]
  We propose amortize the cost of sampling from a posterior distribution of the form $p(mathbfxmidmathbfy) propto p_theta(mathbfx)$. For many models and constraints of interest, the posterior in the noise space is smoother than the posterior in the data space, making it more amenable to such amortized inference.
  arXiv  Detail & Related papers  (2025-02-10T19:49:54Z)
• Diffusion at Absolute Zero: Langevin Sampling Using Successive Moreau Envelopes [52.69179872700035]
  We propose a novel method for sampling from Gibbs distributions of the form $pi(x)proptoexp(-U(x))$ with a potential $U(x)$. Inspired by diffusion models we propose to consider a sequence $(pit_k)_k$ of approximations of the target density, for which $pit_kapprox pi$ for $k$ small and, on the other hand, $pit_k$ exhibits favorable properties for sampling for $k$ large.
  arXiv  Detail & Related papers  (2025-02-03T13:50:57Z)
• Polynomial time sampling from log-smooth distributions in fixed dimension under semi-log-concavity of the forward diffusion with application to strongly dissipative distributions [9.48556659249574]
  We provide a sampling algorithm with complexity in fixed dimension. We prove that our algorithm achieves an expected $epsilon$ error in $KL$ divergence. As an application, we derive an exponential complexity improvement for the problem of sampling from an $L$-log-smooth distribution.
  arXiv  Detail & Related papers  (2024-12-31T17:51:39Z)
• Sum-of-squares lower bounds for Non-Gaussian Component Analysis [33.80749804695003]
  Non-Gaussian Component Analysis (NGCA) is the statistical task of finding a non-Gaussian direction in a high-dimensional dataset. Here we study the complexity of NGCA in the Sum-of-Squares framework.
  arXiv  Detail & Related papers  (2024-10-28T18:19:13Z)
• Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent [83.85536329832722]
  We solve the $k$-sparse parity problem with sign gradient descent (SGD) on two-layer fully-connected neural networks. We show that this approach can efficiently solve the $k$-sparse parity problem on a $d$-dimensional hypercube. We then demonstrate how a trained neural network with sign SGD can effectively approximate this good network, solving the $k$-parity problem with small statistical errors.
  arXiv  Detail & Related papers  (2024-04-18T17:57:53Z)
• Debiasing and a local analysis for population clustering using semidefinite programming [1.9761774213809036]
  We consider the problem of partitioning a small data sample of size $n$ drawn from a mixture of $2$ sub-gaussian distributions. This work is motivated by the application of clustering individuals according to their population of origin.
  arXiv  Detail & Related papers  (2024-01-16T03:14:24Z)
• Data Structures for Density Estimation [66.36971978162461]
  Given a sublinear (in $n$) number of samples from $p$, our main result is the first data structure that identifies $v_i$ in time sublinear in $k$. We also give an improved version of the algorithm of Acharya et al. that reports $v_i$ in time linear in $k$.
  arXiv  Detail & Related papers  (2023-06-20T06:13:56Z)
• Hamiltonian Monte Carlo for efficient Gaussian sampling: long and random steps [0.0]
  Hamiltonian Monte Carlo (HMC) is a Markov chain algorithm for sampling from a high-dimensional distribution with density $e-f(x)$. We show that HMC can sample from a distribution that is $varepsilon$-close in total variation distance using $widetildeO(sqrtkappa d1/4 log(1/varepsilon)$ gradient queries.
  arXiv  Detail & Related papers  (2022-09-26T15:29:29Z)
• Convergence of Sparse Variational Inference in Gaussian Processes Regression [29.636483122130027]
  We show that a method with an overall computational cost of $mathcalO(log N)2D(loglog N)2)$ can be used to perform inference.
  arXiv  Detail & Related papers  (2020-08-01T19:23:34Z)
• Optimal Robust Linear Regression in Nearly Linear Time [97.11565882347772]
  We study the problem of high-dimensional robust linear regression where a learner is given access to $n$ samples from the generative model $Y = langle X,w* rangle + epsilon$ We propose estimators for this problem under two settings: (i) $X$ is L4-L2 hypercontractive, $mathbbE [XXtop]$ has bounded condition number and $epsilon$ has bounded variance and (ii) $X$ is sub-Gaussian with identity second moment and $epsilon$ is
  arXiv  Detail & Related papers  (2020-07-16T06:44:44Z)
• Linear Time Sinkhorn Divergences using Positive Features [51.50788603386766]
  Solving optimal transport with an entropic regularization requires computing a $ntimes n$ kernel matrix that is repeatedly applied to a vector. We propose to use instead ground costs of the form $c(x,y)=-logdotpvarphi(x)varphi(y)$ where $varphi$ is a map from the ground space onto the positive orthant $RRr_+$, with $rll n$.
  arXiv  Detail & Related papers  (2020-06-12T10:21:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.