An algorithm for quadratic programming

By M. Frank, Philip Wolfe. 1956

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

Citations in the corpus

End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, methodology): “The Frank-Wolfe algorithm [11, 15] allows to minimize large convex problems over convex sets by solving a sequence of linear problems.”
Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints (2022, methodology): “Commonly used methods for solving constrained convex optimization problems [1, 11, 21] make assumptions on the properties of the objective function, constraints or feasible set.”
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets (2020, methodology): “Frank-Wolfe (FW) algorithms [Frank et al. 1956], form a class of first-order methods solving constrained optimization problems such as min x∈C f(x).”
Frank-Wolfe Splitting via Augmented Lagrangian Method (2018, neutral): “Compute γ ∈ arg min γ ∈ [0 ,γ max ] ϕ ( x + γ d ) Algorithm 2 FW (one step) : (Frank and Wolfe, 1956) (Lacoste-Julien and Jaggi, 2015), as described in Algorithm 1.”
Frank-Wolfe Algorithms for Saddle Point Problems (2016, methodology): “The Frank-Wolfe (FW) optimization algorithm (Frank and Wolfe, 1956), also known as the conditional gradient method (Demyanov and Rubinov, 1970), is a ﬁrst-order method for smooth constrained optimization over a compact set.”
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (2016, methodology): “At each iteration, the batch Frank-Wolfe algorithm (Frank & Wolfe, 1956), (Lacoste-Julien et al., 2013, Section 3) computes the following quantity, known as the linearization duality gap or Frank-Wolfe gap: g(α) := max s∈M 〈α− s,∇f(α)〉 = 〈α− s∗,∇f(α)〉.”
Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering (2015, methodology): “The Frank-Wolfe algorithm (also called conditional gradient) (Frank and Wolfe, 1956) is a simple ﬁrst-order iterative constrained optimization algorithm for optimizing smooth functions over closed bounded convex sets like M (see Dunn (1980) for its convergence analysis on general inﬁnite…”
Block-Coordinate Frank-Wolfe Optimization for Structural SVMs (2012, methodology): “We apply the known convergence results for the standard Frank-Wolfe Algorithm 1, as given e.g. in (Frank & Wolfe, 1956; Dunn & Harshbarger, 1978; Jaggi, 2013), or as given in the paragraph just after the proof of Theorem C.1: For each k ≥ 1, the iterate α(k) of Algorithm 1 (either using the…”
Weakly Supervised Action Labeling in Videos under Ordering Constraints (2014, methodology): “The Frank-Wolfe algorithm [8,17] is a classical convex optimization procedure that permits optimizing a continuously differentiable convex function over a convex compact domain only by optimizing linear functions over the domain.”
Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs (2019, methodology): “We propose a decentralized algorithm based on FrankWolfe (FW) (Frank and Wolfe, 1956; Jaggi, 2013), also known as conditional gradient descent.”
Supermasks in Superposition (2020, methodology): “This algorithms corresponds to one step of the Frank-Wolfe algorithm [7], or one-step of gradient descent followed by softmax re-normalization with the step size η approaching∞.”
Coresets via Bilevel Optimization for Continual Learning and Streaming (2020, neutral): “Note that by imposing a bound on the weights as commonly done in experimental design [18], our algorithm would be equivalent to Frank-Wolfe [22].”
Introduction to Online Convex Optimization (2016, methodology): “The conditional gradient algorithm was devised in the seminal paper by Frank and Wolfe (43).”
On the Global Linear Convergence of Frank-Wolfe Optimization Variants (2015, methodology): “The Frank-Wolfe algorithm [9] (also known as conditional gradient) is one of the earliest existing methods for constrained convex optimization, and has seen an impressive revival recently due to its nice properties compared to projected or proximal gradient methods, in particular for sparse optimiza”
Towards Practical Differentially Private Convex Optimization (2019, background): “The Frank-Wolfe algorithm [25] has also seen a resurgence lately [26], [27], [28], [29].”
Weakly-Supervised Alignment of Video with Text (2015, methodology): “This type of problem can be solved efficiently using the Frank-Wolfe algorithm [7, 11] as soon as it is possible to minimize linear forms over the convex compact domain.”
The geometry of differential privacy: the sparse and approximate cases (2012, methodology): “This is a quadratic minimization problem, and can be approximated by the simple Frank-Wolfe gradient descent algorithm [FW56].”
Automated Scalable Bayesian Inference via Hilbert Coresets (2017, methodology): “Next, taking inspiration from the large-scale optimization literature Frank and Wolfe (1956); Gu´elat and Marcotte (1986); Jaggi (2013); Lacoste-Julien and Jaggi (2015); Clarkson (2010); Reddi et al. (2016); Balasubramanian and Ghadimi (2018); Hazan and Luo (2016), we solve the convex optimization…”
Learning with Submodular Functions: A Convex Optimization Perspective (2011, methodology): “This is exactly the situation where conditional gradient algorithms are useful (they are also often referred to as “Frank-Wolfe” algorithms [70]).”