English
Related papers

Related papers: Faster Rates for the Frank-Wolfe Method over Stron…

200 papers

Learning a deep neural network requires solving a challenging optimization problem: it is a high-dimensional, non-convex and non-smooth minimization problem with a large number of terms. The current practice in neural network optimization…

Machine Learning · Computer Science 2021-02-23 Leonard Berrada , Andrew Zisserman , M. Pawan Kumar

Invented some 65 years ago in a seminal paper by Marguerite Straus-Frank and Philip Wolfe, the Frank-Wolfe method recently enjoys a remarkable revival, fuelled by the need of fast and reliable first-order optimization methods in Data…

Optimization and Control · Mathematics 2021-06-21 Immanuel. M. Bomze , Francesco Rinaldi , Damiano Zeffiro

We unveil the connections between Frank Wolfe (FW) type algorithms and the momentum in Accelerated Gradient Methods (AGM). On the negative side, these connections illustrate why momentum is unlikely to be effective for FW type algorithms.…

Optimization and Control · Mathematics 2020-06-22 Bingcong Li , Mario Coutino , Georgios B. Giannakis , Geert Leus

Maximizing a DR-submodular function subject to a general convex set is an NP-hard problem arising from many applications in combinatorial optimization and machine learning. While it is highly desirable to design efficient approximation…

Data Structures and Algorithms · Computer Science 2022-03-29 Donglei Du , Zhicheng Liu , Chenchen Wu , Dachuan Xu , Yang Zhou

The Frank-Wolfe algorithm has seen a resurgence in popularity due to its ability to efficiently solve constrained optimization problems in machine learning and high-dimensional statistics. As such, there is much interest in establishing…

Machine Learning · Statistics 2022-05-19 Suhas Vijaykumar

Minimizing a function over an intersection of convex sets is an important task in optimization that is often much more challenging than minimizing it over each individual constraint set. While traditional methods such as Frank-Wolfe (FW) or…

Optimization and Control · Mathematics 2018-04-11 Gauthier Gidel , Fabian Pedregosa , Simon Lacoste-Julien

In this paper, acceleration of gradient methods for convex optimization problems with weak levels of convexity and smoothness is considered. Starting from the universal fast gradient method which was designed to be an optimal method for…

Optimization and Control · Mathematics 2022-06-10 Jongho Park

In the paper, we propose a class of accelerated stochastic gradient-free and projection-free (a.k.a., zeroth-order Frank-Wolfe) methods to solve the constrained stochastic and finite-sum nonconvex optimization. Specifically, we propose an…

Optimization and Control · Mathematics 2020-08-11 Feihu Huang , Lue Tao , Songcan Chen

In many online learning problems the computational bottleneck for gradient-based methods is the projection operation. For this reason, in many problems the most efficient algorithms are based on the Frank-Wolfe method, which replaces…

Machine Learning · Computer Science 2020-02-17 Elad Hazan , Edgar Minasyan

Owing to their low-complexity iterations, Frank-Wolfe (FW) solvers are well suited for various large-scale learning tasks. When block-separable constraints are present, randomized block FW (RB-FW) has been shown to further reduce complexity…

Optimization and Control · Mathematics 2017-11-22 Liang Zhang , Gang Wang , Daniel Romero , Georgios B. Giannakis

We consider the problem of minimizing the sum of two convex functions. One of those functions has Lipschitz-continuous gradients, and can be accessed via stochastic oracles, whereas the other is "simple". We provide a Bregman-type algorithm…

Optimization and Control · Mathematics 2024-11-26 Benjamin Dubois-Taine , Francis Bach , Quentin Berthet , Adrien Taylor

We propose a novel and efficient training method for RNNs by iteratively seeking a local minima on the loss surface within a small region, and leverage this directional vector for the update, in an outer-loop. We propose to utilize the…

Machine Learning · Computer Science 2020-10-16 Yun Yue , Ming Li , Venkatesh Saligrama , Ziming Zhang

In this paper, we provide a sub-gradient based algorithm to solve general constrained convex optimization without taking projections onto the domain set. The well studied Frank-Wolfe type algorithms also avoid projections. However, they are…

Optimization and Control · Mathematics 2023-06-16 Kamiar Asgari , Michael J. Neely

The standard assumption for proving linear convergence of first order methods for smooth convex optimization is the strong convexity of the objective function, an assumption which does not hold for many practical applications. In this…

Optimization and Control · Mathematics 2016-08-10 I. Necoara , Yu. Nesterov , F. Glineur

We study the linear convergence of Frank-Wolfe algorithms over product polytopes. We analyze two condition numbers for the product polytope, namely the \emph{pyramidal width} and the \emph{vertex-facet distance}, based on the condition…

Optimization and Control · Mathematics 2025-09-11 Gabriele Iommazzo , David Martínez-Rubio , Francisco Criado , Elias Wirth , Sebastian Pokutta

We propose a fast and scalable Polyatomic Frank-Wolfe (P-FW) algorithm for the resolution of high-dimensional LASSO regression problems. The latter improves upon traditional Frank-Wolfe methods by considering generalized greedy steps with…

Signal Processing · Electrical Eng. & Systems 2022-03-03 Adrian Jarret , Julien Fageot , Matthieu Simeoni

Coordinate descent algorithms are popular for huge-scale optimization problems due to their low cost per-iteration. Coordinate descent methods apply to problems where the constraint set is separable across coordinates. In this paper, we…

Optimization and Control · Mathematics 2023-04-28 Rahul Mazumder , Haoyue Wang

We study a class of convex-concave saddle-point problems of the form $\min_x\max_y \langle Kx,y\rangle+f_{\cal{P}}(x)-h^\ast(y)$ where $K$ is a linear operator, $f_{\cal{P}}$ is the sum of a convex function $f$ with a Lipschitz-continuous…

Optimization and Control · Mathematics 2021-06-07 Vladimir Kolmogorov , Thomas Pock

Optimal transport (OT), which provides a distance between two probability distributions by considering their spatial locations, has been applied to widely diverse applications. Computing an OT problem requires solution of linear programming…

Machine Learning · Computer Science 2021-03-11 Takumi Fukunaga , Hiroyuki Kasai

The move from hand-designed to learned optimizers in machine learning has been quite successful for gradient-based and -free optimizers. When facing a constrained problem, however, maintaining feasibility typically requires a projection…

Machine Learning · Computer Science 2018-07-31 Patrick Schramowski , Christian Bauckhage , Kristian Kersting