English
Related papers

Related papers: Curvature-Adaptive Perturbation and Subspace Desce…

200 papers

Adaptive Moment Estimation (Adam), which combines Adaptive Learning Rate and Momentum, would be the most popular stochastic optimizer for accelerating the training of deep neural networks. However, it is empirically known that Adam often…

Machine Learning · Computer Science 2022-06-15 Zeke Xie , Xinrui Wang , Huishuai Zhang , Issei Sato , Masashi Sugiyama

In this paper, we study the problem of escaping from saddle points in smooth nonconvex optimization problems subject to a convex set $\mathcal{C}$. We propose a generic framework that yields convergence to a second-order stationary point of…

Machine Learning · Computer Science 2018-10-10 Aryan Mokhtari , Asuman Ozdaglar , Ali Jadbabaie

Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of…

Machine Learning · Computer Science 2017-03-03 Caglar Gulcehre , Jose Sotelo , Marcin Moczulski , Yoshua Bengio

Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive…

Machine Learning · Statistics 2018-10-02 Qi Deng , Yi Cheng , Guanghui Lan

In this paper, we propose a variant of Riemannian stochastic recursive gradient method that can achieve second-order convergence guarantee and escape saddle points using simple perturbation. The idea is to perturb the iterates when gradient…

Optimization and Control · Mathematics 2020-10-30 Andi Han , Junbin Gao

Loss of trainability refers to a phenomenon in continual learning where parameter updates no longer make progress on the optimization objective, so accuracy stalls or degrades as the learning problem changes over time. In this paper, we…

Machine Learning · Computer Science 2025-12-11 Gunbir Singh Baveja , Alex Lewandowski , Mark Schmidt

Modern Large Language Model (LLM) training is fundamentally bottlenecked by pathologically flat saddle points in extreme high-dimensional landscapes. Motivated by this challenge, we analyze the saddle-point escape dynamics of the emerging…

Machine Learning · Computer Science 2026-05-12 Yanlin Long , Yufei Gu , Zeke Xie

We propose novel randomized optimization methods for high-dimensional convex problems based on restrictions of variables to random subspaces. We consider oblivious and data-adaptive subspaces and study their approximation properties via…

Information Theory · Computer Science 2020-12-15 Jonathan Lacotte , Mert Pilanci

Recently, saddle point problems have received much attention due to their powerful modeling capability for a lot of problems from diverse domains. Applications of these problems occur in many applied areas, such as robust optimization,…

Optimization and Control · Mathematics 2022-02-15 Mohammad Alkousa , Alexander Gasnikov , Pavel Dvurechensky , Abdurakhmon Sadiev , Lama Razouk

Large-scale non-convex optimization problems are expensive to solve due to computational and memory costs. To reduce the costs, first-order (computationally efficient) and asynchronous-parallel (memory efficient) algorithms are necessary to…

Optimization and Control · Mathematics 2022-11-21 Marco Bornstein , Jin-Peng Liu , Jingling Li , Furong Huang

Recently, the problem of local minima in very high dimensional non-convex optimization has been challenged and the problem of saddle points has been introduced. This paper introduces a dynamic type of normalization that forces the system to…

Machine Learning · Computer Science 2017-02-08 Armen Aghajanyan

In this work, we analyze the global convergence property of coordinate gradient descent with random choice of coordinates and stepsizes for non-convex optimization problems. Under generic assumptions, we prove that the algorithm iterate…

Optimization and Control · Mathematics 2022-12-01 Ziang Chen , Yingzhou Li , Jianfeng Lu

Without randomization, escaping the saddle points of $f \colon \mathbb{R}^d \to \mathbb{R}$ requires at least $\Omega(d)$ pieces of information about $f$ (values, gradients, Hessian-vector products). With randomization, this can be reduced…

Optimization and Control · Mathematics 2026-03-17 Radu-Alexandru Dragomir , Xiaowen Jiang , Bonan Sun , Nicolas Boumal

Many high-dimensional optimisation problems exhibit rich geometric structures in their set of minimisers, often forming smooth manifolds due to over-parametrisation or symmetries. When this structure is known, at least locally, it can be…

Optimization and Control · Mathematics 2025-10-27 Evan Markou , Thalaiyasingam Ajanthan , Stephen Gould

Distributed nonconvex optimization underpins key functionalities of numerous distributed systems, ranging from power systems, smart buildings, cooperative robots, vehicle networks to sensor networks. Recently, it has also merged as a…

Optimization and Control · Mathematics 2024-03-18 Yanan Bo , Yongqiang Wang

Optimizing non-convex functions is of primary importance in the vast majority of machine learning algorithms. Even though many gradient descent based algorithms have been studied, successive convex approximation based algorithms have been…

Optimization and Control · Mathematics 2019-03-06 Amrit Singh Bedi , Ketan Rajawat , Vaneet Aggarwal

Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to…

Machine Learning · Computer Science 2017-01-17 Xi He , Dheevatsa Mudigere , Mikhail Smelyanskiy , Martin Takáč

Adaptive optimizers can reduce to normalized steepest descent (NSD) when only adapting to the current gradient, suggesting a close connection between the two algorithmic families. A key distinction between their analyses, however, lies in…

Machine Learning · Computer Science 2025-11-26 Shuo Xie , Tianhao Wang , Beining Wu , Zhiyuan Li

Stochastic gradient algorithms have been the main focus of large-scale learning problems and they led to important successes in machine learning. The convergence of SGD depends on the careful choice of learning rate and the amount of the…

Machine Learning · Computer Science 2015-11-03 Caglar Gulcehre , Marcin Moczulski , Yoshua Bengio

We consider a generic convex-concave saddle point problem with separable structure, a form that covers a wide-ranged machine learning applications. Under this problem structure, we follow the framework of primal-dual updates for saddle…

Machine Learning · Statistics 2015-06-15 Zhanxing Zhu , Amos J. Storkey