English
Related papers

Related papers: Sample Variance Decay in Randomly Initialized ReLU…

200 papers

Neuron death is a complex phenomenon with implications for model trainability: the deeper the network, the lower the probability of finding a valid initialization. In this work, we derive both upper and lower bounds on the probability that…

Machine Learning · Computer Science 2021-06-14 Blaine Rister , Daniel L. Rubin

Recently, a spate of papers have provided positive theoretical results for training over-parameterized neural networks (where the network size is larger than what is needed to achieve low error). The key insight is that with sufficient…

Machine Learning · Computer Science 2022-03-01 Gilad Yehudai , Ohad Shamir

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distribution, a network is likely to learn the bias information to…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Byungju Kim , Hyunwoo Kim , Kyungsu Kim , Sungjin Kim , Junmo Kim

The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they improve generalization…

Machine Learning · Computer Science 2020-06-15 Yonatan Dukler , Quanquan Gu , Guido Montúfar

Traditional machine learning excels on static benchmarks, but the real world is dynamic and seldom as carefully curated as test sets. Practical applications may generally encounter undesired inputs, are required to deal with novel…

Machine Learning · Computer Science 2025-03-17 Roshni . R. Kamath , Rupert Mitchell , Subarnaduti Paul , Kristian Kersting , Martin Mundt

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

An emerging design principle in deep learning is that each layer of a deep artificial neural network should be able to easily express the identity transformation. This idea not only motivated various normalization techniques, such as…

Machine Learning · Computer Science 2018-07-23 Moritz Hardt , Tengyu Ma

We identify and study two common failure modes for early training in deep ReLU nets. For each we give a rigorous proof of when it occurs and how to avoid it, for fully connected and residual architectures. The first failure mode,…

Machine Learning · Statistics 2018-11-14 Boris Hanin , David Rolnick

Batch Normalization (BN) is a commonly used technique to accelerate and stabilize training of deep neural networks. Despite its empirical success, a full theoretical understanding of BN is yet to be developed. In this work, we analyze BN…

Machine Learning · Computer Science 2022-03-22 Tolga Ergen , Arda Sahiner , Batu Ozturkler , John Pauly , Morteza Mardani , Mert Pilanci

Stochastic gradient descent samples uniformly the training set to build an unbiased gradient estimate with a limited number of samples. However, at a given step of the training process, some data are more helpful than others to continue…

Machine Learning · Computer Science 2023-03-30 Thibault Lahire

For small training set sizes $P$, the generalization error of wide neural networks is well-approximated by the error of an infinite width neural network (NN), either in the kernel or mean-field/feature-learning regime. However, after a…

Machine Learning · Statistics 2022-12-26 Alexander Atanasov , Blake Bordelon , Sabarish Sainathan , Cengiz Pehlevan

A traditional approach to initialization in deep neural networks (DNNs) is to sample the network weights randomly for preserving the variance of pre-activations. On the other hand, several studies show that during the training process, the…

Machine Learning · Computer Science 2021-02-16 Mert Gurbuzbalaban , Yuanhan Hu

We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of…

Machine Learning · Computer Science 2023-11-14 Erik Lien Bolager , Iryna Burak , Chinmay Datar , Qing Sun , Felix Dietrich

Batch Normalization is a key component in almost all state-of-the-art image classifiers, but it also introduces practical challenges: it breaks the independence between training examples within a batch, can incur compute and memory…

Machine Learning · Computer Science 2021-01-28 Andrew Brock , Soham De , Samuel L. Smith

Importance sampling is widely used to improve the efficiency of deep neural network (DNN) training by reducing the variance of gradient estimators. However, efficiently assessing the variance reduction relative to uniform sampling remains…

Machine Learning · Computer Science 2025-11-19 Takuro Kutsuna

Batch normalization (BN) is comprised of a normalization component followed by an affine transformation and has become essential for training deep neural networks. Standard initialization of each BN in a network sets the affine…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Jim Davis , Logan Frank

The ability to train randomly initialised deep neural networks is known to depend strongly on the variance of the weight matrices and biases as well as the choice of nonlinear activation. Here we complement the existing geometric analysis…

Information Theory · Computer Science 2021-02-09 Jared Tanner , Giuseppe Ughi

Batch Normalization (BN) improves both convergence and generalization in training neural networks. This work understands these phenomena theoretically. We analyze BN by using a basic block of neural networks, consisting of a kernel layer, a…

Machine Learning · Computer Science 2019-04-25 Ping Luo , Xinjiang Wang , Wenqi Shao , Zhanglin Peng

Deep neural networks (DNNs) have significantly advanced machine learning, with model depth playing a central role in their successes. The dynamical system modeling approach has recently emerged as a powerful framework, offering new…

Machine Learning · Computer Science 2026-02-25 Jinshu Huang , Mingfei Sun , Chunlin Wu