Provably reliable machine learning systems

Ugare, Shubham

Permalink

https://hdl.handle.net/2142/132528 Copy

Description

Title

Provably reliable machine learning systems

Author(s)

Ugare, Shubham

Issue Date

2025-11-30

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

Singh, Gagandeep

Doctoral Committee Chair(s)

Misailovic, Sasa

Committee Member(s)

• Zhang, Lingming
• Chaudhuri, Swarat

Department of Study

Siebel School Comp & Data Sci

Discipline

Computer Science

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

Machine Learning, Formal Methods

Abstract

Machine learning systems, which primarily use deep neural networks (DNNs), serve as critical components in safety-critical applications and compound AI systems. Despite their ubiquity, automated formal reasoning about their reliability has lagged significantly. Neural network verification is NP-hard, requiring expensive end-to-end recomputation whenever networks are modified during iterative deployment cycles. Simultaneously, Large Language Models (LLMs) in compound systems frequently generate outputs that violate syntactic and semantic specifications, leading to cascading failures in automated workflows. Thus, developing reliability techniques for machine learning systems that are simultaneously general, precise, and scalable remains a challenging task. To address these challenges, this dissertation develops a comprehensive framework for provably reliable machine learning systems by establishing incremental verification techniques for DNNs and constrained decoding methods specific to LLMs.

Graduation Semester

2025-12

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/132528

Copyright and License Information

Copyright 2025 Shubham Ugare

Owning Collections