English
Related papers

Related papers: Bayesian Double Descent

200 papers

Bayesian inverse problems use observed data to update a prior probability distribution for an unknown state or parameter of a scientific system to a posterior distribution conditioned on the data. In many applications, the unknown parameter…

Numerical Analysis · Mathematics 2026-05-12 Josie König , Elizabeth Qian , Melina A. Freitag

Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for…

Fitting a function by using linear combinations of a large number $N$ of `simple' components is one of the most fruitful ideas in statistical learning. This idea lies at the core of a variety of methods, from two-layer neural networks to…

Statistics Theory · Mathematics 2019-08-20 Adel Javanmard , Marco Mondelli , Andrea Montanari

Models with dimension more than the available sample size are now commonly used in various applications. A sensible inference is possible using a lower-dimensional structure. In regression problems with a large number of predictors, the…

Statistics Theory · Mathematics 2025-11-25 Sayantan Banerjee , Ismaël Castillo , Subhashis Ghosal

Contemporary machine learning methods will try to approach the Bayes error, as it is the lowest possible error any model can achieve. This paper postulates that any decision is composed of not one but two Bayesian decisions and that…

Machine Learning · Computer Science 2024-10-18 Stefan Jaeger

The volume of the distribution of weight sets associated with a loss value may be the source of implicit regularization from overparameterization due to the phenomenon of contracting volume with increasing dimensions for geometric figures…

Machine Learning · Computer Science 2022-09-27 Nicholas J. Teague

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Regression Discontinuity Design (RDD) is a popular framework for estimating a causal effect in settings where treatment is assigned if an observed covariate exceeds a fixed threshold. We consider estimation and inference in the common…

Statistics Theory · Mathematics 2025-04-16 Kevin Tao , Y. Samuel Wang , David Ruppert

We study the learning performance of gradient descent when the empirical risk is weakly convex, namely, the smallest negative eigenvalue of the empirical risk's Hessian is bounded in magnitude. By showing that this eigenvalue can control…

Machine Learning · Statistics 2021-06-02 Dominic Richards , Mike Rabbat

Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through the lens of the Minimum Description Length principle,…

Natural gradient descent is a principled method for adapting the parameters of a statistical model on-line using an underlying Riemannian parameter space to redefine the direction of steepest descent. The algorithm is examined via methods…

Disordered Systems and Neural Networks · Physics 2009-10-31 Magnus Rattray , David Saad

Uplift is a particular case of conditional treatment effect modeling. Such models deal with cause-and-effect inference for a specific factor, such as a marketing intervention or a medical treatment. In practice, these models are built on…

Machine Learning · Statistics 2021-05-12 Mouloud Belbahri , Olivier Gandouet , Alejandro Murua , Vahid Partovi Nia

Approximate Bayesian inference on the basis of summary statistics is well-suited to complex problems for which the likelihood is either mathematically or computationally intractable. However the methods that use rejection suffer from the…

Computation · Statistics 2010-05-04 M. G. B. Blum , O. Francois

This study demonstrates that double descent can be mitigated by adding a dropout layer adjacent to the fully connected linear layer. The unexpected double-descent phenomenon garnered substantial attention in recent years, resulting in…

Machine Learning · Computer Science 2025-08-08 Tian-Le Yang , Joe Suzuki

Models with intractable normalizing functions arise frequently in statistics. Common examples of such models include exponential random graph models for social networks and Markov point processes for ecology and disease modeling. Inference…

Computation · Statistics 2018-08-03 Jaewoo Park , Murali Haran

We demonstrate the ability of hybrid regularization methods to automatically avoid the double descent phenomenon arising in the training of random feature models (RFM). The hallmark feature of the double descent phenomenon is a spike in the…

Machine Learning · Computer Science 2020-12-15 Kelvin Kan , James G Nagy , Lars Ruthotto

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

Recent empirical and theoretical analyses of several commonly used prediction procedures reveal a peculiar risk behavior in high dimensions, referred to as double/multiple descent, in which the asymptotic risk is a non-monotonic function of…

Statistics Theory · Mathematics 2022-05-26 Pratik Patil , Arun Kumar Kuchibhotla , Yuting Wei , Alessandro Rinaldo

Gradient descent is one of the most widely used iterative algorithms in modern statistical learning. However, its precise algorithmic dynamics in high-dimensional settings remain only partially understood, which has limited its broader…

Statistics Theory · Mathematics 2025-11-19 Qiyang Han , Xiaocong Xu

One classical canon of statistics is that large models are prone to overfitting, and model selection procedures are necessary for high dimensional data. However, many overparameterized models, such as neural networks, perform very well in…

Machine Learning · Statistics 2021-01-05 Xi Chen , Qiang Liu , Xin T. Tong
‹ Prev 1 4 5 6 7 8 10 Next ›