Variational Orthogonal Features

• URL: http://arxiv.org/abs/2006.13170v1
• Date: Tue, 23 Jun 2020 17:18:07 GMT
• Title: Variational Orthogonal Features
• Authors: David R. Burt, Carl Edward Rasmussen, Mark van der Wilk
• Abstract summary: We show that for certain priors, features can be defined that remove the $mathcalO(M3)$ cost of computing a minibatch estimate of an evidence lower bound (ELBO) We present a construction of features for any stationary prior kernel that allow for computation of an unbiased estimator to the ELBO using $T$ Monte Carlo samples in $mathcalO(tildeNT+M2T)$ and in $mathcalO(tildeNT+MT)$ with an additional approximation.
• Score: 29.636483122130027
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparse stochastic variational inference allows Gaussian process models to be applied to large datasets. The per iteration computational cost of inference with this method is $\mathcal{O}(\tilde{N}M^2+M^3),$ where $\tilde{N}$ is the number of points in a minibatch and $M$ is the number of `inducing features', which determine the expressiveness of the variational family. Several recent works have shown that for certain priors, features can be defined that remove the $\mathcal{O}(M^3)$ cost of computing a minibatch estimate of an evidence lower bound (ELBO). This represents a significant computational savings when $M\gg \tilde{N}$. We present a construction of features for any stationary prior kernel that allow for computation of an unbiased estimator to the ELBO using $T$ Monte Carlo samples in $\mathcal{O}(\tilde{N}T+M^2T)$ and in $\mathcal{O}(\tilde{N}T+MT)$ with an additional approximation. We analyze the impact of this additional approximation on inference quality.

Related papers

• Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models [37.42736399673992]
  A single-index model (SIM) is a function of the form $sigma(mathbfwast cdot mathbfx)$, where $sigma: mathbbR to mathbbR$ is a known link function and $mathbfwast$ is a hidden unit vector. We show that a proper learner attains $L2$-error of $O(mathrmOPT)+epsilon$, where $
  arXiv  Detail & Related papers  (2024-11-08T17:10:38Z)
• Inverting the Leverage Score Gradient: An Efficient Approximate Newton Method [10.742859956268655]
  This paper aims to recover the intrinsic model parameters given the leverage scores gradient. We specifically scrutinize the inversion of the leverage score gradient, denoted as $g(x)$.
  arXiv  Detail & Related papers  (2024-08-21T01:39:42Z)
• Learning a Single Neuron with Adversarial Label Noise via Gradient Descent [50.659479930171585]
  We study a function of the form $mathbfxmapstosigma(mathbfwcdotmathbfx)$ for monotone activations. The goal of the learner is to output a hypothesis vector $mathbfw$ that $F(mathbbw)=C, epsilon$ with high probability.
  arXiv  Detail & Related papers  (2022-06-17T17:55:43Z)
• Random matrices in service of ML footprint: ternary random features with no performance loss [55.30329197651178]
  We show that the eigenspectrum of $bf K$ is independent of the distribution of the i.i.d. entries of $bf w$. We propose a novel random technique, called Ternary Random Feature (TRF) The computation of the proposed random features requires no multiplication and a factor of $b$ less bits for storage compared to classical random features.
  arXiv  Detail & Related papers  (2021-10-05T09:33:49Z)
• Non-Parametric Estimation of Manifolds from Noisy Data [1.0152838128195467]
  We consider the problem of estimating a $d$ dimensional sub-manifold of $mathbbRD$ from a finite set of noisy samples. We show that the estimation yields rates of convergence of $n-frack2k + d$ for the point estimation and $n-frack-12k + d$ for the estimation of tangent space.
  arXiv  Detail & Related papers  (2021-05-11T02:29:33Z)
• Sparse sketches with small inversion bias [79.77110958547695]
  Inversion bias arises when averaging estimates of quantities that depend on the inverse covariance. We develop a framework for analyzing inversion bias, based on our proposed concept of an $(epsilon,delta)$-unbiased estimator for random matrices. We show that when the sketching matrix $S$ is dense and has i.i.d. sub-gaussian entries, the estimator $(epsilon,delta)$-unbiased for $(Atop A)-1$ with a sketch of size $m=O(d+sqrt d/
  arXiv  Detail & Related papers  (2020-11-21T01:33:15Z)
• List-Decodable Mean Estimation in Nearly-PCA Time [50.79691056481693]
  We study the fundamental task of list-decodable mean estimation in high dimensions. Our algorithm runs in time $widetildeO(ndk)$ for all $k = O(sqrtd) cup Omega(d)$, where $n$ is the size of the dataset. A variant of our algorithm has runtime $widetildeO(ndk)$ for all $k$, at the expense of an $O(sqrtlog k)$ factor in the recovery guarantee
  arXiv  Detail & Related papers  (2020-11-19T17:21:37Z)
• 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)
• 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)
• A Randomized Algorithm to Reduce the Support of Discrete Measures [79.55586575988292]
  Given a discrete probability measure supported on $N$ atoms and a set of $n$ real-valued functions, there exists a probability measure that is supported on a subset of $n+1$ of the original $N$ atoms. We give a simple geometric characterization of barycenters via negative cones and derive a randomized algorithm that computes this new measure by "greedy geometric sampling" We then study its properties, and benchmark it on synthetic and real-world data to show that it can be very beneficial in the $Ngg n$ regime.
  arXiv  Detail & Related papers  (2020-06-02T16:38:36Z)

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.