Deep models, lighter footprint compressing, explaining, and transferring Bayesian neural networks

Saha, Diptarka

Permalink

https://hdl.handle.net/2142/129468 Copy

Description

Title

Deep models, lighter footprint compressing, explaining, and transferring Bayesian neural networks

Author(s)

Saha, Diptarka

Issue Date

2025-05-01

Director of Research (if dissertation) or Advisor (if thesis)

Liang, Feng

Doctoral Committee Chair(s)

Liang, Feng

Committee Member(s)

• Wang, Yuexi
• Wang, Shulei
• Chen, Yuguo

Department of Study

Statistics

Discipline

Statistics

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• Bayesian Neural Networks
• Model Compression
• Feature Selection
• Variational Inference
• Transfer Learning

Abstract

Despite their widespread adoption and impressive empirical performance, modern neural networks often suffer from overparameterization, limited interpretability, and difficulty in knowledge transfer. These limitations hinder their deployment in settings where computational efficiency, transparency, and adaptability are essential. This thesis addresses these challenges through a unifying principle: building \textit{Bayesian deep learning models with a lighter footprint}—models that retain predictive power while being more compact, interpretable, and transferable. The first contribution presents a structured compression framework for Bayesian neural networks (BNNs), where model sparsity is achieved by placing spike-and-slab priors over weights and inferring posterior inclusion probabilities. A scalable variational inference algorithm is developed that simultaneously learns network weights and their relevance, enabling principled pruning at multiple levels of granularity. The second contribution proposes a sensitivity-based feature selection method, \texttt{SENS}, which quantifies the relevance of input features by analyzing the distribution of local sensitivities under the BNN posterior. This method provides statistically grounded feature importance scores along with confidence measures, allowing for robust interpretability and data-driven selection of relevant inputs. The third contribution introduces a semi-supervised, source-free transfer learning approach using power priors. By generating pseudo-labeled auxiliary data from a black-box model and combining it with a small labeled target set, we derive a principled posterior update that enables adaptive transfer without requiring source data or access to pretrained model internals. Each of these contributions is grounded in Bayesian methodology, equipped with theoretical guarantees, and empirically validated across a wide range of synthetic and real-world datasets. Taken together, they demonstrate that deep models need not be large, opaque, or rigid. Instead, through principled Bayesian design, we can construct neural networks that are efficient, interpretable, and resilient—qualities that are increasingly critical as machine learning systems are deployed in high-stakes, resource-constrained, or regulatory-sensitive environments.

Graduation Semester

2025-05

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/129468

Copyright and License Information

Copyright 2025 Diptarka Saha

Owning Collections