# A theoretical and empirical study of new adaptive algorithms with additional momentum steps and shifted updates for stochastic non-convex optimization

arXiv: https://arxiv.org/abs/2110.08531 · HTML: https://mlsanity.com/paper/2110.08531/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 16 Oct 2021.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients](https://mlsanity.com/paper/2010.07468/) (2020)
- [AdaGrad stepsizes: Sharp convergence over nonconvex landscapes](https://mlsanity.com/paper/1806.01811/) (2018)
- [On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization](https://mlsanity.com/paper/1808.02941/) (2018)
- [A Simple Convergence Proof of Adam and Adagrad](https://mlsanity.com/paper/2003.02395/) (2020)
- [A Sufficient Condition for Convergences of Adam and RMSProp](https://mlsanity.com/paper/1811.09358/) (2018)
- [On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization](https://mlsanity.com/paper/1808.05671/) (2018)
- [Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks](https://mlsanity.com/paper/1806.06763/) (2018)
- [Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming](https://mlsanity.com/paper/1310.3787/) (2013)
- [Global convergence of the Heavy-ball method for convex optimization](https://mlsanity.com/paper/1412.7457/) (2014)
- [A High Probability Analysis of Adaptive SGD with Momentum](https://mlsanity.com/paper/2007.14294/) (2020)
- [A Unified Analysis of Stochastic Momentum Methods for Deep Learning](https://mlsanity.com/paper/1808.10396/) (2018)
- [Convergence and Dynamical Behavior of the ADAM Algorithm for Non-Convex Stochastic Optimization](https://mlsanity.com/paper/1810.02263/) (2018)
- [Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization](https://mlsanity.com/paper/1607.01231/) (2016)
- [iPiano: Inertial Proximal Algorithm for Non-Convex Optimization](https://mlsanity.com/paper/1404.4805/) (2014)
- [A general system of differential equations to model first order adaptive algorithms](https://mlsanity.com/paper/1810.13108/) (2018)
- [Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization](https://mlsanity.com/paper/2101.11075/) (2021)
- [Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization](https://mlsanity.com/paper/2009.13586/) (2020)
- [Asymptotic study of stochastic adaptive algorithm in non-convex landscape](https://mlsanity.com/paper/2012.05640/) (2020)
- [On the Curved Geometry of Accelerated Optimization](https://mlsanity.com/paper/1812.04634/) (2018)
- [An extension of the second order dynamical system that models Nesterov's convex gradient method](https://mlsanity.com/paper/1908.02574/) (2019)

## Abstract (arXiv)

It is known that adaptive optimization algorithms represent the key pillar behind the rise of the Machine Learning field. In the Optimization literature numerous studies have been devoted to accelerated gradient methods but only recently adaptive iterative techniques were analyzed from a theoretical point of view. In the present paper we introduce new adaptive algorithms endowed with momentum terms for stochastic non-convex optimization problems. Our purpose is to show a deep connection between accelerated methods endowed with different inertial steps and AMSGrad-type momentum methods. Our methodology is based on the framework of stochastic and possibly non-convex objective mappings, along with some assumptions that are often used in the investigation of adaptive algorithms. In addition to discussing the finite-time horizon analysis in relation to a certain final iteration and the almost sure convergence to stationary points, we shall also look at the worst-case iteration complexity. This will be followed by an estimate for the expectation of the squared Euclidean norm of the gradient. Various computational simulations for the training of neural networks are being used to support the theoretical analysis. For future research we emphasize that there are multiple possible extensions to our work, from which we mention the investigation regarding non-smooth objective functions and the theoretical analysis of a more general formulation that encompass our adaptive optimizers in a stochastic framework.