English
Related papers

Related papers: Optimal Convergence Rates of Deep Neural Network C…

200 papers

Deep neural network (DNN) classifiers are often overconfident, producing miscalibrated class probabilities. In high-risk applications like healthcare, practitioners require $\textit{fully calibrated}$ probability predictions for…

Machine Learning · Statistics 2022-12-09 Zhen Lin , Shubhendu Trivedi , Jimeng Sun

This paper introduces the first globally optimal algorithm for the empirical risk minimization problem of two-layer maxout and ReLU networks, i.e., minimizing the number of misclassifications. The algorithm has a worst-case time complexity…

Machine Learning · Computer Science 2026-05-12 Xi He , Yi Miao , Max A. Little

We develop minimax optimal risk bounds for the general learning task consisting in predicting as well as the best function in a reference set $\mathcal{G}$ up to the smallest possible additive term, called the convergence rate. When the…

Statistics Theory · Mathematics 2009-09-09 Jean-Yves Audibert

This paper develops fundamental limits of deep neural network learning by characterizing what is possible if no constraints are imposed on the learning algorithm and on the amount of training data. Concretely, we consider Kolmogorov-optimal…

Machine Learning · Computer Science 2021-03-15 Dennis Elbrächter , Dmytro Perekrestenko , Philipp Grohs , Helmut Bölcskei

Overparameterized deep neural networks (DNNs), if not sufficiently regularized, are susceptible to overfitting their training examples and not generalizing well to test data. To discourage overfitting, researchers have developed…

Machine Learning · Computer Science 2024-04-12 Nathaniel Dean , Dilip Sarkar

In binary classification framework, we are interested in making cost sensitive label predictions in the presence of uniform/symmetric label noise. We first observe that $0$-$1$ Bayes classifiers are not (uniform) noise robust in cost…

Machine Learning · Computer Science 2020-01-13 Sandhya Tripathi , N. Hemachandra

We investigate theoretical guarantees for the false-negative rate (FNR) -- the fraction of true causal edges whose orientation is not recovered, under single-variable random interventions and an $\epsilon$-interventional faithfulness…

Machine Learning · Computer Science 2025-11-05 Mathieu Chevalley , Arash Mehrjou , Patrick Schwab

Deep neural networks (DNNs) have numerous applications across various domains. Several optimization techniques, such as ResNet and SENet, have been proposed to improve model accuracy. These techniques improve the model performance by…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Wenxiang Xu , Tian Qiu , Linyun Zhou , Zunlei Feng , Mingli Song , Huiqiong Wang

The contextual combinatorial semi-bandit problem with linear payoff functions is a decision-making problem in which a learner chooses a set of arms with the feature vectors in each round under given constraints so as to maximize the sum of…

Bayesian neural networks (BNNs) offer a natural probabilistic formulation for inference in deep learning models. Despite their popularity, their optimality has received limited attention through the lens of statistical decision theory. In…

Statistics Theory · Mathematics 2026-04-07 Daniel Andrew Coulson , Martin T. Wells

Guiding the design of neural networks is of great importance to save enormous resources consumed on empirical decisions of architectural parameters. This paper constructs shallow sigmoid-type neural networks that achieve 100% accuracy in…

Machine Learning · Computer Science 2019-04-22 Youngjae Min , Hye Won Chung

The performance of machine learning classification algorithms are evaluated by estimating metrics, often from the confusion matrix, using training data and cross-validation. However, these do not prove that the best possible performance has…

Machine Learning · Statistics 2024-03-05 L. Crow , S. J. Watts

When model predictions inform downstream decision making, a natural question is under what conditions can the decision-makers simply respond to the predictions as if they were the true outcomes. Calibration suffices to guarantee that simple…

Machine Learning · Computer Science 2025-04-23 Jingwu Tang , Jiayun Wu , Zhiwei Steven Wu , Jiahao Zhang

In this work, we explore the possibility of using probabilistic learning to identify pulsar candidates. We make use of Deep Gaussian Process (DGP) and Deep Kernel Learning (DKL). Trained on a balanced training set in order to avoid the…

Instrumentation and Methods for Astrophysics · Physics 2022-10-12 Sambatra Andrianomena

Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This has motivated research on calibrated models, where…

Machine Learning · Computer Science 2026-05-25 Ramya Hebbalaguppe , Ajay Shastry , Soumya Suvra Ghosal , Chetan Arora

A main puzzle of deep neural networks (DNNs) revolves around the apparent absence of "overfitting", defined in this paper as follows: the expected error does not get worse when increasing the number of neurons or of iterations of gradient…

Machine Learning · Computer Science 2018-07-02 Tomaso Poggio , Qianli Liao , Brando Miranda , Andrzej Banburski , Xavier Boix , Jack Hidary

Convolutional neural networks (CNNs) trained with cross-entropy loss have proven to be extremely successful in classifying images. In recent years, much work has been done to also improve the theoretical understanding of neural networks.…

Statistics Theory · Mathematics 2024-04-30 Michael Kohler , Sophie Langer

We study the approximation capacity of some variation spaces corresponding to shallow ReLU$^k$ neural networks. It is shown that sufficiently smooth functions are contained in these spaces with finite variation norms. For functions with…

Machine Learning · Statistics 2024-06-05 Yunfei Yang , Ding-Xuan Zhou

Let $(Y,X_1,...,X_m)$ be a random vector. It is desired to predict $Y$ based on $(X_1,...,X_m)$. Examples of prediction methods are regression, classification using logistic regression or separating hyperplanes, and so on. We consider the…

Statistics Theory · Mathematics 2007-06-13 Eitan Greenshtein

When learning from positive and unlabelled data, it is a strong assumption that the positive observations are randomly sampled from the distribution of $X$ conditional on $Y = 1$, where X stands for the feature and Y the label. Most…

Machine Learning · Computer Science 2020-03-04 Fengxiang He , Tongliang Liu , Geoffrey I Webb , Dacheng Tao