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 27 for “"Distribution Learning"”.
-
OUT-OF-DISTRIBUTION LEARNING
Traditional machine learning approaches assume data points are independent and identically distributed (iid). However, in practice, a learning agent may face data points which drift significantly from the training distribution. In this thesis, we address the problem of out-of-distribution (OOD) …
-
Private Distribution Learning with Public Data
We study the problem of private distribution learning with access to public data. In this setup, a learner is given both public and private samples drawn from an unknown distribution 𝑝 belonging to a class 𝑄, and has the task of outputting an estimate of 𝑝 while adhering to privacy constraints …
-
OUT-OF-DISTRIBUTION LEARNING FOR ROBUST VISION PERCEPTION
Despite advances in deep learning, most models assume that test data match the training distribution (ID). However, real-world data are unpredictable and often contain out-of-distribution (OOD) samples, posing significant challenges. This thesis focuses on data-efficient OOD learning to improve …
-
A Study on Distribution Learning of Generative Adversarial Networks
… to investigate the learnability of a class of distributions using shallow GANs and conduct experiments to explore the influence of these aspects on the performance of the GAN models. We identify and analyze several pathological phenomena in theoretical analysis and experiments, and propose …
-
Inherent Limitations of Dimensions for Characterizing Learnability
The fundamental theorem of statistical learning establishes the equivalence between various notions of both agnostic and realizable Probably Approximately Correct (PAC) learnability for binary classification with the finiteness of the VC dimension. Motivated by these foundational results, this work …
-
Learning Poisson Binomial Distributions with Differential Privacy
… δύο ερευνητικά πεδία. Το πρώτο πεδίο αφορά το Distribution Learning ενώ το δεύτερο το Differnetial Privacy. Πιο συγκεκριμένα, δοθέντος ενός learning αλγορίθμου ο οποίος μαθαίνει με ε-accuracy μια Poisson διωνυμική κατανομή προσπαθούμε να βρούμε αν ο αλγόριθμος είναι Differential Private. …
-
Skewed Lines of Thought - Biases in Distribution Perception and How to Investigate Them
How do people perceive and process the distribution of socially relevant variables, such as income? The current thesis presents three articles that experimentally investigate processes and phenomena pertinent to this question. The articles, each consisting of three experiments, are linked by two …
-
A PAC-Theory of Clustering with Advice
… knowledge. We provide ``advice complexity'' of learning a representation in this paradigm. Another form of ``advice'' can be obtained by allowing the clustering algorithm to interact with a domain expert by asking same-cluster queries: ``Do these two instances belong to the same cluster?''. The …
-
Learning Representations For Matching
… matches. Additionally, in recent years, deep learning has shown great promise in Computer Vision. Deep learning techniques are state of the art in object detection, segmentation, and image generation. Deep learning techniques excel at feature learning, and prior distribution learning …
-
Learning with classical and quantum information constraints
… the fundamental limit of information-constrained learning and designs sample-optimal algorithms under settings of practical interest. We consider various information constraints, including privacy and communication constraints on classical computers, and inherent randomness governed by the laws of …
-
Optimal algorithms for experts and mixtures of Gaussians
… thesis makes contributions to two problems in learning theory: prediction with expert advice and learning mixtures of Gaussians. The problem of prediction with expert advice can be cast as a sequential game between an algorithm and an adversary as follows. At each time step, an algorithm …
-
Deep Time Series Modeling: From Distribution Regularity to Distribution Shift
… space models, Bayesian models, or other machine learning models for time series modeling. However, these methods usually follow certain assumptions and don't reveal the core and underlying rules of time series. Moreover, the recent advancement of deep learning has made neural networks a powerful …
-
Human-in-the-Loop Learning From Crowdsourcing and Social Media
… in a feasible and scalable manner. Machine learning problems are, as a result, often subjective or ambiguous when humans are involved. That is, humans solving the same problems might come to legitimate but completely different conclusions, based on their personal experiences and beliefs. …
-
NLP-enabled Design Assistance For Visual Communication
… candidates for emphasis, where we propose label distribution learning methods to capture the ambiguity of the input. These models are designed to comprehend the most common interpretation of a written text, so the right emphasis can be achieved automatically or interactively. In the second part …
-
Augmenting Generative De Novo Drug Design with Synthetic Data
… novo drug design is the use of generative deep learning models, such as recurrent neural networks (RNNs). However, despite the promises of RNNs, they can be outperformed by traditional methods such as the Graph GA (Brown et al., 2019). Recent works have used randomised/enumerated SMILES as a …
-
Deep Learning for Automated Image Segmentation Using Optical Signals From Endogenous Metabolic and Structural Biomarkers
… methods may be analyzed through U-Net, a deep learning architecture designed specifically for the task of image segmentation. The goal of this study is to lay the foundation for training a deep learning model capable of segmenting in vivo TPEF images. The study focused first on model training …
-
Multiply sectioned Bayesian belief networks for large knowledge-based systems: an application to neuromuscular diagnosis
… shows very good performance. Coding probability distribution of Bayesian nets in causal direction has several ad vantages. Initially the distribution is elicited from the expert in terms of probabilities of a symptom given causing diseases. Since disease-to-symptom is not the direction of daily …
-
Algorithm design for reliable machine learning
… study questions in the area of Reliable Machine Learning in order to design algorithms that are robust to bias and noise (Robust Machine Learning) and satisfy societal desiderata such as privacy and reproducibility (Responsible Machine Learning).In the area of Robust Machine Learning, we design …
-
PRIVATE DENSITY ESTIMATION FOR MIXTURE DISTRIBUTIONS AND GAUSSIAN MIXTURE MODELS
… a general technique for estimating (mixture) distributions under the constraint of differential privacy (DP). On a high level, we show that if a class of distributions (such as Gaussians) is (1) list decodable and (2) admits a “locally small” cover (Bun et al., 2021) with respect to total …
-
Crisis detection from Arabic social media
… of noisy data in real time. Supervised machine learning classifiers are challenged by out-of-distribution learning when classifying unseen (new) crises due to data variations across events. Besides that, it is impractical to label training data from each novel and emerging crisis since obtaining …
Page 1 of 2