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"”.

  1. 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 …

    mit Repository record for Algorithmic embeddings (opens in a new tab)

  2. 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 …

    mit Repository record for Computational metric embeddings (opens in a new tab)

  3. 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 …

    soton Repository record for Spinors, embeddings and gravity (opens in a new tab)

  4. 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 …

    uiuc Repository record for Geometries of word embeddings (opens in a new tab)

  5. 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 …

    mit Repository record for Quantitative embeddings with applications (opens in a new tab)

  6. 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 …

    uiuc Repository record for Equivariant Embeddings of Algebraic Groups (opens in a new tab)

  7. 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 …

    uiuc Repository record for Learning embeddings for fashion recommendation (opens in a new tab)

  8. 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 …

    mit Repository record for Clustering Tweets via Tweet Embeddings (opens in a new tab)

  9. 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 …

    vt Repository record for QuOTE: Question-Oriented Text Embeddings (opens in a new tab)

  10. 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 …

    umkc Repository record for Deep Assertion discovery using word embeddings (opens in a new tab)

  11. 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 …

    auckland-ms Repository record for Minors and planar embeddings of digraphs (opens in a new tab)

  12. Learning structured representations with hyperbolic embeddings

    Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-05-01

    uiuc Repository record for Learning structured representations with hyperbolic embeddings (opens in a new tab)

  13. 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 …

    uiuc Repository record for Sufficient degree conditions for graph embeddings (opens in a new tab)

  14. 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 …

    cambridge Repository record for Transparent Analysis of Multi-Modal Embeddings (opens in a new tab)

  15. 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 …

    mit Repository record for Discount bundling via dense product embeddings (opens in a new tab)

  16. 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 …

    mit Repository record for On affine embeddings of reductive groups (opens in a new tab)

  17. 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

    vt Repository record for Temporal Topic Embeddings with a Compass (opens in a new tab)

  18. 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 …

    wayne-thes Repository record for Stabilization and classification of poincare duality embeddings (opens in a new tab)

  19. 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 …

    mit Repository record for Learning hierarchical motif embeddings for protein engineering (opens in a new tab)

  20. 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 …

    vt Repository record for TimeLink: Visualizing Diachronic Word Embeddings and Topics (opens in a new tab)

Page 1 of 19