Statistical Mechanics of High-Dimensional Inference

Abstract

To model modern large-scale datasets, we need efficient algorithms to infer a set of $P$ unknown model parameters from $N$ noisy measurements. What are fundamental limits on the accuracy of parameter inference, given finite signal-to-noise ratios, limited measurements, prior information, and computational tractability requirements? How can we combine prior information with measurements to achieve these limits? Classical statistics gives incisive answers to these questions as the measurement density $\alpha =\frac{N}{P}\to \infty$. However, these classical results are not relevant to modern high-dimensional inference problems, which instead occur at finite $\alpha$. We formulate and analyze high-dimensional inference as a problem in the statistical physics of quenched disorder. Our analysis uncovers fundamental limits on the accuracy of inference in high dimensions, and reveals that widely cherished inference algorithms like maximum likelihood (ML) and maximum-a posteriori (MAP) inference cannot achieve these limits. We further find optimal, computationally tractable algorithms that can achieve these limits. Intriguingly, in high dimensions, these optimal algorithms become computationally simpler than MAP and ML, while still outperforming them. For example, such optimal algorithms can lead to as much as a 20% reduction in the amount of data to achieve the same performance relative to MAP. Moreover, our analysis reveals simple relations between optimal high dimensional inference and low dimensional scalar Bayesian inference, insights into the nature of generalization and predictive power in high dimensions, information theoretic limits on compressed sensing, phase transitions in quadratic inference, and connections to central mathematical objects in convex optimization theory and random matrix theory.

See http://ganguli-gang.stanford.edu/pdf/HighDimInf.Supp.pdf for supplementary material

References in corpus (2)

• Probabilistic Reconstruction in Compressed Sensing: Algorithms, Phase Diagrams, and Threshold Achieving Matrices
• Phase transitions and sample complexity in Bayes-optimal matrix factorization

Cited by in corpus (11)

• Coherent Ising machines -- Quantum optics and neural network perspectives
• Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
• Contrasting random and learned features in deep Bayesian linear regression
• Approximate Survey Propagation for Statistical Inference
• A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum-${\ell }_1$-Norm Interpolated Classifiers
• Statistical mechanics of low-rank tensor decomposition
• A statistical physics approach to learning curves for the Inverse Ising problem
• Statistical mechanics of the inverse Ising problem and the optimal objective function
• Exact results on high-dimensional linear regression via statistical physics
• Generalized Approximate Survey Propagation for High-Dimensional Estimation
• Ising Model Selection Using ${\ell }_1$-Regularized Linear Regression: A Statistical Mechanics Analysis