Statistical-Computational Trade-offs in Learning Multi-Index Models via Harmonic Analysis

• URL: http://arxiv.org/abs/2602.09959v1
• Date: Tue, 10 Feb 2026 16:46:32 GMT
• Title: Statistical-Computational Trade-offs in Learning Multi-Index Models via Harmonic Analysis
• Authors: Hugo Latourelle-Vigeant, Theodor Misiakiewicz,
• Abstract summary: We study the problem of learning multi-index models (MIMs)<n>We obtain a sharp harmonic-analytic characterization of the learning complexity for MIMs with spherically symmetric inputs.
• Score: 5.7652356955571085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the problem of learning multi-index models (MIMs), where the label depends on the input $\boldsymbol{x} \in \mathbb{R}^d$ only through an unknown $\mathsf{s}$-dimensional projection $\boldsymbol{W}_*^\mathsf{T} \boldsymbol{x} \in \mathbb{R}^\mathsf{s}$. Exploiting the equivariance of this problem under the orthogonal group $\mathcal{O}_d$, we obtain a sharp harmonic-analytic characterization of the learning complexity for MIMs with spherically symmetric inputs -- which refines and generalizes previous Gaussian-specific analyses. Specifically, we derive statistical and computational complexity lower bounds within the Statistical Query (SQ) and Low-Degree Polynomial (LDP) frameworks. These bounds decompose naturally across spherical harmonic subspaces. Guided by this decomposition, we construct a family of spectral algorithms based on harmonic tensor unfolding that sequentially recover the latent directions and (nearly) achieve these SQ and LDP lower bounds. Depending on the choice of harmonic degree sequence, these estimators can realize a broad range of trade-offs between sample and runtime complexity. From a technical standpoint, our results build on the semisimple decomposition of the $\mathcal{O}_d$-action on $L^2 (\mathbb{S}^{d-1})$ and the intertwining isomorphism between spherical harmonics and traceless symmetric tensors.

Related papers

• On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature [1.6773271875801752]
  Gradient Descent (SGD) introduces anisotropic noise that is correlated with the local curvature of the loss landscape, thereby biasing optimization toward flat minima.<n>We show that this assumption holds only under restrictive conditions that are typically violated in deep neural networks.<n>Experiments across datasets, architectures, and loss functions validate these bounds, providing a unified characterization of the noise-curvature relationship in deep learning.
  arXiv  Detail & Related papers  (2026-02-05T12:35:13Z)
• Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws [21.18373933718468]
  We study the optimization and sample complexity of gradient-based training of a two-layer neural network with quadratic activation function in the high-dimensional regime.<n>We present a sharp analysis of the dynamics in the feature learning regime, for both the population limit and the finite-sample discretization.
  arXiv  Detail & Related papers  (2025-08-05T17:57:56Z)
• Learning single-index models via harmonic decomposition [21.065469907392643]
  We study the problem of learning single-index models, where the label $y in mathbbR$ depends on the input $boldsymbolx in mathbbRd$ only through an unknown one-dimensional projection.<n>We introduce two families of estimators -- based on tensor unfolding and online SGD -- that respectively achieve either optimal sample complexity or optimal runtime.
  arXiv  Detail & Related papers  (2025-06-11T15:59:53Z)
• Tensor cumulants for statistical inference on invariant distributions [49.80012009682584]
  We show that PCA becomes computationally hard at a critical value of the signal's magnitude. We define a new set of objects, which provide an explicit, near-orthogonal basis for invariants of a given degree. It also lets us analyze a new problem of distinguishing between different ensembles.
  arXiv  Detail & Related papers  (2024-04-29T14:33:24Z)
• Computational-Statistical Gaps in Gaussian Single-Index Models [77.1473134227844]
  Single-Index Models are high-dimensional regression problems with planted structure. We show that computationally efficient algorithms, both within the Statistical Query (SQ) and the Low-Degree Polynomial (LDP) framework, necessarily require $Omega(dkstar/2)$ samples.
  arXiv  Detail & Related papers  (2024-03-08T18:50:19Z)
• Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems [98.34292831923335]
  Motivated by the problem of online correlation analysis, we propose the emphStochastic Scaled-Gradient Descent (SSD) algorithm. We bring these ideas together in an application to online correlation analysis, deriving for the first time an optimal one-time-scale algorithm with an explicit rate of local convergence to normality.
  arXiv  Detail & Related papers  (2021-12-29T18:46:52Z)
• A Unified View of Stochastic Hamiltonian Sampling [18.300078015845262]
  This work revisits the theoretical properties of Hamiltonian differential equations (SDEs) for posterior sampling. We study the two types of errors that arise from numerical SDE simulation: the discretization error and the error due to noisy gradient estimates.
  arXiv  Detail & Related papers  (2021-06-30T16:50:11Z)
• Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning [59.71676469100807]
  This work sharpens the sample complexity of synchronous Q-learning to an order of $frac|mathcalS|| (1-gamma)4varepsilon2$ for any $0varepsilon 1$. Our finding unveils the effectiveness of vanilla Q-learning, which matches that of speedy Q-learning without requiring extra computation and storage.
  arXiv  Detail & Related papers  (2021-02-12T14:22:05Z)
• Stochastic Approximation for Online Tensorial Independent Component Analysis [98.34292831923335]
  Independent component analysis (ICA) has been a popular dimension reduction tool in statistical machine learning and signal processing. In this paper, we present a by-product online tensorial algorithm that estimates for each independent component.
  arXiv  Detail & Related papers  (2020-12-28T18:52:37Z)
• On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces [208.67848059021915]
  We study the exploration-exploitation tradeoff at the core of reinforcement learning. In particular, we prove that the complexity of the function class $mathcalF$ characterizes the complexity of the function. Our regret bounds are independent of the number of episodes.
  arXiv  Detail & Related papers  (2020-11-09T18:32:22Z)
• Information-Theoretic Limits for the Matrix Tensor Product [8.206394018475708]
  This paper studies a high-dimensional inference problem involving the matrix tensor product of random matrices. On the technical side, this paper introduces some new techniques for the analysis of high-dimensional matrix-preserving signals.
  arXiv  Detail & Related papers  (2020-05-22T17:03:48Z)

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.