Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 121 for “"Robust learning"”.
-
Robust Learning under Distributional Shifts
Designing robust models is critical for reliable deployment of artificial intelligence systems. Deep neural networks perform exceptionally well on test samples that are drawn from the same distribution as the training set. However, they perform poorly when there is a mismatch between training and …
-
Robust Learning in High Dimension
This thesis focuses on designing efficient and robust algorithms for learning high-dimensional distributions, particularly in the presence of adversarial corruptions. We addresse existing challenges in robust learning in high dimension and establish new connections between robust statistics and …
-
Practical Robust Learning Under Domain Shifts
… the visual changes in the environment, without learning all over again. However, to make machines work in the changed environment we need new annotations from human. The fundamental question is: can we make machines as adaptive as humans? In this thesis, we have worked towards addressing this …
-
A Theoretical Investigation Into Adversarially Robust Learning
Machine learning models based on neural networks power the state-of-the-art systems for various real-world applications. However, systems based on neural networks admit vulnerabilities in the form of adversarial attacks. One such limitation is due to arbitrary adversarial corruption of data at the …
-
ROBUST LEARNING AND PREDICTION IN DEEP LEARNING
Robustness is the ability to withstand adverse conditions. When it is transposed into deep learning, it refers to the ability to tolerate perturbations that might affect the deep model's functionality. Learning a deep model and deploying it for usage require robustness. In this thesis, we explore …
-
Distributionally Robust Learning under the Wasserstein Metric
… develops a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data using Distributionally Robust Optimization (DRO) under the Wasserstein metric. The learning problems that are studied include: (i) Distributionally Robust Linear …
-
Sample complexity of robust learning against evasion attacks
… to understand the vulnerability of machine learning models to adversarial attacks. One of the fundamental problems in adversarial machine learning is to quantify how much training data is needed in the presence of so-called evasion attacks, where data is corrupted at test time. In this …
-
Towards Expressive and Robust Learning with Hyperbolic Geometry
Machine learning models traditionally operate within the confines of Euclidean space, assuming the Euclidean nature of data. However, there is a growing interest in learning within non-Euclidean hyperbolic space, particularly in scenarios where data exhibits explicit or implicit hierarchies, such …
-
Robust Learning, Inference and Uncertainty Quantification via Contrast
… contrast to improve trustworthiness in machine learning. We do this in two specific ways. We provide a new framework for producing counterfactuals which uses contrast to verify that they will have the intended effect without acting adversarially. We also propose a new fine-grained measure of …
-
Towards provably safe and robust learning-enabled systems
Machine learning (ML) has demonstrated great success in numerous complicated tasks. Fueled by these advances, many real-world systems like autonomous vehicles and aircraft are adopting ML techniques by adding learning-enabled components. Unfortunately, ML models widely used today, like neural …
-
Adaptive and weighted optimization for efficient and robust learning
Modern machine learning has made significant breakthroughs for scientific and technological applications and led to paradigm shifts in optimization and generalization theories. Adaptive and weighted optimization have become the workhorses behind today's machine learning applications, but there is …
-
Robust Learning Architectures for Perceiving Object Semantics and Geometry
… substantial progress has been made towards learning scalable image representation for large-scale vision problems such as image classification. However, there still remains some fundamental challenges in learning robust object representation. First, creating object representations that are …
-
A Robust Learning Framework for Resource-Constrained Domain Adaptation
Most existing machine learning models assume that training and test data are independently and identically distributed (\iid) according to the same data distribution. Under this assumption, a model trained on labeled data is expected to generalize well to unseen test data. However, real-world …
-
Robust Learning Frameworks and Algorithms for Scalable Data Systems
The data explosion and advances in machine learning have empowered modern computing systems with intelligence. While blossomed in business, science, and engineering with numerous real-world applications, unprecedented challenges in security, privacy, and scalability have been found. This …
-
CARE: certifiably robust learning with reasoning via variational inference
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Robust learning to rank models and their biomedical applications
… value of some discrete or continuous outcome. Learning-to-Rank (LTR) refers to a group of algorithms that apply machine learning techniques to tackle these ranking problems. Despite their empirical success, most existing LTR models are not built to be robust to errors in labeling or annotation, …
-
Robust learning of deep neural networks under data corruption
… some previous studies that aim to enhance the robustness of machine learning models against data corruption, most of them either lack theoretical robustness guarantees or unable to scale to the millions of model parameters governing deep neural networks. The goal of this thesis is to design …
-
Robust learning with low-dimensional structure: theory,algorithms and applications
In this thesis, we study the robust learning of low-dimensional structures when there are uncertainties in the data. In particular, we consider two structures that are common in real problems: ?low-rank subspace model? that underlies matrix completion and Robust PCA, and ?union-of-subspace model? …
-
Adversarial Attack and Robust Learning in Multi-Arm Bandit Problems
In this paper we study bandit learning problem with adversaries. Bandit learning setting is a typical sequential decisions making setting whose biggest challenge is to balance the exploration and exploitation. Models based on bandit learning setting are widely applied in a variety fields of …
-
TOWARDS ROBUST LEARNING USING DIAMETRICAL RISK MINIMIZATION FOR NETWORK INTRUSION DETECTION
… Empirical Risk Minimization (ERM), which is not robust to misclassified or altered training data. We propose applying Diametrical Risk Minimization (DRM), which is shown to lead to more robust optimization solutions, to train DNNs to classify malicious network traffic. Using two different network …
Page 1 of 7