English
Related papers

Related papers: A note on sample complexity of learning binary out…

200 papers

Classifiers trained using conventional empirical risk minimization or maximum likelihood methods are known to suffer dramatic performance degradations when tested over examples adversarially selected based on knowledge of the classifier's…

Machine Learning · Statistics 2018-03-01 Alireza Bagheri , Osvaldo Simeone , Bipin Rajendran

This paper argues that the judicial use of formal language theory and grammatical inference are invaluable tools in understanding how deep neural networks can and cannot represent and learn long-term dependencies in temporal sequences.…

Computation and Language · Computer Science 2017-10-17 Enes Avcu , Chihiro Shibata , Jeffrey Heinz

Although deep neural networks have provided impressive gains in performance, these improvements often come at the cost of increased computational complexity and expense. In many cases, such as 3D volume or video classification tasks, not…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Sharath M Shankaranarayana , Soumava Kumar Roy , Prasad Sudhakar , Chandan Aladahalli

Mostof the existing literature on supervised machine learning problems focuses on the case when the training data set is drawn from an i.i.d. sample. However, many practical problems are characterized by temporal dependence and strong…

Statistics Theory · Mathematics 2023-01-23 Nikola Sandrić , Stjepan Šebek

It is argued that deep learning is efficient for data that is generated from hierarchal generative models. Examples of such generative models include wavelet scattering networks, functions of compositional structure, and deep rendering…

Machine Learning · Computer Science 2018-09-06 Elchanan Mossel

We consider the problem of finding a two-layer neural network with sigmoid, rectified linear unit (ReLU), or binary step activation functions that "fits" a training data set as accurately as possible as quantified by the training error; and…

Machine Learning · Statistics 2022-04-06 David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

Learning distribution families over $\mathbb{R}^d$ is a fundamental problem in unsupervised learning and statistics. A central question in this setting is whether a given family of distributions possesses sufficient structure to be (at…

Machine Learning · Statistics 2025-06-10 Arefe Boushehrian , Amir Najafi

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L_2 regularization: We introduce the \gamma-adapted-dimension, which is a simple function of the spectrum of a…

Machine Learning · Computer Science 2015-03-17 Sivan Sabato , Nathan Srebro , Naftali Tishby

Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. By succinctly…

Machine Learning · Computer Science 2021-10-22 Alireza Sadeghi , Meng Ma , Bingcong Li , Georgios B. Giannakis

Semisupervised learning has emerged as a popular framework for improving modeling accuracy while controlling labeling cost. Based on an extension of stochastic composite likelihood we quantify the asymptotic accuracy of generative…

Machine Learning · Computer Science 2010-03-02 Joshua V Dillon , Krishnakumar Balasubramanian , Guy Lebanon

In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong augmentation, are still correctly classified with high…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Guan Gui , Zhen Zhao , Lei Qi , Luping Zhou , Lei Wang , Yinghuan Shi

In Deep Learning, a well-known approach for training a Deep Neural Network starts by training a generative Deep Belief Network model, typically using Contrastive Divergence (CD), then fine-tuning the weights using backpropagation or other…

Quantum Physics · Physics 2015-10-22 Steven H. Adachi , Maxwell P. Henderson

Let $(X,Y)\in\mathcal{X}\times \mathcal{Y}$ be a random couple with unknown distribution $P$. Let $\GG$ be a class of measurable functions and $\ell$ a loss function. The problem of statistical learning deals with the estimation of the…

Statistics Theory · Mathematics 2012-07-12 Sébastien Loustau

We consider the problem of learning a non-negative linear classifier with a $1$-norm of at most $k$, and a fixed threshold, under the hinge-loss. This problem generalizes the problem of learning a $k$-monotone disjunction. We prove that we…

Machine Learning · Statistics 2016-04-19 Sivan Sabato , Shai Shalev-Shwartz , Nathan Srebro , Daniel Hsu , Tong Zhang

In supervised learning with distributional inputs in the two-stage sampling setup, relevant to applications like learning-based medical screening or causal learning, the inputs (which are probability distributions) are not accessible in the…

Machine Learning · Computer Science 2026-01-22 Christian Fiedler

Spiking Neural Networks (SNNs) capture some of the efficiency of biological brains for inference and learning via the dynamic, online, event-driven processing of binary time series. Most existing learning algorithms for SNNs are based on…

Machine Learning · Computer Science 2021-01-06 Hyeryung Jang , Osvaldo Simeone

Dependency networks (Heckerman et al., 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their…

Machine Learning · Computer Science 2026-04-02 Kazuya Takabatake , Shotaro Akaho

Complex systems, ranging from soft materials to wireless communication, are often organised as random geometric networks in which nodes and edges evenly fill up the volume of some space. Studying such networks is difficult because they…

Probability · Mathematics 2022-07-19 Ivan Kryven , Rik Versendaal

Neural Network-based active learning (NAL) is a cost-effective data selection technique that utilizes neural networks to select and train on a small subset of samples. While existing work successfully develops various effective or…

Machine Learning · Computer Science 2024-06-07 Dake Bu , Wei Huang , Taiji Suzuki , Ji Cheng , Qingfu Zhang , Zhiqiang Xu , Hau-San Wong

The algorithm for Monte Carlo simulation of parton-level events based on an Artificial Neural Network (ANN) proposed in arXiv:1810.11509 is used to perform a simulation of $H\to 4\ell$ decay. Improvements in the training algorithm have been…

High Energy Physics - Phenomenology · Physics 2021-02-03 I-Kai Chen , Matthew D. Klimek , Maxim Perelstein