The Proxy Step-size Technique for Regularized Optimization on the Sphere Manifold
September 05, 2022 Β· Declared Dead Β· π IEEE Transactions on Pattern Analysis and Machine Intelligence
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Fang Bai, Adrien Bartoli
arXiv ID
2209.01812
Category
math.OC: Optimization & Control
Cross-listed
cs.RO
Citations
1
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Last Checked
4 months ago
Abstract
We give an effective solution to the regularized optimization problem $g (\boldsymbol{x}) + h (\boldsymbol{x})$, where $\boldsymbol{x}$ is constrained on the unit sphere $\Vert \boldsymbol{x} \Vert_2 = 1$. Here $g (\cdot)$ is a smooth cost with Lipschitz continuous gradient within the unit ball $\{\boldsymbol{x} : \Vert \boldsymbol{x} \Vert_2 \le 1 \}$ whereas $h (\cdot)$ is typically non-smooth but convex and absolutely homogeneous, \textit{e.g.,}~norm regularizers and their combinations. Our solution is based on the Riemannian proximal gradient, using an idea we call \textit{proxy step-size} -- a scalar variable which we prove is monotone with respect to the actual step-size within an interval. The proxy step-size exists ubiquitously for convex and absolutely homogeneous $h(\cdot)$, and decides the actual step-size and the tangent update in closed-form, thus the complete proximal gradient iteration. Based on these insights, we design a Riemannian proximal gradient method using the proxy step-size. We prove that our method converges to a critical point, guided by a line-search technique based on the $g(\cdot)$ cost only. The proposed method can be implemented in a couple of lines of code. We show its usefulness by applying nuclear norm, $\ell_1$ norm, and nuclear-spectral norm regularization to three classical computer vision problems. The improvements are consistent and backed by numerical experiments.
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