English
Related papers

Related papers: Mitigating deep double descent by concatenating in…

200 papers

Double machine learning is a statistical method for leveraging complex black-box models to construct approximately unbiased treatment effect estimates given observational data with high-dimensional covariates, under the assumption of a…

Machine Learning · Statistics 2022-06-03 Nitai Fingerhut , Matteo Sesia , Yaniv Romano

In deep learning it is common to overparameterize neural networks, that is, to use more parameters than training samples. Quite surprisingly training the neural network via (stochastic) gradient descent leads to models that generalize very…

Optimization and Control · Mathematics 2025-01-30 Hung-Hsu Chou , Johannes Maly , Holger Rauhut

Integrating probability and nonprobability survey samples is an important problem in modern survey sampling. Nonprobability samples often contain rich outcome information but may lack population representativeness, whereas probability…

Statistics Theory · Mathematics 2026-05-28 Yufang Dai , Shihua Luo , Wendy Lou , Zilin Wang , Xuewen Lu

A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics…

A recent line of work has shown remarkable behaviors of the generalization error curves in simple learning models. Even the least-squares regression has shown atypical features such as the model-wise double descent, and further works have…

Machine Learning · Statistics 2022-12-20 Antoine Bodin , Nicolas Macris

Motivated by the observation that humans can learn patterns from two given images at one time, we propose a dual pattern learning network architecture in this paper. Unlike conventional networks, the proposed architecture has two input…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Haimin Zhang , Min Xu

Although statistical learning theory provides a robust framework to understand supervised learning, many theoretical aspects of deep learning remain unclear, in particular how different architectures may lead to inductive bias when trained…

Machine Learning · Computer Science 2024-03-27 Cédric Gerbelot , Avetik Karagulyan , Stefani Karp , Kavya Ravichandran , Menachem Stern , Nathan Srebro

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the…

Machine Learning · Computer Science 2021-10-01 James O' Neill , Sourav Dutta , Haytham Assem

We investigate the asymptotic risk of a general class of overparameterized likelihood models, including deep models. The recent empirical success of large-scale models has motivated several theoretical studies to investigate a scenario…

Machine Learning · Statistics 2021-03-16 Ryumei Nakada , Masaaki Imaizumi

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…

Computation and Language · Computer Science 2022-01-24 Qianben Chen , Richong Zhang , Yaowei Zheng , Yongyi Mao

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Chang-Hui Liang , Wan-Lei Zhao , Run-Qing Chen

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

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a…

Optimization and Control · Mathematics 2023-10-26 Pierre Marion , Raphaël Berthier

An important component of the success of large AI models is double descent, in which networks avoid overfitting as they grow relative to the amount of training data, instead improving their performance on unseen data. Here we demonstrate…

Disordered Systems and Neural Networks · Physics 2025-11-25 Sam Dillavou , Jason W Rocks , Jacob F Wycoff , Andrea J Liu , Douglas J Durian

Large-sample data became prevalent as data acquisition became cheaper and easier. While a large sample size has theoretical advantages for many statistical methods, it presents computational challenges. Sketching, or compression, is a…

Machine Learning · Statistics 2020-05-11 Alexander F. Lapanowski , Irina Gaynanova

Machine learning methods are commonly used to solve inverse problems, wherein an unknown signal must be estimated from few indirect measurements generated via a known acquisition procedure. In particular, neural networks perform well…

Machine Learning · Computer Science 2025-12-05 Hannah Laus , Suzanna Parkinson , Vasileios Charisopoulos , Felix Krahmer , Rebecca Willett

Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural networks (DCNNs), which significantly improve the performance…

Machine Learning · Computer Science 2016-11-01 Shuangfei Zhai , Yu Cheng , Weining Lu , Zhongfei Zhang

We introduce a randomly extrapolated primal-dual coordinate descent method that adapts to sparsity of the data matrix and the favorable structures of the objective function. Our method updates only a subset of primal and dual variables with…

Optimization and Control · Mathematics 2020-07-14 Ahmet Alacaoglu , Olivier Fercoq , Volkan Cevher

We study a continuous-time approximation of the stochastic gradient descent process for minimizing the population expected loss in learning problems. The main results establish general sufficient conditions for the convergence, extending…

Machine Learning · Computer Science 2025-11-03 Gabor Lugosi , Eulalia Nualart

We propose a two-scale neural network method for optimal control problems governed by convection-dominated convection-diffusion-reaction equations. Building on two-scale architectures developed for singularly perturbed forward problems, we…

Numerical Analysis · Mathematics 2026-05-19 Sijing Liu , Marcus Sarkis , Yi Zhang , Zhongqiang Zhang