English
Related papers

Related papers: Generalization Error Bounds for Iterative Recovery…

200 papers

Many algorithms have been recently proposed for causal machine learning. Yet, there is little to no theory on their quality, especially considering finite samples. In this work, we propose a theory based on generalization bounds that…

Machine Learning · Statistics 2024-05-16 Daniel Csillag , Claudio José Struchiner , Guilherme Tegoni Goedert

The flexibility of decision boundaries in neural networks that are unguided by training data is a well-known problem typically resolved with generalization methods. A surprising result from recent knowledge distillation (KD) literature is…

Machine Learning · Computer Science 2024-10-28 HeeSeung Jung , Kangil Kim , Hoyong Kim , Jong-Hun Shin

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

Generalization error bounds are essential to understanding machine learning algorithms. This paper presents novel expected generalization error upper bounds based on the average joint distribution between the output hypothesis and each…

Information Theory · Computer Science 2022-02-25 Gholamali Aminian , Yuheng Bu , Gregory Wornell , Miguel Rodrigues

Solving linear inverse problems plays a crucial role in numerous applications. Algorithm unfolding based, model-aware data-driven approaches have gained significant attention for effectively addressing these problems. Learned iterative…

We study the excess capacity of deep networks in the context of supervised classification. That is, given a capacity measure of the underlying hypothesis class - in our case, empirical Rademacher complexity - to what extent can we (a…

Machine Learning · Computer Science 2023-01-20 Florian Graf , Sebastian Zeng , Bastian Rieck , Marc Niethammer , Roland Kwitt

The ability of overparameterized deep networks to generalize well has been linked to the fact that stochastic gradient descent (SGD) finds solutions that lie in flat, wide minima in the training loss -- minima where the output of the…

Machine Learning · Computer Science 2019-06-03 Vaishnavh Nagarajan , J. Zico Kolter

We give algorithms with provable guarantees that learn a class of deep nets in the generative model view popularized by Hinton and others. Our generative model is an $n$ node multilayer neural net that has degree at most $n^{\gamma}$ for…

Machine Learning · Computer Science 2013-10-25 Sanjeev Arora , Aditya Bhaskara , Rong Ge , Tengyu Ma

We propose Rademacher complexity bounds for multiclass classifiers trained with a two-step semi-supervised model. In the first step, the algorithm partitions the partially labeled data and then identifies dense clusters containing $\kappa$…

Machine Learning · Statistics 2021-09-15 Yury Maximov , Massih-Reza Amini , Zaid Harchaoui

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

Machine Learning · Statistics 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang

In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation sometimes help, but…

Machine Learning · Computer Science 2020-11-23 Hrayr Harutyunyan , Kyle Reing , Greg Ver Steeg , Aram Galstyan

We consider information-theoretic bounds on expected generalization error for statistical learning problems in a networked setting. In this setting, there are $K$ nodes, each with its own independent dataset, and the models from each node…

Information Theory · Computer Science 2024-01-17 L. P. Barnes , Alex Dytso , H. V. Poor

The single-layer feedforward neural network with random weights is a recurring motif in the neural networks literature. The advantage of these networks is their simplified training, which reduces to solving a ridge-regression problem. A…

Machine Learning · Computer Science 2025-02-25 M. Andrecut

This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general theoretical framework, we establish a duality between…

Machine Learning · Statistics 2022-07-01 Eugenio Clerico , Amitis Shidani , George Deligiannidis , Arnaud Doucet

We consider neural networks with a single hidden layer and non-decreasing homogeneous activa-tion functions like the rectified linear units. By letting the number of hidden units grow unbounded and using classical non-Euclidean…

Machine Learning · Computer Science 2016-11-01 Francis Bach

Recently, contrastive learning has found impressive success in advancing the state of the art in solving various machine learning tasks. However, the existing generalization analysis is very limited or even not meaningful. In particular,…

Machine Learning · Computer Science 2023-03-01 Yunwen Lei , Tianbao Yang , Yiming Ying , Ding-Xuan Zhou

Providing generalization guarantees for stochastic optimization algorithms remains a key challenge in learning theory. Recently, numerous works demonstrated the impact of the geometric properties of optimization trajectories on…

Machine Learning · Computer Science 2026-01-23 Mario Tuci , Lennart Bastian , Benjamin Dupuis , Nassir Navab , Tolga Birdal , Umut Şimşekli

Exponential generalization bounds with near-tight rates have recently been established for uniformly stable learning algorithms. The notion of uniform stability, however, is stringent in the sense that it is invariant to the data-generating…

Machine Learning · Statistics 2022-06-09 Xiao-Tong Yuan , Ping Li

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple averaging of multiple points along the trajectory of SGD,…

Machine Learning · Computer Science 2019-02-26 Pavel Izmailov , Dmitrii Podoprikhin , Timur Garipov , Dmitry Vetrov , Andrew Gordon Wilson