R.I.P.
👻
Ghosted
Unifying mirror descent and dual averaging
October 30, 2019 · Declared Dead · 🏛 Mathematical programming
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Anatoli Juditsky, Joon Kwon, Éric Moulines
arXiv ID
1910.13742
Category
math.OC: Optimization & Control
Cross-listed
cs.LG
Citations
29
Venue
Mathematical programming
Last Checked
2 months ago
Abstract
We introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this family, we define new algorithms for constrained optimization that combines the advantages of mirror descent and dual averaging. Our preliminary simulation study shows that these new algorithms significantly outperform available methods in some situations.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Optimization & Control
R.I.P.
👻
Ghosted
Local SGD Converges Fast and Communicates Little
R.I.P.
👻
Ghosted
On Lazy Training in Differentiable Programming
R.I.P.
👻
Ghosted
A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications
R.I.P.
👻
Ghosted
Learned Primal-dual Reconstruction
R.I.P.
👻
Ghosted
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
Died the same way — 👻 Ghosted
R.I.P.
👻
Ghosted
Language Models are Few-Shot Learners
R.I.P.
👻
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
👻
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
👻
Ghosted