Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models

• URL: http://arxiv.org/abs/2411.15669v1
• Date: Sat, 23 Nov 2024 23:13:24 GMT
• Title: Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models
• Authors: Ilias Diakonikolas, Daniel M. Kane,
• Abstract summary: We study the task of learning latent-variable models. Motivated by such applications, we develop a general efficient algorithm for implicit moment computation. By leveraging our general algorithm, we obtain the first-time learners for the following models.
• Score: 39.33814194788341
• License:
• Abstract: We study the task of learning latent-variable models. An obstacle towards designing efficient algorithms for such models is the necessity of approximating moment tensors of super-constant degree. Motivated by such applications, we develop a general efficient algorithm for implicit moment tensor computation. Our algorithm computes in $\mathrm{poly}(d, k)$ time a succinct approximate description of tensors of the form $M_m=\sum_{i=1}^{k}w_iv_i^{\otimes m}$, for $w_i\in\mathbb{R}_+$--even for $m=\omega(1)$--assuming there exists a polynomial-size arithmetic circuit whose expected output on an appropriate samplable distribution is equal to $M_m$, and whose covariance on this input is bounded. Our framework broadly generalizes the work of~\cite{LL21-opt} which developed an efficient algorithm for the specific moment tensors that arise in clustering mixtures of spherical Gaussians. By leveraging our general algorithm, we obtain the first polynomial-time learners for the following models. * Mixtures of Linear Regressions. We give a $\mathrm{poly}(d, k, 1/\epsilon)$-time algorithm for this task. The previously best algorithm has super-polynomial complexity in $k$. * Learning Mixtures of Spherical Gaussians. We give a $\mathrm{poly}(d, k, 1/\epsilon)$-time density estimation algorithm, under the condition that the means lie in a ball of radius $O(\sqrt{\log k})$. Prior algorithms incur super-polynomial complexity in $k$. We also give a $\mathrm{poly}(d, k, 1/\epsilon)$-time parameter estimation algorithm, under the {\em optimal} mean separation of $\Omega(\log^{1/2}(k/\epsilon))$. * PAC Learning Sums of ReLUs. We give a learner with complexity $\mathrm{poly}(d, k) 2^{\mathrm{poly}(1/\epsilon)}$. This is the first algorithm for this task that runs in $\mathrm{poly}(d, k)$ time for subconstant values of $\epsilon = o_{k, d}(1)$.

Related papers

• Iterative thresholding for non-linear learning in the strong $\varepsilon$-contamination model [3.309767076331365]
  We derive approximation bounds for learning single neuron models using thresholded descent. We also study the linear regression problem, where $sigma(mathbfx) = mathbfx$.
  arXiv  Detail & Related papers  (2024-09-05T16:59:56Z)
• 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)
• A Sub-Quadratic Time Algorithm for Robust Sparse Mean Estimation [6.853165736531941]
  We study the algorithmic problem of sparse mean estimation in the presence of adversarial outliers. Our main contribution is an algorithm for robust sparse mean estimation which runs in emphsubquadratic time using $mathrmpoly(k,log d,1/epsilon)$ samples.
  arXiv  Detail & Related papers  (2024-03-07T18:23:51Z)
• Do you know what q-means? [50.045011844765185]
  Clustering is one of the most important tools for analysis of large datasets. We present an improved version of the "$q$-means" algorithm for clustering. We also present a "dequantized" algorithm for $varepsilon which runs in $Obig(frack2varepsilon2(sqrtkd + log(Nd))big.
  arXiv  Detail & Related papers  (2023-08-18T17:52:12Z)
• Efficiently Learning One-Hidden-Layer ReLU Networks via Schur Polynomials [50.90125395570797]
  We study the problem of PAC learning a linear combination of $k$ ReLU activations under the standard Gaussian distribution on $mathbbRd$ with respect to the square loss. Our main result is an efficient algorithm for this learning task with sample and computational complexity $(dk/epsilon)O(k)$, whereepsilon>0$ is the target accuracy.
  arXiv  Detail & Related papers  (2023-07-24T14:37:22Z)
• Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise [50.64137465792738]
  We show that any efficient SQ algorithm for the problem requires sample complexity at least $Omega(d1/2/(maxp, epsilon)2)$. Our lower bound suggests that this quadratic dependence on $1/epsilon$ is inherent for efficient algorithms.
  arXiv  Detail & Related papers  (2023-07-13T18:59:28Z)
• Near-Optimal Quantum Coreset Construction Algorithms for Clustering [15.513270929560088]
  We give quantum algorithms that find coresets for $k$-clustering in $mathbbRd$ with $tildeO(sqrtnkd3/2)$ query complexity. Our coreset reduces the input size from $n$ to $mathrmpoly(kepsilon-1d)$, so that existing $alpha$-approximation algorithms for clustering can run on top of it.
  arXiv  Detail & Related papers  (2023-06-05T12:22:46Z)
• Most Neural Networks Are Almost Learnable [52.40331776572531]
  We show that for any fixed $epsilon>0$ and depth $i$, there is a poly-time algorithm that learns random Xavier networks of depth $i$. The algorithm runs in time and sample complexity of $(bard)mathrmpoly(epsilon-1)$, where $bar d$ is the size of the network. For some cases of sigmoid and ReLU-like activations the bound can be improved to $(bard)mathrmpolylog(eps
  arXiv  Detail & Related papers  (2023-05-25T22:27:42Z)
• 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)
• Small Covers for Near-Zero Sets of Polynomials and Learning Latent Variable Models [56.98280399449707]
  We show that there exists an $epsilon$-cover for $S$ of cardinality $M = (k/epsilon)O_d(k1/d)$. Building on our structural result, we obtain significantly improved learning algorithms for several fundamental high-dimensional probabilistic models hidden variables.
  arXiv  Detail & Related papers  (2020-12-14T18:14:08Z)

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.