English
Related papers

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

200 papers

We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization that we add to the traditional training loss penalizes the…

Machine Learning · Statistics 2025-03-31 Michael Unser , Alexis Goujon , Stanislas Ducotterd

In this paper we study how the choice of loss functions of non-convex optimization problems affects their robustness and optimization landscape, through the study of noisy matrix sensing. In traditional regression tasks, mean squared error…

Machine Learning · Computer Science 2026-01-06 Xinyuan Song , Ziye Ma

Supervised training of deep neural nets typically relies on minimizing cross-entropy. However, in many domains, we are interested in performing well on metrics specific to the application. In this paper we propose a direct loss minimization…

Machine Learning · Computer Science 2016-06-03 Yang Song , Alexander G. Schwing , Richard S. Zemel , Raquel Urtasun

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Wei Hu , Yuping Luo

We consider recovery of low-rank matrices from noisy data by shrinkage of singular values, in which a single, univariate nonlinearity is applied to each of the empirical singular values. We adopt an asymptotic framework, in which the matrix…

Statistics Theory · Mathematics 2016-05-17 Matan Gavish , David L. Donoho

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applications. This is a potential issue because of the great amount of computational resources needed for training, and of the possible loss of…

Computation and Language · Computer Science 2022-10-31 Giovanni Bonetta , Matteo Ribero , Rossella Cancelliere

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

Deep neural networks (DNNs) have shown great success in many machine learning tasks. Their training is challenging since the loss surface of the network architecture is generally non-convex, or even non-smooth. How and under what…

Machine Learning · Computer Science 2022-02-09 Lam M. Nguyen , Trang H. Tran , Marten van Dijk

Matrix factorization is a simple and natural test-bed to investigate the implicit regularization of gradient descent. Gunasekar et al. (2017) conjectured that Gradient Flow with infinitesimal initialization converges to the solution that…

Machine Learning · Computer Science 2021-04-13 Zhiyuan Li , Yuping Luo , Kaifeng Lyu

Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Huan Wang , Can Qin , Yulun Zhang , Yun Fu

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on…

Machine Learning · Computer Science 2021-11-25 Gabin Maxime Nguegnang , Holger Rauhut , Ulrich Terstiege

Neural networks (NNs) are central to modern machine learning and achieve state-of-the-art results in many applications. However, the relationship between loss geometry and generalization is still not well understood. The local geometry of…

Machine Learning · Computer Science 2026-04-15 Yuto Omae , Kazuki Sakai , Yohei Kakimoto , Makoto Sasaki , Yusuke Sakai , Hirotaka Takahashi

We analyze the training dynamics for deep linear networks using a new metric - layer imbalance - which defines the flatness of a solution. We demonstrate that different regularization methods, such as weight decay or noise data…

Machine Learning · Computer Science 2020-07-21 Boris Ginsburg

Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem.…

Machine Learning · Computer Science 2017-08-01 Carlo Ciliberto , Dimitris Stamos , Massimiliano Pontil

We consider a deep matrix factorization model of covariance matrices trained with the Bures-Wasserstein distance. While recent works have made advances in the study of the optimization problem for overparametrized low-rank matrix…

Machine Learning · Statistics 2023-07-20 Pierre Bréchet , Katerina Papagiannouli , Jing An , Guido Montúfar

Overparameterization is central to the success of deep learning, yet the mechanisms by which it improves optimization remain incompletely understood. We analyze weight-space symmetries in neural networks and show that overparameterization…

Machine Learning · Computer Science 2026-05-11 Kusha Sareen , Mohammad Pedramfar , Sékou-Oumar Kaba , Mehran Shakerinava , Siamak Ravanbakhsh

Weight optimization of frame structures with continuous cross-section parametrization is a challenging non-convex problem that has traditionally been solved by local optimization techniques. Here, we exploit its inherent semi-algebraic…

Optimization and Control · Mathematics 2025-01-29 Marek Tyburec , Michal Kočvara , Martin Kružík

We introduce a Bayesian perspective for the structured matrix factorization problem. The proposed framework provides a probabilistic interpretation for existing geometric methods based on determinant minimization. We model input data…

Machine Learning · Computer Science 2023-02-17 Gokcan Tatli , Alper T. Erdogan

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Zheng Dang , Kwang Moo Yi , Yinlin Hu , Fei Wang , Pascal Fua , Mathieu Salzmann