English
Related papers

Related papers: Pushing Stochastic Gradient towards Second-Order M…

200 papers

A method that allows us to give a different treatment to any neuron inside feedforward neural networks is presented. The algorithm has been implemented with two very different learning methods: a standard Back-propagation (BP) procedure and…

Neural and Evolutionary Computing · Computer Science 2014-04-22 M. Konomi , G. M. Sacha

In this paper, we advocate for two stages in a neural network's decision making process. The first is the existing feed-forward inference framework where patterns in given data are sensed and associated with previously learned patterns. The…

Machine Learning · Computer Science 2022-09-20 Mohit Prabhushankar , Ghassan AlRegib

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a…

Optimization and Control · Mathematics 2023-10-26 Pierre Marion , Raphaël Berthier

Bilevel optimization is a powerful tool for many machine learning problems, such as hyperparameter optimization and meta-learning. Estimating hypergradients (also known as implicit gradients) is crucial for developing gradient-based methods…

Optimization and Control · Mathematics 2025-05-06 Youran Dong , Junfeng Yang , Wei Yao , Jin Zhang

Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during…

Machine Learning · Statistics 2018-10-23 Peter Bloem

We introduce the "NoBackTrack" algorithm to train the parameters of dynamical systems such as recurrent neural networks. This algorithm works in an online, memoryless setting, thus requiring no backpropagation through time, and is scalable,…

Neural and Evolutionary Computing · Computer Science 2015-11-24 Yann Ollivier , Corentin Tallec , Guillaume Charpiat

With the rise of big data analytics, multi-layer neural networks have surfaced as one of the most powerful machine learning methods. However, their theoretical mathematical properties are still not fully understood. Training a neural…

Machine Learning · Computer Science 2021-01-01 Victor Luo , Yazhen Wang , Glenn Fung

The backpropagation algorithm has long been the canonical training method for neural networks. Modern paradigms are implicitly optimized for it, and numerous guidelines exist to ensure its proper use. Recently, synthetic gradients methods…

Machine Learning · Statistics 2019-06-12 Julien Launay , Iacopo Poli , Florent Krzakala

We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs). Since their training already involves expensive gradient…

Machine Learning · Computer Science 2021-11-09 Guan-Horng Liu , Tianrong Chen , Evangelos A. Theodorou

Neuromorphic computing systems are set to revolutionize energy-constrained robotics by achieving orders-of-magnitude efficiency gains, while enabling native temporal processing. Spiking Neural Networks (SNNs) represent a promising…

Artificial Intelligence · Computer Science 2025-10-29 Korneel Van den Berghe , Stein Stroobants , Vijay Janapa Reddi , G. C. H. E. de Croon

The gradients used to train neural networks are typically computed using backpropagation. While an efficient way to obtain exact gradients, backpropagation is computationally expensive, hinders parallelization, and is biologically…

Machine Learning · Computer Science 2026-01-14 Katharina Flügel , Daniel Coquelin , Marie Weiel , Charlotte Debus , Achim Streit , Markus Götz

Interest in biologically inspired alternatives to backpropagation is driven by the desire to both advance connections between deep learning and neuroscience and address backpropagation's shortcomings on tasks such as online, continual…

Neural and Evolutionary Computing · Computer Science 2020-06-18 Jack Lindsey , Ashok Litwin-Kumar

This work introduces a transformation-based learner model for classification forests. The weak learner at each split node plays a crucial role in a classification tree. We propose to optimize the splitting objective by learning a linear…

Computer Vision and Pattern Recognition · Computer Science 2014-02-07 Qiang Qiu , Guillermo Sapiro

In recent years, there has been an intense debate about how learning in biological neural networks (BNNs) differs from learning in artificial neural networks. It is often argued that the updating of connections in the brain relies only on…

Neurons and Cognition · Quantitative Biology 2024-04-11 Sören Christensen , Jan Kallsen

This paper addresses design of accelerators using systolic architectures for training of neural networks using a novel gradient interleaving approach. Training the neural network involves backpropagation of error and computation of…

Signal Processing · Electrical Eng. & Systems 2023-02-27 Nanda Unnikrishnan , Keshab K. Parhi

We present a loss function for neural networks that encompasses an idea of trivial versus non-trivial predictions, such that the network jointly determines its own prediction goals and learns to satisfy them. This permits the network to…

Artificial Intelligence · Computer Science 2016-12-15 Nicholas Guttenberg , Martin Biehl , Ryota Kanai

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation,…

Recent experimental studies indicate that synaptic changes induced by neuronal activity are discrete jumps between a small number of stable states. Learning in systems with discrete synapses is known to be a computationally hard problem.…

Neurons and Cognition · Quantitative Biology 2009-11-13 Carlo Baldassi , Alfredo Braunstein , Nicolas Brunel , Riccardo Zecchina

Most stochastic gradient descent algorithms can optimize neural networks that are sub-differentiable in their parameters; however, this implies that the neural network's activation function must exhibit a degree of continuity which limits…

Neural and Evolutionary Computing · Computer Science 2021-12-16 Anastasis Kratsios , Behnoosh Zamanlooy

Training deep neural networks consumes increasing computational resource shares in many compute centers. Often, a brute force approach to obtain hyperparameter values is employed. Our goal is (1) to enhance this by enabling second-order…

Machine Learning · Computer Science 2022-08-04 Severin Reiz , Tobias Neckel , Hans-Joachim Bungartz