English
Related papers

Related papers: A Complete Loss Landscape Analysis of Regularized …

200 papers

A robust algorithm for non-negative matrix factorization (NMF) is presented in this paper with the purpose of dealing with large-scale data, where the separability assumption is satisfied. In particular, we modify the Linear Programming…

Machine Learning · Statistics 2014-01-10 Jason Gejie Liu , Shuchin Aeron

Training a neural network requires navigating a high-dimensional, non-convex loss surface to find parameters that minimize this loss. In many ways, it is surprising that optimizers such as stochastic gradient descent and ADAM can reliably…

Machine Learning · Computer Science 2026-02-06 Conor Rowan , Finn Murphy-Blanchard

The maximal coding rate reduction (MCR$^2$) objective for learning structured and compact deep representations is drawing increasing attention, especially after its recent usage in the derivation of fully explainable and highly effective…

Machine Learning · Computer Science 2025-11-17 Peng Wang , Huikang Liu , Druv Pai , Yaodong Yu , Zhihui Zhu , Qing Qu , Yi Ma

The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions. In this paper, we empirically investigate the loss functions of state-of-the-art networks, and how…

Machine Learning · Computer Science 2017-12-11 Daniel Jiwoong Im , Michael Tao , Kristin Branson

Lens designers routinely use optimization in their everyday practice. Local optimization algorithms lead to the nearest minimum. In this paper, a new deterministic approach for multi-extremum optimization is proposed. Optimal solutions for…

Optics · Physics 2020-03-13 Ilya Agurok

Distributed training in deep learning (DL) is common practice as data and models grow. The current practice for distributed training of deep neural networks faces the challenges of communication bottlenecks when operating at scale, and…

Machine Learning · Computer Science 2020-12-21 Shubhankar Gahlot , Junqi Yin , Mallikarjun Shankar

Mathematical optimization is a fundamental tool for decision-making in a wide range of applications. However, in many real-world scenarios, the parameters of the optimization problem are not known a priori and must be predicted from…

Machine Learning · Computer Science 2025-11-13 Senne Berden , Ali İrfan Mahmutoğulları , Dimos Tsouros , Tias Guns

We explore the local landscape of low-rank matrix recovery, focusing on reconstructing a $d_1\times d_2$ matrix $X^\star$ with rank $r$ from $m$ linear measurements, some potentially noisy. When the noise is distributed according to an…

Machine Learning · Computer Science 2025-04-07 Jianhao Ma , Salar Fattahi

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

Similarity matrix serves as a fundamental tool at the core of numerous downstream machine-learning tasks. However, missing data is inevitable and often results in an inaccurate similarity matrix. To address this issue, Similarity Matrix…

Machine Learning · Computer Science 2024-10-01 Changyi Ma , Runsheng Yu , Xiao Chen , Youzhi Zhang

We consider a setting in which an evolving surface is implicitly characterized as the zero level of a level set function. Such an implicit surface does not encode any information about the path of a single point on the evolving surface. In…

Numerical Analysis · Mathematics 2026-02-02 Tilman Aleman , Arnold Reusken

Previous theoretical work on deep learning and neural network optimization tend to focus on avoiding saddle points and local minima. However, the practical observation is that, at least in the case of the most successful Deep Convolutional…

Machine Learning · Computer Science 2017-06-23 Qianli Liao , Tomaso Poggio

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method…

Machine Learning · Computer Science 2024-05-24 Yuyan Zhou , Ye Li , Lei Feng , Sheng-Jun Huang

Convergence guarantees for optimization over bounded-rank matrices are delicate to obtain because the feasible set is a non-smooth and non-convex algebraic variety. Existing techniques include projected gradient descent, fixed-rank…

Optimization and Control · Mathematics 2024-06-21 Quentin Rebjock , Nicolas Boumal

We study implicit regularization when optimizing an underdetermined quadratic objective over a matrix $X$ with gradient descent on a factorization of $X$. We conjecture and provide empirical and theoretical evidence that with small enough…

Machine Learning · Statistics 2017-05-26 Suriya Gunasekar , Blake Woodworth , Srinadh Bhojanapalli , Behnam Neyshabur , Nathan Srebro

During the training of networks for distance metric learning, minimizers of the typical loss functions can be considered as "feasible points" satisfying a set of constraints imposed by the training data. To this end, we reformulate distance…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Oğul Can , Yeti Ziya Gürbüz , A. Aydın Alatan

Matrix factorization models have been extensively studied as a valuable test-bed for understanding the implicit biases of overparameterized models. Although both low nuclear norm and low rank regularization have been studied for these…

Machine Learning · Computer Science 2025-06-03 Zhiwei Bai , Jiajie Zhao , Yaoyu Zhang

In this paper we explore avenues for improving the reliability of dimensionality reduction methods such as Non-Negative Matrix Factorization (NMF) as interpretive exploratory data analysis tools. We first explore the difficulties of the…

Artificial Intelligence · Computer Science 2009-04-22 Nikolaos Vasiloglou , Alexander G. Gray , David V. Anderson

Supervised matrix factorization (SMF) is a classical machine learning method that simultaneously seeks feature extraction and classification tasks, which are not necessarily a priori aligned objectives. Our goal is to use SMF to learn…

Machine Learning · Statistics 2023-11-21 Joowon Lee , Hanbaek Lyu , Weixin Yao

We study the non-convex matrix factorization approach to matrix completion via Riemannian geometry. Based on an optimization formulation over a Grassmannian manifold, we characterize the landscape based on the notion of principal angles…

Optimization and Control · Mathematics 2021-02-02 Kwangjun Ahn , Felipe Suarez