Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension

• URL: http://arxiv.org/abs/2201.13383v1
• Date: Mon, 31 Jan 2022 17:44:58 GMT
• Title: Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension
• Authors: Bruno Loureiro and C\'edric Gerbelot and Maria Refinetti and Gabriele Sicuro and Florent Krzakala
• Abstract summary: We develop a theory for the study of fluctuations in an ensemble of generalised linear models trained on different, but correlated, features. We provide a complete description of the joint distribution of the empirical risk minimiser for generic convex loss and regularisation in the high-dimensional limit.
• Score: 25.711297863946193
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: From the sampling of data to the initialisation of parameters, randomness is ubiquitous in modern Machine Learning practice. Understanding the statistical fluctuations engendered by the different sources of randomness in prediction is therefore key to understanding robust generalisation. In this manuscript we develop a quantitative and rigorous theory for the study of fluctuations in an ensemble of generalised linear models trained on different, but correlated, features in high-dimensions. In particular, we provide a complete description of the asymptotic joint distribution of the empirical risk minimiser for generic convex loss and regularisation in the high-dimensional limit. Our result encompasses a rich set of classification and regression tasks, such as the lazy regime of overparametrised neural networks, or equivalently the random features approximation of kernels. While allowing to study directly the mitigating effect of ensembling (or bagging) on the bias-variance decomposition of the test error, our analysis also helps disentangle the contribution of statistical fluctuations, and the singular role played by the interpolation threshold that are at the roots of the "double-descent" phenomenon.

Related papers

• GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations [77.34726150561087]
  We propose a holistic approach for the detection of generalization errors in deep neural networks. GIT combines the usage of gradient information and invariance transformations. Our experiments demonstrate the superior performance of GIT compared to the state-of-the-art on a variety of network architectures.
  arXiv  Detail & Related papers  (2023-07-05T22:04:38Z)
• Learning Linear Causal Representations from Interventions under General Nonlinear Mixing [52.66151568785088]
  We prove strong identifiability results given unknown single-node interventions without access to the intervention targets. This is the first instance of causal identifiability from non-paired interventions for deep neural network embeddings.
  arXiv  Detail & Related papers  (2023-06-04T02:32:12Z)
• Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach [1.4469725791865984]
  We characterise the learning of a mixture of two clouds of data points with generic centroids. We study the generalisation performance of the obtained estimator, we analyse the role of regularisation, and we analytically the separability transition.
  arXiv  Detail & Related papers  (2023-04-06T07:53:05Z)
• Optimal regularizations for data generation with probabilistic graphical models [0.0]
  Empirically, well-chosen regularization schemes dramatically improve the quality of the inferred models. We consider the particular case of L 2 and L 1 regularizations in the Maximum A Posteriori (MAP) inference of generative pairwise graphical models.
  arXiv  Detail & Related papers  (2021-12-02T14:45:16Z)
• 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)
• The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks [51.1848572349154]
  neural network models that perfectly fit noisy data can generalize well to unseen test data. We consider interpolating two-layer linear neural networks trained with gradient flow on the squared loss and derive bounds on the excess risk.
  arXiv  Detail & Related papers  (2021-08-25T22:01:01Z)
• Uniform Convergence, Adversarial Spheres and a Simple Remedy [40.44709296304123]
  Previous work has cast doubt on the general framework of uniform convergence and its ability to explain generalization in neural networks. We provide an extensive theoretical investigation of the previously studied data setting through the lens of infinitely-wide models. We prove that the Neural Tangent Kernel (NTK) also suffers from the same phenomenon and we uncover its origin.
  arXiv  Detail & Related papers  (2021-05-07T20:23:01Z)
• Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition [34.235007566913396]
  We describe an interpretable, symmetric decomposition of the variance into terms associated with the labels. We find that the bias decreases monotonically with the network width, but the variance terms exhibit non-monotonic behavior. We also analyze the strikingly rich phenomenology that arises.
  arXiv  Detail & Related papers  (2020-11-04T21:04:02Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)
• Generalisation error in learning with random features and the hidden manifold model [23.71637173968353]
  We study generalised linear regression and classification for a synthetically generated dataset. We consider the high-dimensional regime and using the replica method from statistical physics. We show how to obtain the so-called double descent behaviour for logistic regression with a peak at the threshold. We discuss the role played by correlations in the data generated by the hidden manifold model.
  arXiv  Detail & Related papers  (2020-02-21T14:49:41Z)

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.