Stochastic Frank-Wolfe for Composite Convex Minimization
January 29, 2019 Β· Declared Dead Β· π Neural Information Processing Systems
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Francesco Locatello, Alp Yurtsever, Olivier Fercoq, Volkan Cevher
arXiv ID
1901.10348
Category
math.OC: Optimization & Control
Cross-listed
cs.AI,
cs.LG,
stat.ML
Citations
18
Venue
Neural Information Processing Systems
Last Checked
3 months ago
Abstract
A broad class of convex optimization problems can be formulated as a semidefinite program (SDP), minimization of a convex function over the positive-semidefinite cone subject to some affine constraints. The majority of classical SDP solvers are designed for the deterministic setting where problem data is readily available. In this setting, generalized conditional gradient methods (aka Frank-Wolfe-type methods) provide scalable solutions by leveraging the so-called linear minimization oracle instead of the projection onto the semidefinite cone. Most problems in machine learning and modern engineering applications, however, contain some degree of stochasticity. In this work, we propose the first conditional-gradient-type method for solving stochastic optimization problems under affine constraints. Our method guarantees $\mathcal{O}(k^{-1/3})$ convergence rate in expectation on the objective residual and $\mathcal{O}(k^{-5/12})$ on the feasibility gap.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Optimization & Control
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Local SGD Converges Fast and Communicates Little
R.I.P.
π»
Ghosted
On Lazy Training in Differentiable Programming
π
π
The Cartographer
A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications
R.I.P.
π»
Ghosted
Learned Primal-dual Reconstruction
R.I.P.
π»
Ghosted
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted