English
Related papers

Related papers: Sample Variance Decay in Randomly Initialized ReLU…

200 papers

We address the problem of estimating statistics of hidden units in a neural network using a method of analytic moment propagation. These statistics are useful for approximate whitening of the inputs in front of saturating non-linearities…

Machine Learning · Computer Science 2018-03-29 Alexander Shekhovtsov , Boris Flach

In this paper, orthogonal to the existing data and model studies, we instead resort our efforts to investigate the potential of loss function in a new perspective and present our belief ``Random Weights Networks can Be Acted as Loss Prior…

Computer Vision and Pattern Recognition · Computer Science 2023-03-30 Man Zhou , Naishan Zheng , Jie Huang , Xiangyu Rui , Chunle Guo , Deyu Meng , Chongyi Li , Jinwei Gu

Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent work has shown that…

Machine Learning · Statistics 2015-10-07 César Laurent , Gabriel Pereyra , Philémon Brakel , Ying Zhang , Yoshua Bengio

Proper weight initialization prior to training has historically been one of the key factors that helped kick off the deep learning revolution. Initialization is even more crucial in "reservoir computing", where the weights of a readout…

Machine Learning · Computer Science 2026-05-12 Tommaso Fioratti , Riccardo Marcaccioli , Francesco Casola

Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered…

Machine Learning · Computer Science 2020-06-25 Jary Pomponi , Simone Scardapane , Vincenzo Lomonaco , Aurelio Uncini

We investigate the training and generalization errors of overparameterized neural networks (NNs) with a wide class of leaky rectified linear unit (ReLU) functions. More specifically, we carefully upper bound both the convergence rate of the…

Machine Learning · Computer Science 2024-02-27 Yinglong Guo , Shaohan Li , Gilad Lerman

Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set.…

Computer Vision and Pattern Recognition · Computer Science 2020-06-29 Yunhan Zhao , Ye Tian , Charless Fowlkes , Wei Shen , Alan Yuille

\emph{Batch normalization} is a successful building block of neural network architectures. Yet, it is not well understood. A neural network layer with batch normalization comprises three components that affect the representation induced by…

Machine Learning · Computer Science 2024-12-05 Ido Nachum , Marco Bondaschi , Michael Gastpar , Anatoly Khina

Weight decay (WD) is a traditional regularization technique in deep learning, but despite its ubiquity, its behavior is still an area of active research. Golatkar et al. have recently shown that WD only matters at the start of the training…

Machine Learning · Computer Science 2020-12-29 Johan Bjorck , Kilian Weinberger , Carla Gomes

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for…

Machine Learning · Computer Science 2023-08-10 Sebastian Neumayer , Lénaïc Chizat , Michael Unser

Vanishing (and exploding) gradients effect is a common problem for recurrent neural networks with nonlinear activation functions which use backpropagation method for calculation of derivatives. Deep feedforward neural networks with many…

Neural and Evolutionary Computing · Computer Science 2017-02-15 Artem Chernodub , Dimitri Nowicki

A popular strategy to train recurrent neural networks (RNNs), known as ``teacher forcing'' takes the ground truth as input at each time step and makes the later predictions partly conditioned on those inputs. Such training strategy impairs…

Computation and Language · Computer Science 2021-03-23 Liping Yuan , Jiangtao Feng , Xiaoqing Zheng , Xuanjing Huang

While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Zhenlin Xu , Deyi Liu , Junlin Yang , Colin Raffel , Marc Niethammer

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. (2020) empirically showed that only pruning the weights can achieve remarkable performance…

Machine Learning · Computer Science 2022-04-06 Daiki Chijiwa , Shin'ya Yamaguchi , Yasutoshi Ida , Kenji Umakoshi , Tomohiro Inoue

In this work we investigate the reasons why Batch Normalization (BN) improves the generalization performance of deep networks. We argue that one major reason, distinguishing it from data-independent normalization methods, is randomness of…

Machine Learning · Computer Science 2018-11-05 Alexander Shekhovtsov , Boris Flach

Intuitively, one would expect accuracy of a trained neural network's prediction on test samples to correlate with how densely the samples are surrounded by seen training samples in representation space. We find that a bound on empirical…

Machine Learning · Computer Science 2022-07-29 Xu Ji , Razvan Pascanu , Devon Hjelm , Balaji Lakshminarayanan , Andrea Vedaldi

In past few years, various initialization schemes have been proposed. These schemes are glorot initialization, He initialization, initialization using orthogonal matrix, random walk method for initialization. Some of these methods stress on…

Machine Learning · Computer Science 2025-09-08 Vijay Pandey

Uncertainty quantification in deep learning is crucial for safe and reliable decision-making in downstream tasks. Existing methods quantify uncertainty at the last layer or other approximations of the network which may miss some sources of…

Machine Learning · Statistics 2025-04-25 James McInerney , Nathan Kallus

Randomly initialized neural networks induce a prior over functions, but the predictor used in practice is produced only after training. We ask how much of this initial bias survives the training pipeline. To make the question measurable, we…

Machine Learning · Computer Science 2026-05-29 Mohua Das , Pierfrancesco Beneventano , Shibshankar Dey , Gareth H. McKinkey , Tomaso Poggio