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 373 for “"Embeddings"”.
-
Algorithmic embeddings
We present several computationally efficient algorithms, and complexity results on low distortion mappings between metric spaces. An embedding between two metric spaces is a mapping between the two metric spaces and the distortion of the embedding is the factor by which the distances change. We …
-
Computational metric embeddings
… hardness of computing optimal, or near-optimal embeddings. When the input space is an ultrametric, we show that it is NP-hard to compute an optimal embedding into R2 under the ... norm. Moreover, we prove that for any fixed d > 2, it is NP-hard to approximate the minimum distortion embedding of …
-
Spinors, embeddings and gravity
… thesis is concerned with the theory of spinors, embeddings and everywhere invariance with applications to general relativity. The approach is entirely geometric with particular emphasis on the use of natural structures. A clear indication of the interaction between the above topics is given; this …
-
Geometries of word embeddings
Real-valued word embeddings have transformed natural language processing (NLP) applications, recognized for their ability to capture linguistic regularities. Popular examples are word2vec, GloVe, GPT and BERT. Both word2vec and GloVe are static whose word representations are independent of its …
-
Quantitative embeddings with applications
In this thesis, we discuss quantitative embeddings that generalize a theorem of Kolmogorov and Barzdin. The theorem says that any bounded degree graph with V vertices can be mapped into a 3-dimensional ball of radius sqrt(V), so that at most a constant number of edges intersect any unit ball. In …
-
Equivariant Embeddings of Algebraic Groups
We classify embeddings of algebraic groups as open orbits in affine varieties, generalizing results from toric geometry to connected reductive groups. In particular, we show that an embedding is determined by the set of one-parameter subgroups that have a limit in the embedding. We then investigate …
-
Learning embeddings for fashion recommendation
In this work, we present a novel methodology to recommend items that are compatible with a given item of clothing. Compatibility is a hard notion to capture because of its diversity and subjectivity. We propose an embedding based approach to solve this problem, and perform recommendation based on …
-
Clustering Tweets via Tweet Embeddings
… various embedding models to produce tweet embeddings, which we then use to cluster the tweets, forming groups of semantically similar tweets. We then compare these tweet clusters to users clustered by interest based on accounts they follow. This work introduces techniques on how to …
-
QuOTE: Question-Oriented Text Embeddings
We present QuOTE (Question-Oriented Text Embeddings), a novel enhancement to retrieval- augmented generation (RAG) systems, aimed at improving document representation for accurate and nuanced retrieval. Unlike traditional RAG pipelines, which rely on embed- ding raw text chunks, QuOTE augments …
-
Deep Assertion discovery using word embeddings
In recent years, there has been explosive growth in the amount of biomedical data (e.g., publications, notes from EHRs, clinical trial results), with the majority being unstructured data. As the volume of data is increasing faster, the demand for extracting knowledge from unstructured data …
-
Minors and planar embeddings of digraphs
… vertex. Clustered planar digraphs have planar embeddings in which, at each vertex, all of the in-arcs occur sequentially in the local rotation. Three different variations of minors are presented, each of which produces a finite set of obstructions to clustered planarity. These variations …
-
Learning structured representations with hyperbolic embeddings
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-05-01
-
Sufficient degree conditions for graph embeddings
In this dissertation, we focus on the sufficient conditions to guarantee one graph being the subgraph of another. In Chapter 2, we discuss list packing, a modification of the idea of graph packing. This is fitting one graph in the complement of another graph. Sauer and Spencer showed a sufficient …
-
Transparent Analysis of Multi-Modal Embeddings
… Space Models of Distributional Semantics – or Embeddings – serve as useful statistical models of word meanings, which can be applied as proxies to learn about human concepts. One of their main benefits is that not only textual, but a wide range of data types can be mapped to a space, where they …
-
Discount bundling via dense product embeddings
… continuous representations of products called embeddings. We then put minimal structure on these embeddings and develop heuristics for complementarity and substitutability among products. Subsequently, we use the heuristics to create multiple bundles for each product and test their performance …
-
On affine embeddings of reductive groups
… study the properties and the classification of embeddings of homogeneous spaces, especially the case of affine normal embeddings of reductive groups. We might guess that as in the case of toric varieties, some specific subset of one-parameter subgroups may contribute to the classification of …
-
Temporal Topic Embeddings with a Compass
Aligning Word2vec word embeddings using a compass in a system of Compass-aligned Distributional Embeddings (CADE) creates stable and accurate temporal word embeddings. This thesis seeks to expand the CADE framework into the area of dynamic topic modeling (DTM), where temporal word2vec embeddings …
-
Stabilization and classification of poincare duality embeddings
<p>We define a space E(K,X) of Poincare Duality embeddings and show that such spaces admit a highly connected stabilization map.</p> <p>This serves as a tool for classifying Poincare Duality embeddings in terms of the homotopy types of their complements. In</p> <p>particular, a Poincare embedding …
-
Learning hierarchical motif embeddings for protein engineering
… of proteins into a set of functional motif embeddings. We introduce, CoMET - Convolutional Motif Embeddings Tool, a machine learning framework that allows the automated extraction of nonlinear motif representations from large sets of protein sequences. At the core of CoMET, lies a Deep …
-
TimeLink: Visualizing Diachronic Word Embeddings and Topics
… is not easy. Work has been done to develop word embeddings, allowing researchers to treat words like any number. This makes it possible to create simple charts based on word embeddings like scatter plots. However, these methods are inefficient due to loss of effectiveness with multiple time …
Page 1 of 19