English
Related papers

Related papers: Gradient-free training of autoencoders for non-dif…

200 papers

Error correcting codes play a central role in digital communication, ensuring that transmitted information can be accurately reconstructed despite channel impairments. Recently, autoencoder (AE) based approaches have gained attention for…

Information Theory · Computer Science 2025-11-13 Vukan Ninkovic , Dejan Vukobratovic

Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer, from the output layer to the hidden layers. A recently…

Machine Learning · Statistics 2016-12-22 Arild Nøkland

Hessian-free (HF) optimization has been shown to effectively train deep autoencoders (Martens, 2010). In this paper, we aim to accelerate HF training of autoencoders by reducing the amount of data used in training. HF utilizes the conjugate…

Machine Learning · Computer Science 2025-04-21 Ibrahim Emirahmetoglu , David E. Stewart

Pulse shaping for coherent optical fiber communication has been an active area of research for the past decade. Most of the early schemes are based on classic Nyquist pulse shaping that was originally intended for linear channels. The best…

Information Theory · Computer Science 2022-07-14 Tim Uhlemann , Alexander Span , Sebastian Dörner , Stephan ten Brink

The unscented Kalman filter is a nonlinear estimation algorithm commonly used in navigation applications. The prediction of the mean and covariance matrix is crucial to the stable behavior of the filter. This prediction is done by…

Robotics · Computer Science 2025-12-16 Amit Levy , Itzik Klein

We propose KOALA++, a scalable Kalman-based optimization algorithm that explicitly models structured gradient uncertainty in neural network training. Unlike second-order methods, which rely on expensive second order gradient calculation,…

Machine Learning · Computer Science 2025-10-27 Zixuan Xia , Aram Davtyan , Paolo Favaro

In this work, we present a new derivative-free optimization method and investigate its use for training neural networks. Our method is motivated by the Ensemble Kalman Filter (EnKF), which has been used successfully for solving optimization…

Numerical Analysis · Mathematics 2018-06-01 Eldad Haber , Felix Lucka , Lars Ruthotto

Neural networks increasingly embed non-differentiable components (spiking neurons, quantized layers, discrete routing, blackbox simulators, etc.) where backpropagation is inapplicable and surrogate gradients introduce bias. We present…

Machine Learning · Computer Science 2026-05-05 An T. Le

A particle filtering approach is suggested for the training of multi-layer neural networks without utilizing gradients calculation. The network weights are considered to be the components of the estimated state-vector of a noise driven…

Optimization and Control · Mathematics 2020-10-13 Isaac Yaesh , Natan Grinfeld

Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in…

Machine Learning · Computer Science 2018-07-24 Zhouyuan Huo , Bin Gu , Qian Yang , Heng Huang

Backward propagation (BP) is widely used to compute the gradients in neural network training. However, it is hard to implement BP on edge devices due to the lack of hardware and software resources to support automatic differentiation. This…

Machine Learning · Computer Science 2023-10-11 Yequan Zhao , Xinling Yu , Zhixiong Chen , Ziyue Liu , Sijia Liu , Zheng Zhang

Training deep generative models like Variational Autoencoders (VAEs) requires propagating gradients through stochastic latent variables, which introduces estimation variance that can slow convergence and degrade performance. In this paper,…

Machine Learning · Computer Science 2026-02-27 Zilei Shao , Anji Liu , Guy Van den Broeck

Leveraging powerful deep learning techniques, the end-to-end (E2E) learning of communication system is able to outperform the classical communication system. Unfortunately, this communication system cannot be trained by deep learning…

Information Theory · Computer Science 2022-04-04 Hao Jiang , Shuangkaisheng Bi , Linglong Dai , Hao Wang , Jiankun Zhang

Backpropagation dominates modern machine learning, yet it is not the only principled method for optimizing dynamical systems. We propose Kalman World Models (KWM), a class of learned state-space models trained via recursive Bayesian…

Machine Learning · Computer Science 2026-03-17 Andrew Kiruluta

In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function. We propose a solution by…

Computer Vision and Pattern Recognition · Computer Science 2020-03-19 Bohan Zhuang , Lingqiao Liu , Mingkui Tan , Chunhua Shen , Ian Reid

In this paper, we propose a non-parametric method for state estimation of high-dimensional nonlinear stochastic dynamical systems, which evolve according to gradient flows with isotropic diffusion. We combine diffusion maps, a manifold…

Signal Processing · Electrical Eng. & Systems 2019-02-26 Tal Shnitzer , Ronen Talmon , Jean-Jacques Slotine

With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient…

Machine Learning · Computer Science 2016-05-09 Gavin Taylor , Ryan Burmeister , Zheng Xu , Bharat Singh , Ankit Patel , Tom Goldstein

Vendor interoperability is one of the desired future characteristics of optical networks. This means that the transmission system needs to support a variety of hardware with different components, leading to system uncertainties throughout…

Signal Processing · Electrical Eng. & Systems 2022-06-08 Ognjen Jovanovic , Metodi P. Yankov , Francesco Da Ros , Darko Zibar

While backpropagation--reverse-mode automatic differentiation--has been extraordinarily successful in deep learning, it requires two passes (forward and backward) through the neural network and the storage of intermediate activations.…

Machine Learning · Computer Science 2025-11-06 Daniel Wang , Evan Markou , Dylan Campbell

This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Felipe Torres Figueroa , Hanwei Zhang , Ronan Sicre , Yannis Avrithis , Stephane Ayache