Corpus ID: 344476

An equivalence between high dimensional Bayes optimal inference and M-estimation

  title={An equivalence between high dimensional Bayes optimal inference and M-estimation},
  author={Madhu S. Advani and S. Ganguli},
When recovering an unknown signal from noisy measurements, the computational difficulty of performing optimal Bayesian MMSE (minimum mean squared error) inference often necessitates the use of maximum a posteriori (MAP) inference, a special case of regularized M-estimation, as a surrogate. However, MAP is suboptimal in high dimensions, when the number of unknown signal components is similar to the number of measurements. In this work we demonstrate, when the signal distribution and the… Expand
Discreteness-Aware Approximate Message Passing for Discrete-Valued Vector Reconstruction
Optimal errors and phase transitions in high-dimensional generalized linear models
Statistical mechanics of low-rank tensor decomposition
Generalization Error of Generalized Linear Models in High Dimensions
Strong replica symmetry for high-dimensional disordered log-concave Gibbs measures
High-dimensional dynamics of generalization error in neural networks
A Characterization of Proximity Operators


High dimensional robust M-estimation: asymptotic variance via approximate message passing
Precise high-dimensional error analysis of regularized M-estimators
Generalized approximate message passing for estimation with random linear mixing
  • S. Rangan
  • Computer Science, Mathematics
  • 2011 IEEE International Symposium on Information Theory Proceedings
  • 2011
Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization
Message-passing algorithms for compressed sensing
A single-letter characterization of optimal noisy compressed sensing
Random Sparse Linear Systems Observed Via Arbitrary Channels: A Decoupling Principle
  • Dongning Guo, C. Wang
  • Mathematics, Computer Science
  • 2007 IEEE International Symposium on Information Theory
  • 2007
Optimal M-estimation in high-dimensional regression