Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts

• URL: http://arxiv.org/abs/2009.10622v7
• Date: Tue, 2 Jul 2024 17:04:08 GMT
• Title: Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts
• Authors: TrungTin Nguyen, Hien D Nguyen, Faicel Chamroukhi, Geoffrey J McLachlan,
• Abstract summary: We consider the class of softmax-gated Gaussian MoE (SGMoE) models with softmax gating functions and Gaussian experts. To the best of our knowledge, we are the first to investigate the $l_1$-regularization properties of SGMoE models from a non-asymptotic perspective. We provide a lower bound on the regularization parameter of the Lasso penalty that ensures non-asymptotic theoretical control of the Kullback--Leibler loss of the Lasso estimator for SGMoE models.
• Score: 2.794896499906838
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate the estimation properties of the mixture of experts (MoE) model in a high-dimensional setting, where the number of predictors is much larger than the sample size, and for which the literature is particularly lacking in theoretical results. We consider the class of softmax-gated Gaussian MoE (SGMoE) models, defined as MoE models with softmax gating functions and Gaussian experts, and focus on the theoretical properties of their $l_1$-regularized estimation via the Lasso. To the best of our knowledge, we are the first to investigate the $l_1$-regularization properties of SGMoE models from a non-asymptotic perspective, under the mildest assumptions, namely the boundedness of the parameter space. We provide a lower bound on the regularization parameter of the Lasso penalty that ensures non-asymptotic theoretical control of the Kullback--Leibler loss of the Lasso estimator for SGMoE models. Finally, we carry out a simulation study to empirically validate our theoretical findings.

Related papers

• Method-of-Moments Inference for GLMs and Doubly Robust Functionals under Proportional Asymptotics [30.324051162373973]
  We consider the estimation of regression coefficients and signal-to-noise ratio in high-dimensional Generalized Linear Models (GLMs) We derive Consistent and Asymptotically Normal (CAN) estimators of our targets of inference. We complement our theoretical results with numerical experiments and comparisons with existing literature.
  arXiv  Detail & Related papers  (2024-08-12T12:43:30Z)
• Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts [78.3687645289918]
  We show that the sigmoid gating function enjoys a higher sample efficiency than the softmax gating for the statistical task of expert estimation. We find that experts formulated as feed-forward networks with commonly used activation such as ReLU and GELU enjoy faster convergence rates under the sigmoid gating.
  arXiv  Detail & Related papers  (2024-05-22T21:12:34Z)
• Data-freeWeight Compress and Denoise for Large Language Models [101.53420111286952]
  We propose a novel approach termed Data-free Joint Rank-k Approximation for compressing the parameter matrices. We achieve a model pruning of 80% parameters while retaining 93.43% of the original performance without any calibration data.
  arXiv  Detail & Related papers  (2024-02-26T05:51:47Z)
• On Least Square Estimation in Softmax Gating Mixture of Experts [78.3687645289918]
  We investigate the performance of the least squares estimators (LSE) under a deterministic MoE model. We establish a condition called strong identifiability to characterize the convergence behavior of various types of expert functions. Our findings have important practical implications for expert selection.
  arXiv  Detail & Related papers  (2024-02-05T12:31:18Z)
• Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts? [27.924615931679757]
  We explore the impacts of a dense-to-sparse gating mixture of experts (MoE) on the maximum likelihood estimation under the MoE. We propose using a novel activation dense-to-sparse gate, which routes the output of a linear layer to an activation function before delivering them to the softmax function.
  arXiv  Detail & Related papers  (2024-01-25T01:09:09Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts [28.13187489224953]
  We propose a novel class of modified softmax gating functions which transform the input before delivering them to the gating functions. As a result, the previous interaction disappears and the parameter estimation rates are significantly improved.
  arXiv  Detail & Related papers  (2023-10-22T05:32:19Z)
• Algebraic and Statistical Properties of the Ordinary Least Squares Interpolator [3.4320157633663064]
  We provide results for the minimum $ell$-norm OLS interpolator. We present statistical results such as an extension of the Gauss-Markov theorem. We conduct simulations that further explore the properties of the OLS interpolator.
  arXiv  Detail & Related papers  (2023-09-27T16:41:10Z)
• Inverting brain grey matter models with likelihood-free inference: a tool for trustable cytoarchitecture measurements [62.997667081978825]
  characterisation of the brain grey matter cytoarchitecture with quantitative sensitivity to soma density and volume remains an unsolved challenge in dMRI. We propose a new forward model, specifically a new system of equations, requiring a few relatively sparse b-shells. We then apply modern tools from Bayesian analysis known as likelihood-free inference (LFI) to invert our proposed model.
  arXiv  Detail & Related papers  (2021-11-15T09:08:27Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• A non-asymptotic penalization criterion for model selection in mixture of experts models [1.491109220586182]
  We consider the Gaussian-gated localized MoE (GLoME) regression model for modeling heterogeneous data. This model poses challenging questions with respect to the statistical estimation and model selection problems. We study the problem of estimating the number of components of the GLoME model, in a penalized maximum likelihood estimation framework.
  arXiv  Detail & Related papers  (2021-04-06T16:24:55Z)

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.