English
Related papers

Related papers: How to trap a gradient flow

200 papers

Stochastic gradient descent (SGD) is a simple and popular method to solve stochastic optimization problems which arise in machine learning. For strongly convex problems, its convergence rate was known to be O(\log(T)/T), by running SGD for…

Machine Learning · Computer Science 2015-03-19 Alexander Rakhlin , Ohad Shamir , Karthik Sridharan

It has been established that when the gradient coding problem is distributed among $n$ servers, the computation load (number of stored data partitions) of each worker is at least $s+1$ in order to resists $s$ stragglers. This scheme incurs…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-01-25 Sinong Wang , Jiashang Liu , Ness Shroff

The analysis of gradient descent-type methods typically relies on the Lipschitz continuity of the objective gradient. This generally requires an expensive hyperparameter tuning process to appropriately calibrate a stepsize for a given…

Optimization and Control · Mathematics 2023-11-16 Albert S. Berahas , Lindon Roberts , Fred Roosta

The gradient descent method aims at finding local minima of a given multivariate function by moving along the direction of its gradient, and hence, the algorithm typically involves computing all partial derivatives of a given function,…

Quantum Physics · Physics 2025-02-25 Nhat A. Nghiem

We consider the minimization of non-convex quadratic forms regularized by a cubic term, which exhibit multiple saddle points and poor local minima. Nonetheless, we prove that, under mild assumptions, gradient descent approximates the…

Optimization and Control · Mathematics 2022-08-31 Yair Carmon , John C. Duchi

This paper focuses on minimizing a smooth function combined with a nonsmooth regularization term on a compact Riemannian submanifold embedded in the Euclidean space under a decentralized setting. Typically, there are two types of approaches…

Optimization and Control · Mathematics 2025-07-16 Lei Wang , Le Bao , Xin Liu

The behavior of the gradient descent (GD) algorithm is analyzed for a deep neural network model with skip-connections. It is proved that in the over-parametrized regime, for a suitable initialization, with high probability GD can find a…

Machine Learning · Computer Science 2019-04-16 Weinan E , Chao Ma , Qingcan Wang , Lei Wu

We study the use of gradient descent with backtracking line search (GD-BLS) to solve the noisy optimization problem $\theta_\star:=\mathrm{argmin}_{\theta\in\mathbb{R}^d} \mathbb{E}[f(\theta,Z)]$, imposing that the function…

Optimization and Control · Mathematics 2025-04-02 Feifei Hu , Mathieu Gerber

We derive bounds on the path length $\zeta$ of gradient descent (GD) and gradient flow (GF) curves for various classes of smooth convex and nonconvex functions. Among other results, we prove that: (a) if the iterates are linearly convergent…

Machine Learning · Computer Science 2021-07-20 Chirag Gupta , Sivaraman Balakrishnan , Aaditya Ramdas

We consider non-differentiable dynamic optimization problems such as those arising in robotics and subspace tracking. Given the computational constraints and the time-varying nature of the problem, a low-complexity algorithm is desirable,…

Optimization and Control · Mathematics 2019-02-20 Rishabh Dixit , Amrit Singh Bedi , Ruchi Tripathi , Ketan Rajawat

It is well-known that given a smooth, bounded-from-below, and possibly nonconvex function, standard gradient-based methods can find $\epsilon$-stationary points (with gradient norm less than $\epsilon$) in $\mathcal{O}(1/\epsilon^2)$…

Optimization and Control · Mathematics 2022-10-28 Guy Kornowski , Ohad Shamir

We consider the problem of finding an approximate second-order stationary point of a constrained non-convex optimization problem. We first show that, unlike the gradient descent method for unconstrained optimization, the vanilla projected…

Optimization and Control · Mathematics 2020-06-04 Maher Nouiehed , Jason D. Lee , Meisam Razaviyayn

We develop a fast and scalable numerical approach to solve Wasserstein gradient flows (WGFs), particularly suitable for high-dimensional cases. Our approach is to use general reduced-order models, like deep neural networks, to parameterize…

Numerical Analysis · Mathematics 2024-05-24 Yijie Jin , Shu Liu , Hao Wu , Xiaojing Ye , Haomin Zhou

The symmetric low-rank matrix factorization serves as a building block in many learning tasks, including matrix recovery and training of neural networks. However, despite a flurry of recent research, the dynamics of its training via…

Machine Learning · Computer Science 2024-11-26 Hesameddin Mohammadi , Mohammad Tinati , Stephen Tu , Mahdi Soltanolkotabi , Mihailo R. Jovanović

We characterize the query complexity of finding stationary points of one-dimensional non-convex but smooth functions. We consider four settings, based on whether the algorithms under consideration are deterministic or randomized, and…

Optimization and Control · Mathematics 2023-03-21 Sinho Chewi , Sébastien Bubeck , Adil Salim

The problem of space-efficient depth-first search (DFS) is reconsidered. A particularly simple and fast algorithm is presented that, on a directed or undirected input graph $G=(V,E)$ with $n$ vertices and $m$ edges, carries out a DFS in…

Data Structures and Algorithms · Computer Science 2018-05-31 Torben Hagerup

We study the iteration complexity of the optimistic gradient descent-ascent (OGDA) method and the extra-gradient (EG) method for finding a saddle point of a convex-concave unconstrained min-max problem. To do so, we first show that both…

Optimization and Control · Mathematics 2020-09-30 Aryan Mokhtari , Asuman Ozdaglar , Sarath Pattathil

The defining equation $(\ast):\ \dot \omega\_t=-F'(\omega\_t),$ of a gradient flow is kinetic in essence. This article explores some dynamical (rather than kinetic) features of gradient flows (i) by embedding equation $(\ast)$ into the…

Probability · Mathematics 2018-06-11 Ivan Gentil , Christian Léonard , Luigia Ripani

We consider the fundamental problem in non-convex optimization of efficiently reaching a stationary point. In contrast to the convex case, in the long history of this basic problem, the only known theoretical results on first-order…

Optimization and Control · Mathematics 2016-08-26 Zeyuan Allen-Zhu , Elad Hazan

Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad…

Machine Learning · Computer Science 2021-05-18 Xingyi Yang