R.I.P.
👻
Ghosted
SDCA without Duality, Regularization, and Individual Convexity
February 04, 2016 · Declared Dead · 🏛 International Conference on Machine Learning
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Shai Shalev-Shwartz
arXiv ID
1602.01582
Category
cs.LG: Machine Learning
Citations
106
Venue
International Conference on Machine Learning
Last Checked
3 months ago
Abstract
Stochastic Dual Coordinate Ascent is a popular method for solving regularized loss minimization for the case of convex losses. We describe variants of SDCA that do not require explicit regularization and do not rely on duality. We prove linear convergence rates even if individual loss functions are non-convex, as long as the expected loss is strongly convex.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Machine Learning
R.I.P.
👻
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
👻
Ghosted
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
R.I.P.
👻
Ghosted
Semi-Supervised Classification with Graph Convolutional Networks
R.I.P.
👻
Ghosted
Proximal Policy Optimization Algorithms
R.I.P.
👻
Ghosted
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Died the same way — 👻 Ghosted
R.I.P.
👻
Ghosted
Language Models are Few-Shot Learners
R.I.P.
👻
Ghosted
You Only Look Once: Unified, Real-Time Object Detection
R.I.P.
👻
Ghosted
A Unified Approach to Interpreting Model Predictions
R.I.P.
👻
Ghosted