Which exceptional low-dimensional projections of a Gaussian point cloud can be found in polynomial time?

• URL: http://arxiv.org/abs/2406.02970v1
• Date: Wed, 5 Jun 2024 05:54:56 GMT
• Title: Which exceptional low-dimensional projections of a Gaussian point cloud can be found in polynomial time?
• Authors: Andrea Montanari, Kangjie Zhou,
• Abstract summary: We study the subset $mathscrF_m,alpha$ of distributions that can be realized by a class of iterative algorithms. Non-rigorous methods from statistical physics yield an indirect characterization of $mathscrF_m,alpha$ in terms of a generalized Parisi formula.
• Score: 8.74634652691576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given $d$-dimensional standard Gaussian vectors $\boldsymbol{x}_1,\dots, \boldsymbol{x}_n$, we consider the set of all empirical distributions of its $m$-dimensional projections, for $m$ a fixed constant. Diaconis and Freedman (1984) proved that, if $n/d\to \infty$, all such distributions converge to the standard Gaussian distribution. In contrast, we study the proportional asymptotics, whereby $n,d\to \infty$ with $n/d\to \alpha \in (0, \infty)$. In this case, the projection of the data points along a typical random subspace is again Gaussian, but the set $\mathscr{F}_{m,\alpha}$ of all probability distributions that are asymptotically feasible as $m$-dimensional projections contains non-Gaussian distributions corresponding to exceptional subspaces. Non-rigorous methods from statistical physics yield an indirect characterization of $\mathscr{F}_{m,\alpha}$ in terms of a generalized Parisi formula. Motivated by the goal of putting this formula on a rigorous basis, and to understand whether these projections can be found efficiently, we study the subset $\mathscr{F}^{\rm alg}_{m,\alpha}\subseteq \mathscr{F}_{m,\alpha}$ of distributions that can be realized by a class of iterative algorithms. We prove that this set is characterized by a certain stochastic optimal control problem, and obtain a dual characterization of this problem in terms of a variational principle that extends Parisi's formula. As a byproduct, we obtain computationally achievable values for a class of random optimization problems including `generalized spherical perceptron' models.

Related papers

• Dimension-free Private Mean Estimation for Anisotropic Distributions [55.86374912608193]
  Previous private estimators on distributions over $mathRd suffer from a curse of dimensionality. We present an algorithm whose sample complexity has improved dependence on dimension.
  arXiv  Detail & Related papers  (2024-11-01T17:59:53Z)
• SoS Certifiability of Subgaussian Distributions and its Algorithmic Applications [37.208622097149714]
  We prove that there is a universal constant $C>0$ so that for every $d inmathbb N$, every centered subgaussian distribution $mathcal D$ on $mathbb Rd$, and every even $p inmathbb N$, the $d-optimal inmathbb N$, and the $d-optimal inmathbb N$. This establishes that every subgaussian distribution is emphS-certifiably subgaussian -- a condition that yields efficient learning algorithms for a wide variety of
  arXiv  Detail & Related papers  (2024-10-28T16:36:58Z)
• Provably learning a multi-head attention layer [55.2904547651831]
  Multi-head attention layer is one of the key components of the transformer architecture that sets it apart from traditional feed-forward models. In this work, we initiate the study of provably learning a multi-head attention layer from random examples. We prove computational lower bounds showing that in the worst case, exponential dependence on $m$ is unavoidable.
  arXiv  Detail & Related papers  (2024-02-06T15:39:09Z)
• Efficient Estimation of the Central Mean Subspace via Smoothed Gradient Outer Products [12.047053875716506]
  We consider the problem of sufficient dimension reduction for multi-index models. We show that a fast parametric convergence rate of form $C_d cdot n-1/2$ is achievable.
  arXiv  Detail & Related papers  (2023-12-24T12:28:07Z)
• A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing [68.80803866919123]
  Under nonlinear measurements, most prior results are non-uniform, i.e., they hold with high probability for a fixed $mathbfx*$ rather than for all $mathbfx*$ simultaneously. Our framework accommodates GCS with 1-bit/uniformly quantized observations and single index models as canonical examples. We also develop a concentration inequality that produces tighter bounds for product processes whose index sets have low metric entropy.
  arXiv  Detail & Related papers  (2023-09-25T17:54:19Z)
• Robust Mean Estimation Without Moments for Symmetric Distributions [7.105512316884493]
  We show that for a large class of symmetric distributions, the same error as in the Gaussian setting can be achieved efficiently. We propose a sequence of efficient algorithms that approaches this optimal error. Our algorithms are based on a generalization of the well-known filtering technique.
  arXiv  Detail & Related papers  (2023-02-21T17:52:23Z)
• High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors [15.802475232604667]
  In location estimation, we are given $n$ samples from a known distribution $f$ shifted by an unknown translation $lambda$. Asymptotically, the maximum likelihood estimate achieves the Cram'er-Rao bound of error $mathcal N(0, frac1nmathcal I)$. We build on the theory using emphsmoothed estimators to bound the error for finite $n$ in terms of $mathcal I_r$, the Fisher information of the $r$-smoothed
  arXiv  Detail & Related papers  (2023-02-05T22:17:04Z)
• Overparametrized linear dimensionality reductions: From projection pursuit to two-layer neural networks [10.368585938419619]
  Given a cloud of $n$ data points in $mathbbRd$, consider all projections onto $m$-dimensional subspaces of $mathbbRd$. What does this collection of probability distributions look like when $n,d$ grow large? Denoting by $mathscrF_m, alpha$ the set of probability distributions in $mathbbRm$ that arise as low-dimensional projections in this limit, we establish new inner and outer bounds on $mathscrF_
  arXiv  Detail & Related papers  (2022-06-14T00:07:33Z)
• 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)
• Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals [49.60752558064027]
  We study the fundamental problems of agnostically learning halfspaces and ReLUs under Gaussian marginals. Our lower bounds provide strong evidence that current upper bounds for these tasks are essentially best possible.
  arXiv  Detail & Related papers  (2020-06-29T17:10:10Z)
• 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.