DeepAI AI Chat
Log In Sign Up

Statistical Mechanics of High-Dimensional Inference

by   Madhu Advani, et al.
Stanford University

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 α = N/P→∞. However, these classical results are not relevant to modern high-dimensional inference problems, which instead occur at finite α. 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 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.


page 1

page 2

page 3

page 4


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

When recovering an unknown signal from noisy measurements, the computati...

Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality

Avoiding overfitting is a central challenge in machine learning, yet man...

Understanding Phase Transitions via Mutual Information and MMSE

The ability to understand and solve high-dimensional inference problems ...

Statistical physics of inference: Thresholds and algorithms

Many questions of fundamental interest in todays science can be formulat...

Statistical Problems with Planted Structures: Information-Theoretical and Computational Limits

Over the past few years, insights from computer science, statistical phy...

High-dimensional inference: a statistical mechanics perspective

Statistical inference is the science of drawing conclusions about some s...

Emergent limits of an indirect measurement from phase transitions of inference

Measurements are inseparable from inference, where the estimation of sig...