English
Related papers

Related papers: On the Loss Landscape Geometry of Regularized Deep…

200 papers

Determining the optimal depth of a neural network is a fundamental yet challenging problem, typically resolved through resource-intensive experimentation. This paper introduces a formal theoretical framework to address this question by…

Machine Learning · Computer Science 2025-06-23 Qian Qi

We develop regularization methods to find flat minima while training deep neural networks. These minima generalize better than sharp minima, yielding models outperforming baselines on real-world test data (which may be distributed…

Machine Learning · Computer Science 2025-07-04 Adam Sandler , Diego Klabjan , Yuan Luo

We prove that the empirical risk of most well-known loss functions factors into a linear term aggregating all labels with a term that is label free, and can further be expressed by sums of the loss. This holds true even for non-smooth,…

Machine Learning · Computer Science 2016-02-11 Giorgio Patrini , Frank Nielsen , Richard Nock , Marcello Carioni

We present a computational method for empirically characterizing the training loss level-sets of deep neural networks. Our method numerically constructs a path in parameter space that is constrained to a set with a fixed near-zero training…

Machine Learning · Computer Science 2021-04-27 Naveed Tahir , Garrett E. Katz

The hierarchical matrix framework partitions matrices into subblocks that are either small or of low numerical rank, enabling linear storage complexity and efficient matrix-vector multiplication. This work focuses on the $H^2$-matrix format…

Numerical Analysis · Mathematics 2026-02-02 Anna Yesypenko , Per-Gunnar Martinsson

Overparametrization is a key factor in the absence of convexity to explain global convergence of gradient descent (GD) for neural networks. Beside the well studied lazy regime, infinite width (mean field) analysis has been developed for…

Neural and Evolutionary Computing · Computer Science 2023-02-07 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

The $\chi^2$-principle generalizes the Morozov discrepancy principle (MDP) to the augmented residual of the Tikhonov regularized least squares problem. Weighting of the data fidelity by a known Gaussian noise distribution on the measured…

Numerical Analysis · Mathematics 2022-08-16 Saeed Vatankhah , Rosemary A Renaut , Vahid E Ardestani

We consider the matrix completion problem under a form of row/column weighted entrywise sampling, including the case of uniform entrywise sampling as a special case. We analyze the associated random observation operator, and prove that with…

Information Theory · Computer Science 2011-05-17 Sahand Negahban , Martin J. Wainwright

Understanding the relation between deep and shallow neural networks is extremely important for the theoretical study of deep learning. In this work, we discover an embedding principle in depth that loss landscape of an NN "contains" all…

Machine Learning · Computer Science 2025-04-15 Zhiwei Bai , Tao Luo , Zhi-Qin John Xu , Yaoyu Zhang

Despite widespread adoption in practice, guarantees for the LASSO and Group LASSO are strikingly lacking in settings beyond statistical problems, and these algorithms are usually considered to be a heuristic in the context of sparse convex…

Machine Learning · Computer Science 2023-07-17 Kyriakos Axiotis , Taisuke Yasuda

Local loss-landscape stabilization under sample growth is typically measured either pointwise or through isotropic averaging in the full parameter space. Despite practical value, both choices probe directions that contribute little to the…

Machine Learning · Computer Science 2026-04-17 Nikita Kiselev , Andrey Grabovoy

Weight decay is a widely used technique for training Deep Neural Networks(DNN). It greatly affects generalization performance but the underlying mechanisms are not fully understood. Recent works show that for layers followed by…

Machine Learning · Computer Science 2021-03-30 Yucong Zhou , Yunxiao Sun , Zhao Zhong

In this paper, we develop a novel regularization method for deep neural networks by penalizing the trace of Hessian. This regularizer is motivated by a recent guarantee bound of the generalization error. We explain its benefits in finding…

Machine Learning · Computer Science 2023-02-23 Yucong Liu , Shixing Yu , Tong Lin

We study the matrix denoising problem of estimating the singular vectors of a rank-$1$ signal corrupted by noise with both column and row correlations. Existing works are either unable to pinpoint the exact asymptotic estimation error or,…

Statistics Theory · Mathematics 2024-10-29 Yihan Zhang , Marco Mondelli

Due to the success of deep learning to solving a variety of challenging machine learning tasks, there is a rising interest in understanding loss functions for training neural networks from a theoretical aspect. Particularly, the properties…

Machine Learning · Statistics 2017-11-01 Yi Zhou , Yingbin Liang

We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical…

Machine Learning · Statistics 2018-12-06 Timothy E. Wang , Yiming Gu , Dhagash Mehta , Xiaojun Zhao , Edgar A. Bernal

We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backward pass is performed…

Computer Vision and Pattern Recognition · Computer Science 2020-05-26 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

We analyze the convergence rate of gradient flows on objective functions induced by Dropout and Dropconnect, when applying them to shallow linear Neural Networks (NNs) - which can also be viewed as doing matrix factorization using a…

Machine Learning · Computer Science 2020-12-04 Albert Senen-Cerda , Jaron Sanders

In this paper, we study equality-type Clarke subdifferential chain rules of matrix factorization and factorization machine. Specifically, we show for these problems that provided the latent dimension is larger than some multiple of the…

Optimization and Control · Mathematics 2024-10-08 Jiewen Guan , Anthony Man-Cho So

The critical locus of the loss function of a neural network is determined by the geometry of the functional space and by the parameterization of this space by the network's weights. We introduce a natural distinction between pure critical…

Machine Learning · Computer Science 2020-04-06 Matthew Trager , Kathlén Kohn , Joan Bruna