English
Related papers

Related papers: Stochastic Training is Not Necessary for Generaliz…

200 papers

The success of SGD in deep learning has been ascribed by prior works to the implicit bias induced by finite batch sizes ("SGD noise"). While prior works focused on offline learning (i.e., multiple-epoch training), we study the impact of SGD…

Machine Learning · Computer Science 2024-06-10 Nikhil Vyas , Depen Morwani , Rosie Zhao , Gal Kaplun , Sham Kakade , Boaz Barak

Recently, deep learning is considered to optimize the end-to-end performance of digital communication systems. The promise of learning a digital communication scheme from data is attractive, since this makes the scheme adaptable and…

Signal Processing · Electrical Eng. & Systems 2021-07-19 Simon Bos , Evgenii Vinogradov , Sofie Pollin

We take a geometrical viewpoint and present a unifying view on supervised deep learning with the Bregman divergence loss function - this entails frequent classification and prediction tasks. Motivated by simulations we suggest that there is…

Machine Learning · Computer Science 2021-07-07 Petr Taborsky , Lars Kai Hansen

In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducing the number of independent parameters, and improving…

Machine Learning · Computer Science 2024-05-30 Feng Chen , Daniel Kunin , Atsushi Yamamura , Surya Ganguli

Deep neural networks are known to be vulnerable to adversarial attacks. Current methods of defense from such attacks are based on either implicit or explicit regularization, e.g., adversarial training. Randomized smoothing, the averaging of…

Despite an extensive body of literature on deep learning optimization, our current understanding of what makes an optimization algorithm effective is fragmented. In particular, we do not understand well whether enhanced optimization…

Machine Learning · Computer Science 2024-03-04 Toki Tahmid Inan , Mingrui Liu , Amarda Shehu

Batch Normalization is a commonly used trick to improve the training of deep neural networks. These neural networks use L2 regularization, also called weight decay, ostensibly to prevent overfitting. However, we show that L2 regularization…

Machine Learning · Computer Science 2017-06-19 Twan van Laarhoven

When training deep neural networks, it is typically assumed that the training examples are uniformly difficult to learn. Or, to restate, it is assumed that the training error will be uniformly distributed across the training examples. Based…

Machine Learning · Computer Science 2015-10-09 Andrew J. R. Simpson

While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solution has certain drawbacks. For instance, BN depends on batch…

Machine Learning · Statistics 2016-06-21 Devansh Arpit , Yingbo Zhou , Hung Ngo , Venu Govindaraju

Batch normalization is currently the most widely used variant of internal normalization for deep neural networks. Additional work has shown that the normalization of weights and additional conditioning as well as the normalization of…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Wolfgang Fuhl , Enkelejda Kasneci

Several techniques have recently aimed to improve the performance of deep learning models for Scene Graph Generation (SGG) by incorporating background knowledge. State-of-the-art techniques can be divided into two families: one where the…

Machine Learning · Computer Science 2022-09-08 Davide Buffelli , Efthymia Tsamoura

Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with…

Machine Learning · Computer Science 2017-09-29 Zhenguo Li , Fengwei Zhou , Fei Chen , Hang Li

The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Martin Kolarik , Radim Burget , Kamil Riha

Motivated by the observation that humans can learn patterns from two given images at one time, we propose a dual pattern learning network architecture in this paper. Unlike conventional networks, the proposed architecture has two input…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Haimin Zhang , Min Xu

The largely successful method of training neural networks is to learn their weights using some variant of stochastic gradient descent (SGD). Here, we show that the solutions found by SGD can be further improved by ensembling a subset of the…

Generalization of neural networks is crucial for deploying them safely in the real world. Common training strategies to improve generalization involve the use of data augmentations, ensembling and model averaging. In this work, we first…

Machine Learning · Computer Science 2023-06-13 Samyak Jain , Sravanti Addepalli , Pawan Sahu , Priyam Dey , R. Venkatesh Babu

Bootstrapping is behind much of the successes of Deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to…

Analyzing neural network dynamics via stochastic gradient descent (SGD) is crucial to building theoretical foundations for deep learning. Previous work has analyzed structured inputs within the \textit{hidden manifold model}, often under…

Machine Learning · Statistics 2025-12-01 Jaeyong Bae , Hawoong Jeong

Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has asked: why do deep networks not overfit to their training data?…

Machine Learning · Computer Science 2023-03-24 Minyoung Huh , Hossein Mobahi , Richard Zhang , Brian Cheung , Pulkit Agrawal , Phillip Isola

Stochastic optimization lies at the core of most statistical learning models. The recent great development of stochastic algorithmic tools focused significantly onto proximal gradient iterations, in order to find an efficient approach for…

Machine Learning · Computer Science 2020-03-31 Andrei Patrascu , Ciprian Paduraru , Paul Irofti