An Adaptive Memory Multi-Batch L-BFGS Algorithm for Neural Network Training

Federico Zocco*, Seán McLoone

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Motivated by the potential for parallel implementation of batch-based algorithms and the accelerated convergence achievable with approximated second order information a limited memory version of the BFGS algorithm has been receiving increasing attention in recent years for large neural network training problems. As the shape of the cost function is generally not quadratic and only becomes approximately quadratic in the vicinity of a minimum, the use
of second order information by L-BFGS can be unreliable during the initial phase of training, i.e. when far from a minimum. Therefore, to control the in
uence of second order information as training progresses, we propose a multi-batch L-BFGS algorithm, namely MB-AM, that gradually increases its trust in the curvature information by implementing a progressive storage and use of curvature data through a development-based increase (dev-increase) scheme. Using six discriminative modelling benchmark problems we show empirically that MB-AM has slightly faster convergence and, on average, achieves better solutions than the standard multi-batch L-BFGS algorithm when training MLP and CNN models.
Original languageEnglish
Title of host publication 21st IFAC World Congress: Proceedings
Number of pages6
Publication statusAccepted - 28 Apr 2020
Event21st IFAC World Congress - Berlin, Germany
Duration: 12 Jul 202017 Jul 2020
Conference number: 21st


Conference21st IFAC World Congress
Internet address

Bibliographical note

Will be available Diamond Open Access at

Fingerprint Dive into the research topics of 'An Adaptive Memory Multi-Batch L-BFGS Algorithm for Neural Network Training'. Together they form a unique fingerprint.

Cite this