Generalized Approximate Survey Propagation for High-Dimensional Estimation
May 13, 2019 Β· Declared Dead Β· π International Conference on Machine Learning
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Luca Saglietti, Yue M. Lu, Carlo Lucibello
arXiv ID
1905.05313
Category
cond-mat.dis-nn
Cross-listed
cond-mat.stat-mech,
cs.IT,
cs.LG
Citations
12
Venue
International Conference on Machine Learning
Last Checked
6 months ago
Abstract
In Generalized Linear Estimation (GLE) problems, we seek to estimate a signal that is observed through a linear transform followed by a component-wise, possibly nonlinear and noisy, channel. In the Bayesian optimal setting, Generalized Approximate Message Passing (GAMP) is known to achieve optimal performance for GLE. However, its performance can significantly degrade whenever there is a mismatch between the assumed and the true generative model, a situation frequently encountered in practice. In this paper, we propose a new algorithm, named Generalized Approximate Survey Propagation (GASP), for solving GLE in the presence of prior or model mis-specifications. As a prototypical example, we consider the phase retrieval problem, where we show that GASP outperforms the corresponding GAMP, reducing the reconstruction threshold and, for certain choices of its parameters, approaching Bayesian optimal performance. Furthermore, we present a set of State Evolution equations that exactly characterize the dynamics of GASP in the high-dimensional limit.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β cond-mat.dis-nn
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Mutual Information, Neural Networks and the Renormalization Group
R.I.P.
π»
Ghosted
Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic space
R.I.P.
π»
Ghosted
Classification and Geometry of General Perceptual Manifolds
R.I.P.
π»
Ghosted
The jamming transition as a paradigm to understand the loss landscape of deep neural networks
R.I.P.
π»
Ghosted
Criticality in Formal Languages and Statistical Physics
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