English
Related papers

Related papers: Entropic gradient descent algorithms and wide flat…

200 papers

We study the population loss landscape of two-layer ReLU networks of the form $\sum_{k=1}^K \mathrm{ReLU}(w_k^\top x)$ in a realisable teacher-student setting with Gaussian covariates. We show that local minima admit an exact…

Machine Learning · Statistics 2026-04-13 Jie Huang , Bruno Loureiro , Stefano Sarao Mannelli

Classical analyses of gradient descent (GD) define a stability threshold based on the largest eigenvalue of the loss Hessian, often termed sharpness. When the learning rate lies below this threshold, training is stable and the loss…

Machine Learning · Computer Science 2025-11-18 Lawrence Wang , Stephen J. Roberts

Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We…

Machine Learning · Statistics 2018-05-23 Ashia C. Wilson , Rebecca Roelofs , Mitchell Stern , Nathan Srebro , Benjamin Recht

Bayesian Neural Networks (BNNs) provide a probabilistic interpretation for deep learning models by imposing a prior distribution over model parameters and inferring a posterior distribution based on observed data. The model sampled from the…

Machine Learning · Computer Science 2023-11-15 Van-Anh Nguyen , Tung-Long Vuong , Hoang Phan , Thanh-Toan Do , Dinh Phung , Trung Le

Using gradient descent (GD) with fixed or decaying step-size is a standard practice in unconstrained optimization problems. However, when the loss function is only locally convex, such a step-size schedule artificially slows GD down as it…

Machine Learning · Statistics 2023-02-03 Nhat Ho , Tongzheng Ren , Sujay Sanghavi , Purnamrita Sarkar , Rachel Ward

Traditional landscape analysis of deep neural networks aims to show that no sub-optimal local minima exist in some appropriate sense. From this, one may be tempted to conclude that descent algorithms which escape saddle points will reach a…

Machine Learning · Computer Science 2020-01-01 Shiyu Liang , Ruoyu Sun , R. Srikant

In this paper we model the loss function of high-dimensional optimization problems by a Gaussian random field, or equivalently a Gaussian process. Our aim is to study gradient descent in such loss functions or energy landscapes and compare…

Machine Learning · Statistics 2018-03-28 Mariano Chouza , Stephen Roberts , Stefan Zohren

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

The remarkable generalization ability of neural networks is usually attributed to the implicit bias of SGD, which often yields models with lower complexity using simpler (e.g. linear) and low-rank features. Recent works have provided…

Machine Learning · Computer Science 2024-10-23 Khashayar Gatmiry , Zhiyuan Li , Sashank J. Reddi , Stefanie Jegelka

Large-scale distributed optimization is of great importance in various applications. For data-parallel based distributed learning, the inter-node gradient communication often becomes the performance bottleneck. In this paper, we propose the…

Computer Vision and Pattern Recognition · Computer Science 2018-06-22 Jiaxiang Wu , Weidong Huang , Junzhou Huang , Tong Zhang

In this paper, we propose a novel optimization algorithm for training machine learning models called Input Normalized Stochastic Gradient Descent (INSGD), inspired by the Normalized Least Mean Squares (NLMS) algorithm used in adaptive…

Machine Learning · Computer Science 2023-06-28 Salih Atici , Hongyi Pan , Ahmet Enis Cetin

The elusive nature of gradient-based optimization in neural networks is tied to their loss landscape geometry, which is poorly understood. However recent work has brought solid evidence that there is essentially no loss barrier between the…

Machine Learning · Statistics 2023-10-17 Simone Rossi , Ankit Singh , Thomas Hannagan

Gradient descent algorithm is the most utilized method when optimizing machine learning issues. However, there exists many local minimums and saddle points in the loss function, especially for high dimensional non-convex optimization…

Machine Learning · Computer Science 2021-07-19 Zhicheng Cai

Modern supervised learning techniques, particularly those using deep nets, involve fitting high dimensional labelled data sets with functions containing very large numbers of parameters. Much of this work is empirical. Interesting phenomena…

Machine Learning · Statistics 2018-05-30 Partha P Mitra

Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to…

Machine Learning · Computer Science 2017-01-17 Xi He , Dheevatsa Mudigere , Mikhail Smelyanskiy , Martin Takáč

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in…

Multiagent Systems · Computer Science 2020-04-01 Stefan Vlaski , Ali H. Sayed

Implicit deep learning has recently become popular in the machine learning community since these implicit models can achieve competitive performance with state-of-the-art deep networks while using significantly less memory and computational…

Machine Learning · Computer Science 2022-05-17 Tianxiang Gao , Hongyang Gao

Due to the highly non-convex nature of large-scale robust parameter estimation, avoiding poor local minima is challenging in real-world applications where input data is contaminated by a large or unknown fraction of outliers. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Huu Le , Christopher Zach

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

We study a distributed consensus-based stochastic gradient descent (SGD) algorithm and show that the rate of convergence involves the spectral properties of two matrices: the standard spectral gap of a weight matrix from the network…

Optimization and Control · Mathematics 2016-09-02 Avleen S. Bijral , Anand D. Sarwate , Nathan Srebro