English
Related papers

Related papers: UNREALIZABLE LEARNING IN FEEDFORWARD NEURAL NETWOR…

200 papers

We carry out an information-theoretical analysis of a two-layer neural network trained from input-output pairs generated by a teacher network with matching architecture, in overparametrized regimes. Our results come in the form of bounds…

Machine Learning · Computer Science 2023-07-13 Francesco Camilli , Daria Tieplova , Jean Barbier

Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We…

Machine Learning · Computer Science 2013-03-12 Tommi Vatanen , Tapani Raiko , Harri Valpola , Yann LeCun

Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over…

Machine Learning · Computer Science 2023-05-09 Ambar Pal , Jeremias Sulam

In this work, we study the training and generalization performance of two-layer neural networks (NNs) after one gradient descent step under structured data modeled by Gaussian mixtures. While previous research has extensively analyzed this…

Machine Learning · Statistics 2025-05-20 Samet Demir , Zafer Dogan

Machine unlearning, the ability to erase the effect of specific training samples without retraining from scratch, is critical for privacy, regulation, and efficiency. However, most progress in unlearning has been empirical, with little…

Machine Learning · Computer Science 2026-02-04 Wei-Kai Chang , Rajiv Khanna

We analyze the learning of noisy teacher-generated examples by nonlinear and differentiable student perceptrons using the cavity method. The generic activation of an example is a function of the cavity activation of the example, which is…

Disordered Systems and Neural Networks · Physics 2009-11-07 Peixun Luo , K. Y. Michael Wong

Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR). However, tremendous scale of datasets inevitably lead to noisy data, which obviously reduce the…

Computer Vision and Pattern Recognition · Computer Science 2019-03-27 Wei Hu , Yangyu Huang , Fan Zhang , Ruirui Li

Self-supervised learning is an increasingly popular approach to unsupervised learning, achieving state-of-the-art results. A prevalent approach consists in contrasting data points and noise points within a classification task: this requires…

Machine Learning · Statistics 2023-01-25 Omar Chehab , Alexandre Gramfort , Aapo Hyvarinen

Inference is typically intractable in high-treewidth undirected graphical models, making maximum likelihood learning a challenge. One way to overcome this is to restrict parameters to a tractable set, most typically the set of…

Machine Learning · Computer Science 2015-11-02 Justin Domke

Deep neural networks are known to exhibit a `double descent' behavior as the number of parameters increases. Recently, it has also been shown that an `epochwise double descent' effect exists in which the generalization error initially…

Machine Learning · Computer Science 2021-08-30 Cory Stephenson , Tyler Lee

We study asymmetric rank-one spiked tensor models in the high-dimensional regime, where the noise entries are independent and identically distributed with zero mean, unit variance, and finite fourth moment. This extends the classical…

Statistics Theory · Mathematics 2026-03-12 Yanjin Xiang , Zhihua Zhang

Transformation Synchronization is the problem of recovering absolute transformations from a given set of pairwise relative motions. Despite its usefulness, the problem remains challenging due to the influences from noisy and outlier…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Zi Jian Yew , Gim Hee Lee

Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks under certain conditions, one step of gradient descent on the…

Machine Learning · Statistics 2025-04-11 Behrad Moniri , Donghwan Lee , Hamed Hassani , Edgar Dobriban

Weak-to-strong generalization refers to the phenomenon where a stronger model trained under supervision from a weaker one can outperform its teacher. While prior studies aim to explain this effect, most theoretical insights are limited to…

Machine Learning · Computer Science 2025-10-30 Junsoo Oh , Jerry Song , Chulhee Yun

We consider dense, associative neural-networks trained by a teacher (i.e., with supervision) and we investigate their computational capabilities analytically, via statistical-mechanics of spin glasses, and numerically, via Monte Carlo…

Disordered Systems and Neural Networks · Physics 2023-08-16 Elena Agliari , Linda Albanese , Francesco Alemanno , Andrea Alessandrelli , Adriano Barra , Fosca Giannotti , Daniele Lotito , Dino Pedreschi

We analysed the generalisation performance of a binary perceptron with quantum fluctuations using the replica method. An exponential number of local minima dominate the energy landscape of the binary perceptron. Local search algorithms…

Disordered Systems and Neural Networks · Physics 2021-07-07 Shunta Arai , Masayuki Ohzeki , Kazuyuki Tanaka

The performance of large neural networks can be judged not only by their storage capacity but also by the time required for learning. A polynomial learning algorithm with learning time $\sim N^2$ in a network with $N$ units might be…

Disordered Systems and Neural Networks · Physics 2017-02-08 Heinz Horner , Anthea Bethge

Large neural networks trained in the overparameterized regime are able to fit noise to zero train error. Recent work \citep{nakkiran2020distributional} has empirically observed that such networks behave as "conditional samplers" from the…

Machine Learning · Computer Science 2022-03-29 Gal Kaplun , Eran Malach , Preetum Nakkiran , Shai Shalev-Shwartz

We study the improper learning of multi-layer neural networks. Suppose that the neural network to be learned has $k$ hidden layers and that the $\ell_1$-norm of the incoming weights of any neuron is bounded by $L$. We present a kernel-based…

Machine Learning · Computer Science 2015-10-14 Yuchen Zhang , Jason D. Lee , Michael I. Jordan

This article addresses the challenge of learning effective regularizers for linear inverse problems. We analyze and compare several types of learned variational regularization against the theoretical benchmark of the optimal affine…

Numerical Analysis · Mathematics 2025-10-15 Sebastian Banert , Christoph Brauer , Dirk Lorenz , Lionel Tondji