English
Related papers

Related papers: Is SGD a Bayesian sampler? Well, almost

200 papers

Currently, it is hard to reap the benefits of deep learning for Bayesian methods, which allow the explicit specification of prior knowledge and accurately capture model uncertainty. We present Prior-Data Fitted Networks (PFNs). PFNs…

Machine Learning · Computer Science 2024-08-14 Samuel Müller , Noah Hollmann , Sebastian Pineda Arango , Josif Grabocka , Frank Hutter

Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks. Where a Bayesian treatment is usually associated with high-quality predictions and uncertainties, the practical reality has been…

Background. A main theoretical puzzle is why over-parameterized Neural Networks (NNs) generalize well when trained to zero loss (i.e., so they interpolate the data). Usually, the NN is trained with Stochastic Gradient Descent (SGD) or one…

Machine Learning · Computer Science 2025-02-18 Gon Buzaglo , Itamar Harel , Mor Shpigel Nacson , Alon Brutzkus , Nathan Srebro , Daniel Soudry

Training Deep Neural Networks (DNNs) with small batches using Stochastic Gradient Descent (SGD) yields superior test performance compared to larger batches. The specific noise structure inherent to SGD is known to be responsible for this…

Machine Learning · Statistics 2024-02-14 Tom Sander , Maxime Sylvestre , Alain Durmus

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

Computation and Language · Computer Science 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-context learning. Despite their strong empirical performance…

Machine Learning · Statistics 2026-05-27 Gyeonghun Kang , Changwoo J. Lee , Xiang Cheng

Sum-product networks (SPNs) are probabilistic models characterized by exact and fast evaluation of fundamental probabilistic operations. Its superior computational tractability has led to applications in many fields, such as machine…

Machine Learning · Statistics 2024-06-19 Soma Yokoi , Issei Sato

Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance trade-off in classical learning theory. Recent studies claimed…

Machine Learning · Computer Science 2022-11-15 Xiao Zhang , Haoyi Xiong , Dongrui Wu

Neural-net-induced Gaussian process (NNGP) regression inherits both the high expressivity of deep neural networks (deep NNs) as well as the uncertainty quantification property of Gaussian processes (GPs). We generalize the current NNGP to…

Machine Learning · Computer Science 2019-03-27 Guofei Pang , Liu Yang , George Em Karniadakis

Recently it was shown in several papers that backpropagation is able to find the global minimum of the empirical risk on the training data using over-parametrized deep neural networks. In this paper a similar result is shown for deep neural…

Statistics Theory · Mathematics 2020-01-15 Michael Kohler , Adam Krzyzak

Despite being highly over-parametrized, and having the ability to fully interpolate the training data, deep networks are known to generalize well to unseen data. It is now understood that part of the reason for this is that the training…

Machine Learning · Computer Science 2023-02-21 Danil Akhtiamov , Babak Hassibi

While significant theoretical progress has been achieved, unveiling the generalization mystery of overparameterized neural networks still remains largely elusive. In this paper, we study the generalization behavior of shallow neural…

Machine Learning · Computer Science 2022-09-21 Yunwen Lei , Rong Jin , Yiming Ying

In this work, we focus on variational Bayesian inference on the sparse Deep Neural Network (DNN) modeled under a class of spike-and-slab priors. Given a pre-specified sparse DNN structure, the corresponding variational posterior contraction…

Statistics Theory · Mathematics 2020-08-04 Jincheng Bai , Qifan Song , Guang Cheng

Deep feedforward neural networks (DFNNs) are a powerful tool for functional approximation. We describe flexible versions of generalized linear and generalized linear mixed models incorporating basis functions formed by a DFNN. The…

Computation · Statistics 2018-05-28 Minh-Ngoc Tran , Nghia Nguyen , David Nott , Robert Kohn

This work is substituted by the paper in arXiv:2011.14066. Stochastic gradient descent is the de facto algorithm for training deep neural networks (DNNs). Despite its popularity, it still requires fine tuning in order to achieve its best…

Machine Learning · Statistics 2020-12-02 Vatsal Shah , Anastasios Kyrillidis , Sujay Sanghavi

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

Machine Learning · Computer Science 2018-01-17 Pratik Chaudhari , Stefano Soatto

Bayesian approaches for training deep neural networks (BNNs) have received significant interest and have been effectively utilized in a wide range of applications. There have been several studies on the properties of posterior…

Machine Learning · Statistics 2024-03-22 Insung Kong , Yongdai Kim

The classical statistical learning theory implies that fitting too many parameters leads to overfitting and poor performance. That modern deep neural networks generalize well despite a large number of parameters contradicts this finding and…

Machine Learning · Statistics 2022-10-18 Masaaki Imaizumi , Johannes Schmidt-Hieber

Bayesian Neural Networks (BNNs) provide a probabilistic interpretation for deep learning models by imposing a prior distribution over model parameters and inferring a posterior distribution based on observed data. The model sampled from the…

Machine Learning · Computer Science 2023-11-15 Van-Anh Nguyen , Tung-Long Vuong , Hoang Phan , Thanh-Toan Do , Dinh Phung , Trung Le

Several works have proposed Simplicity Bias (SB)---the tendency of standard training procedures such as Stochastic Gradient Descent (SGD) to find simple models---to justify why neural networks generalize well [Arpit et al. 2017, Nakkiran et…

Machine Learning · Computer Science 2020-10-29 Harshay Shah , Kaustav Tamuly , Aditi Raghunathan , Prateek Jain , Praneeth Netrapalli