Back to search

Boston University

Auxiliaries for training deep neural networks

Abstract

dc:description.abstract

The generalization of deep neural networks (DNNs) remains a critical challenge in machine learning, where the goal is to ensure that models perform well on unseen test data. Regularization techniques play a pivotal role in this process by constraining the model's capacity to prevent overfitting. Methods such as dropout, data augmentation, normalization, and penalty functions introduce beneficial biases that guide the optimization process towards better generalization. Traditional regularizations are typically data-agnostic. In this dissertation, we propose leveraging data-dependent auxiliary sources for regularization, focusing on image classification across various settings including supervised learning, knowledge distillation, federated learning, meta-learning, and few-shot learning, as well as imitation learning for autonomous driving. We introduce four main types of auxiliary sources: models, gradients, features and data. Auxiliary models approximate the mean of historical predictions, providing data-dependent regularization by aligning the deployed model's output with the auxiliary model's output. This method, which we extend to knowledge distillation, demonstrates improved generalization and draws connections to applications in large language models (LLMs). Auxiliary gradients address bias in neural networks handling multiple tasks, particularly in personalized federated learning and online meta-learning. We propose algorithms that dynamically modify gradients to reduce task-specific biases, enhancing model performance across diverse users and tasks. Then, auxiliary features focus on tasks like few-shot learning and fine-grained image recognition, where specialized modeling is required to capture detailed visual characteristics. We propose Deep Object Parsing to generate auxiliary features that enhance performance in these settings. For imitation learning in autonomous driving, we introduce frameworks that utilize vast amounts of auxiliary data. The SelfD framework leverages unlabeled dash camera data through semi-supervised learning, while the AnyD framework utilizes cross-domain driving data to improve policy learning. Both frameworks demonstrate significant improvements in driving performance by efficiently using auxiliary data.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Electrical & Computer Engineering
Grantor
Boston University
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhu, Ruizhao
Advisor dc:contributor.advisor
  • Saligrama, Venkatesh
ORCID dc:identifier.orcid

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • Attribution 4.0 International
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/2144/49253

Chain of custody

source
Harvested from
Boston University
Base URL
open.bu.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Zhu, Ruizhao. Auxiliaries for training deep neural networks. doctoral thesis, Boston University, 2024. https://hdl.handle.net/2144/49253