Neural-Inspired Posterior Approximation (NIPA)

TL;DR

This paper introduces a biologically inspired sampling algorithm for Bayesian inference, combining model-based, model-free, and episodic memory mechanisms to improve efficiency and scalability in machine learning applications.

Contribution

It proposes a novel sampling algorithm inspired by neural systems, integrating three components to enhance Bayesian inference and uncertainty quantification in deep learning.

Findings

The algorithm improves sampling efficiency in large-scale problems.

It enhances uncertainty quantification in Bayesian deep learning.

The approach advances Bayesian methods with biological plausibility.

Abstract

Humans learn efficiently from their environment by engaging multiple interacting neural systems that support distinct yet complementary forms of control, including model-based (goal-directed) planning, model-free (habitual) responding, and episodic memory-based learning. Model-based mechanisms compute prospective action values using an internal model of the environment, supporting flexible but computationally costly planning; model-free mechanisms cache value estimates and build heuristics that enable fast, efficient habitual responding; and memory-based mechanisms allow rapid adaptation from individual experience. In this work, we aim to elucidate the computational principles underlying this biological efficiency and translate them into a sampling algorithm for scalable Bayesian inference through effective exploration of the posterior distribution. More specifically, our proposed algorithm comprises three components: a model-based module that uses the target distribution for guided but computationally slow sampling; a model-free module that uses previous samples to learn patterns in the parameter space, enabling fast, reflexive sampling without directly evaluating the expensive target distribution; and an episodic-control module that supports rapid sampling by recalling specific past events (i.e., samples). We show that this approach advances Bayesian methods and facilitates their application to large-scale statistical machine learning problems. In particular, we apply our proposed framework to Bayesian deep learning, with an emphasis on proper and principled uncertainty quantification.