English
Related papers

Related papers: Asymmetric Valleys: Beyond Sharp and Flat Local Mi…

200 papers

Stochastic gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order…

Machine Learning · Computer Science 2018-08-17 Robert Kleinberg , Yuanzhi Li , Yang Yuan

Generalization is one of the most important problems in deep learning (DL). In the overparameterized regime in neural networks, there exist many low-loss solutions that fit the training data equally well. The key question is which solution…

Disordered Systems and Neural Networks · Physics 2023-06-21 Ning Yang , Chao Tang , Yuhai Tu

The classical statistical learning theory implies that fitting too many parameters leads to overfitting and poor performance. That modern deep neural networks generalize well despite a large number of parameters contradicts this finding and…

Machine Learning · Statistics 2022-10-18 Masaaki Imaizumi , Johannes Schmidt-Hieber

Despite their overwhelming capacity to overfit, deep learning architectures tend to generalize relatively well to unseen data, allowing them to be deployed in practice. However, explaining why this is the case is still an open area of…

Machine Learning · Computer Science 2017-11-15 Laurent Dinh , Razvan Pascanu , Samy Bengio , Yoshua Bengio

This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape. Local extrema with low generalization error have a large proportion of…

In several experimental reports on nonconvex optimization problems in machine learning, stochastic gradient descent (SGD) was observed to prefer minimizers with flat basins in comparison to more deterministic methods, yet there is very…

Optimization and Control · Mathematics 2018-05-08 Vivak Patel

Stochastic descent methods (of the gradient and mirror varieties) have become increasingly popular in optimization. In fact, it is now widely recognized that the success of deep learning is not only due to the special deep architecture of…

Machine Learning · Computer Science 2019-01-21 Navid Azizan , Babak Hassibi

Stochastic gradient descent (SGD) is almost ubiquitously used for training non-convex optimization tasks. Recently, a hypothesis proposed by Keskar et al. [2017] that large batch methods tend to converge to sharp minimizers has received…

Machine Learning · Statistics 2018-12-04 Xiaowu Dai , Yuhua Zhu

Understanding the generalization behavior of learning algorithms is a central goal of learning theory. A recently emerging explanation is that learning algorithms are successful in practice because they converge to flat minima, which have…

Machine Learning · Computer Science 2026-05-26 Matan Schliserman , Shira Vansover-Hager , Tomer Koren

Multi-layer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires to optimize a non-convex high-dimensional…

Machine Learning · Statistics 2022-06-08 Song Mei , Andrea Montanari , Phan-Minh Nguyen

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing…

Machine Learning · Computer Science 2021-11-30 Pan Zhou , Jiashi Feng , Chao Ma , Caiming Xiong , Steven Hoi , Weinan E

Exploring the loss landscape offers insights into the inherent principles of deep neural networks (DNNs). Recent work suggests an additional asymmetry of the valley beyond the flat and sharp ones, yet without thoroughly examining its causes…

Machine Learning · Computer Science 2024-10-10 Xin-Chun Li , Jin-Lin Tang , Bo Zhang , Lan Li , De-Chuan Zhan

Despite the tremendous success of Stochastic Gradient Descent (SGD) algorithm in deep learning, little is known about how SGD finds generalizable solutions in the high-dimensional weight space. By analyzing the learning dynamics and loss…

Data Analysis, Statistics and Probability · Physics 2020-01-07 Yu Feng , Yuhai Tu

By using the viewpoint of modern computational algebraic geometry, we explore properties of the optimization landscapes of the deep linear neural network models. After clarifying on the various definitions of "flat" minima, we show that the…

Machine Learning · Statistics 2018-10-19 Dhagash Mehta , Tianran Chen , Tingting Tang , Jonathan D. Hauenstein

Stochastic gradient descent (SGD), a widely used algorithm in deep-learning neural networks has attracted continuing studies for the theoretical principles behind its success. A recent work reports an anomaly (inverse) relation between the…

Adaptation and Self-Organizing Systems · Physics 2023-08-16 Xia Xiong , Yong-Cong Chen , Chunxiao Shi , Ping Ao

Previous works on stochastic gradient descent (SGD) often focus on its success. In this work, we construct worst-case optimization problems illustrating that, when not in the regimes that the previous works often assume, SGD can exhibit…

Machine Learning · Computer Science 2023-05-30 Liu Ziyin , Botao Li , James B. Simon , Masahito Ueda

The intuition that local flatness of the loss landscape is correlated with better generalization for deep neural networks (DNNs) has been explored for decades, spawning many different flatness measures. Recently, this link with…

Machine Learning · Computer Science 2021-06-22 Shuofeng Zhang , Isaac Reid , Guillermo Valle Pérez , Ard Louis

Recently, flat-minima optimizers, which seek to find parameters in low-loss neighborhoods, have been shown to improve a neural network's generalization performance over stochastic and adaptive gradient-based optimizers. Two methods have…

Machine Learning · Computer Science 2023-01-30 Jean Kaddour , Linqing Liu , Ricardo Silva , Matt J. Kusner

Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys. Yet, little is known about the theoretical origin of such valleys. We present a general framework for…

Machine Learning · Computer Science 2023-03-24 Bo Zhao , Iordan Ganev , Robin Walters , Rose Yu , Nima Dehmamy

The volume hypothesis suggests deep learning is effective because it is likely to find flat minima due to their large volumes, and flat minima generalize well. This picture does not explain the role of large datasets in generalization.…

Machine Learning · Computer Science 2025-11-10 Raymond Fan , Bryce Sandlund , Lin Myat Ko
‹ Prev 1 2 3 10 Next ›