Back to search

Cornell University

Beyond the Black Box: Optimization within Latent Spaces

Abstract

dc:description.abstract

In the past decade, neural networks have evolved into extraordinarily powerful tools, with wide-ranging applications across many different domains. These models allow us to use immense computational power to learn low-level features and high-level abstract concepts from vast datasets. Neural networks embed data of different forms (text, image, audio, etc.) into high dimensional latent spaces that encode salient features of the data and capture complex relationships between data points. This thesis aims to probe model parameters and latent spaces—to understand not only how information is stored and processed in networks but also how the encoded knowledge can be extracted and harnessed. We leverage these insights to develop novel methods that optimize specific parameters or representations from trained models to perform various downstream tasks. We present three specific methods in this thesis. First, we introduce BERTScore, an algorithm that utilizes representations from pre-trained language models to measure the similarity between two pieces of text. BERTScore approximates a form of transport distance to match tokens in the texts. Then, we focus on an information retrieval setting, where transformers are trained end-to-end to map search queries to corresponding documents. In this setting, we introduce IncDSI, a method to add new documents to a trained retrieval system by solving a constrained convex optimization problem to obtain new document representations. Finally, we present Fixed Neural Network Steganography (FNNS), a technique for image steganography that hides information by exploiting a neural network's sensitivity to imperceptible perturbations.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Computer Science
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kishore, Varsha
Chair dc:contributor.chair
  • Weinberger, Kilian
Committee members dc:contributor.committeemember
  • Damle, Anil
  • Hariharan, Bharath

Rights

dc:rights
Statement dc:rights
  • Attribution-ShareAlike 4.0 International
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
16611770
Dc Identifier Other
ProQuest Submission ID: 14608
ProQuest Publication ID: 31489136

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Kishore, Varsha. Beyond the Black Box: Optimization within Latent Spaces. Doctor of Philosophy thesis, Cornell University, 2024. https://hdl.handle.net/1813/116490