English
Related papers

Related papers: A Model of Double Descent for High-dimensional Bin…

200 papers

Gaussian Process (GPs) models are a rich distribution over functions with inductive biases controlled by a kernel function. Learning occurs through the optimisation of kernel hyperparameters using the marginal likelihood as the objective.…

Machine Learning · Statistics 2021-11-22 Fergus Simpson , Vidhi Lalchand , Carl Edward Rasmussen

Recent advances in machine learning have been achieved by using overparametrized models trained until near interpolation of the training data. It was shown, e.g., through the double descent phenomenon, that the number of parameters is a…

Machine Learning · Statistics 2024-03-14 Hong Hu , Yue M. Lu , Theodor Misiakiewicz

Most theoretical studies explaining the regularization effect in deep learning have only focused on gradient descent with a sufficient small learning rate or even gradient flow (infinitesimal learning rate). Such researches, however, have…

Machine Learning · Computer Science 2020-12-17 Wei Huang , Weitao Du , Richard Yi Da Xu , Chunrui Liu

We study class-imbalanced linear classification in a high-dimensional Gaussian mixture model. We develop a tight, closed form approximation for the test error of several practical learning methods, including logit adjustment and class…

Machine Learning · Computer Science 2025-03-10 Eliav Mor , Yair Carmon

We show that running gradient descent with variable learning rate guarantees loss $f(x) \leq 1.1 \cdot f(x^*) + \epsilon$ for the logistic regression objective, where the error $\epsilon$ decays exponentially with the number of iterations…

Machine Learning · Computer Science 2023-06-27 Kyriakos Axiotis , Maxim Sviridenko

Single-Index Models are high-dimensional regression problems with planted structure, whereby labels depend on an unknown one-dimensional projection of the input via a generic, non-linear, and potentially non-deterministic transformation. As…

Machine Learning · Computer Science 2024-03-14 Alex Damian , Loucas Pillaud-Vivien , Jason D. Lee , Joan Bruna

Double descent presents a counter-intuitive aspect within the machine learning domain, and researchers have observed its manifestation in various models and tasks. While some theoretical explanations have been proposed for this phenomenon…

Machine Learning · Computer Science 2024-04-26 Yufei Gu , Xiaoqing Zheng , Tomaso Aste

We introduce a simple and scalable method for training Gaussian process (GP) models that exploits cross-validation and nearest neighbor truncation. To accommodate binary and multi-class classification we leverage P\`olya-Gamma auxiliary…

Machine Learning · Statistics 2022-03-10 Martin Jankowiak , Geoff Pleiss

Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks without providing any insight into their nature.…

Machine Learning · Computer Science 2019-10-16 Paavo Parmas , Masashi Sugiyama

We study a distributed consensus-based stochastic gradient descent (SGD) algorithm and show that the rate of convergence involves the spectral properties of two matrices: the standard spectral gap of a weight matrix from the network…

Optimization and Control · Mathematics 2016-09-02 Avleen S. Bijral , Anand D. Sarwate , Nathan Srebro

Recent research has observed that in machine learning optimization, gradient descent (GD) often operates at the edge of stability (EoS) [Cohen, et al., 2021], where the stepsizes are set to be large, resulting in non-monotonic losses…

Machine Learning · Computer Science 2023-10-17 Jingfeng Wu , Vladimir Braverman , Jason D. Lee

We consider stochastic gradient descent (SGD) for least-squares regression with potentially several passes over the data. While several passes have been widely reported to perform practically better in terms of predictive performance on…

Machine Learning · Computer Science 2018-11-26 Loucas Pillaud-Vivien , Alessandro Rudi , Francis Bach

The kernel function and its hyperparameters are the central model selection choice in a Gaussian proces (Rasmussen and Williams, 2006). Typically, the hyperparameters of the kernel are chosen by maximising the marginal likelihood, an…

Machine Learning · Statistics 2022-11-07 Vidhi Lalchand , Wessel P. Bruinsma , David R. Burt , Carl E. Rasmussen

We study the problem of differentially private linear regression where each data point is sampled from a fixed sub-Gaussian style distribution. We propose and analyze a one-pass mini-batch stochastic gradient descent method (DP-AMBSSGD)…

Machine Learning · Computer Science 2022-07-14 Prateek Varshney , Abhradeep Thakurta , Prateek Jain

This article characterizes the exact asymptotics of random Fourier feature (RFF) regression, in the realistic setting where the number of data samples $n$, their dimension $p$, and the dimension of feature space $N$ are all large and…

Machine Learning · Statistics 2022-01-11 Zhenyu Liao , Romain Couillet , Michael W. Mahoney

We consider gradient descent (GD) with a constant stepsize applied to logistic regression with linearly separable data, where the constant stepsize $\eta$ is so large that the loss initially oscillates. We show that GD exits this initial…

Machine Learning · Computer Science 2024-06-11 Jingfeng Wu , Peter L. Bartlett , Matus Telgarsky , Bin Yu

Score matching has become a central training objective in modern generative modeling, particularly in diffusion models, where it is used to learn high-dimensional data distributions through the estimation of score functions. Despite its…

Machine Learning · Computer Science 2025-12-01 Yiran Zhang , Weihang Xu , Mo Zhou , Maryam Fazel , Simon Shaolei Du

Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very…

Machine Learning · Computer Science 2019-11-28 Yuan Cao , Quanquan Gu

Likelihood-based, or explicit, deep generative models use neural networks to construct flexible high-dimensional densities. This formulation directly contradicts the manifold hypothesis, which states that observed data lies on a…

Machine Learning · Statistics 2022-11-30 Gabriel Loaiza-Ganem , Brendan Leigh Ross , Jesse C. Cresswell , Anthony L. Caterini

Understanding generalization and estimation error of estimators for simple models such as linear and generalized linear models has attracted a lot of attention recently. This is in part due to an interesting observation made in machine…

Machine Learning · Statistics 2021-03-09 Mojtaba Sahraee-Ardakan , Tung Mai , Anup Rao , Ryan Rossi , Sundeep Rangan , Alyson K. Fletcher