On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “ML-VAMP”

Inference with Deep Generative Priors in High Dimensionscs.LG

Paper presents ML-VAMP for efficient multi-layer inference with exact performance analysis.

problem Inference in multi-layer deep neural networks with non-convex optimization.

method ML-VAMP algorithm for MAP and MMSE estimates, with performance predictions in high dimensions.

result ML-VAMP achieves Bayes-optimal MSE under certain conditions, providing exact performance characterization.

Deep learning Inference Multi-layer networks Optimization Message passing

2019-11-08abs ↗pdf ↗

Inference in Deep Networks in High Dimensionscs.LG

Paper presents a new method for inference in deep networks, achieving precise performance guarantees in high dimensions.

problem Inference in deep networks with known parameters, especially in high dimensions.

method Multi-Layer Vector Approximate Message Passing (ML-VAMP) derived from expectation propagation.

result Exact prediction of mean-squared error (MSE) in a large system limit (LSL) for deep networks.

deep networks inference high dimensions output-to-input ML-VAMP

2017-06-20abs ↗pdf ↗

Asymptotics of MAP Inference in Deep Networkscs.IT

New method provides exact performance guarantees for MAP inference in deep networks.

problem Analyzing MAP inference in deep networks with complex data.

method Multi-layer vector approximate message passing (ML-VAMP) method.

result Mean squared error of ML-VAMP estimate can be exactly characterized in high-dimensional random limit.

MAP inference deep networks message passing error analysis high-dimensional limit

2019-03-01abs ↗pdf ↗

Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Modelsstat.ML

New AMP algorithms improve multi-layer signal reconstruction.

problem Reconstructing signals and hidden variables from multi-layer networks with rotationally invariant weights.

method Developed multi-layer rotationally invariant generalized AMP (ML-RI-GAMP) algorithms and state evolution recursion.

result ML-RI-GAMP outperforms existing methods in terms of lower complexity and similar performance.

AMP algorithms multi-layer networks rotationally invariant state evolution signal reconstruction

2022-12-03abs ↗pdf ↗

Inference in Multi-Layer Networks with Matrix-Valued Unknownscs.LG

Algorithm predicts performance of learning in multi-layer networks with matrix-valued hidden variables.

problem Signal recovery and learning in multi-layer neural networks with matrix-valued hidden variables.

method Unified approximation algorithm for MAP and MMSE inference, extending ML-VAMP to handle matrix-valued unknowns.

result Performance of ML-Mat-VAMP algorithm can be predicted in a random large-system limit.

multi-layer networks matrix-valued unknowns signal recovery stochastic neural networks approximate message passing

2020-01-26abs ↗pdf ↗