Results 1 -
3 of
3
Constrained convex minimization via model-based excessive gap
- in Proceedings of Neural Information Processing Systems Foundation (NIPS
, 2014
"... We introduce a model-based excessive gap technique to analyze first-order primal-dual methods for constrained convex minimization. As a result, we construct first-order primal-dual methods with optimal convergence rates on the primal objec-tive residual and the primal feasibility gap of their iterat ..."
Abstract
-
Cited by 3 (2 self)
- Add to MetaCart
(Show Context)
We introduce a model-based excessive gap technique to analyze first-order primal-dual methods for constrained convex minimization. As a result, we construct first-order primal-dual methods with optimal convergence rates on the primal objec-tive residual and the primal feasibility gap of their iterates separately. Through a dual smoothing and prox-center selection strategy, our framework subsumes the augmented Lagrangian, alternating direction, and dual fast-gradient methods as special cases, where our rates apply. 1
Structured Sampling and Recovery of iEEG Signals
"... Abstract—Wireless implantable devices capable of monitoring the electrical activity of the brain are becoming an important tool for understanding, and potentially treating, mental diseases such as epilepsy and depression. Compressive sensing (CS) is emerging as a promising approach to directly acqui ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Wireless implantable devices capable of monitoring the electrical activity of the brain are becoming an important tool for understanding, and potentially treating, mental diseases such as epilepsy and depression. Compressive sensing (CS) is emerging as a promising approach to directly acquire compressed signals, allowing to reduce the power consumption associated with data transmission. To this end, we propose an efficient CS scheme which exploits the structure of the intracranial EEG signals, both in sampling and recovery. Our structure-aware approach is conceptually simple to implement in hardware and yields state-of-the-art compression rates up to 32x with high reconstruction quality, as illustrated on two human iEEG datasets.
Primal-Dual Approaches for Solving Large-Scale Optimization Problems
, 2014
"... ar ..."
(Show Context)
