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 142 for “"Efficient Inference"”.
-
Efficient Inference-time Control and Alignment
… paradigm: enforcing behavioral objectives at inference time rather than modifying model parameters during post-training. In this approach, smaller modular control models are combined with a base model to shape predictions during the decision process. Our aim is to design alignment mechanisms …
-
Efficient inference algorithms for network activities
… activities in the social network. The inference of relationship between users/nodes or groups of users/nodes could be further complicated when activities are interval-censored, that is, when one only observed the number of activities that occurred in certain time windows. The same …
-
Efficient inference in general semiparametric regression models
… that are addressed in this work are related to efficient inferential procedures in general semiparametric regression problems. We first discuss efficient estimation of population-level summaries in general semiparametric regression models. Here our focus is on estimating general population-level …
-
Adapting MoE for efficient inference and applications
… replication engine that vastly reduce MoE inference latency, MoE model merging techniques and use of MoE for better representation learning in graphs.
-
Novel neural architectures & algorithms for efficient inference
… size, compute-intensive training, increased inference latency, higher working memory, etc. This thesis aims at improving the resource efficiency of neural architectures, i.e., significantly reducing the computational, storage, and energy consumption of a DNN without any significant loss in …
-
Efficient inference algorithms for some probabilistic graphical models
… navigation and many more. We propose several inference algorithms for some probabilistic graphical models. For Bayesian network graphical models, we focus on the problem of overlapping clustering, where a data point is allowed to belong to multiple clusters. We present an overlapping …
-
Learning and Exploiting Relational Structure for Efficient Inference
… models over a set of related objects. However, inference in Markov logic and similar languages is #P-complete. Most existing tractable statistical relational representations are very limited in expressiveness. This dissertation explores two strategies for dealing with intractability while …
-
Fast and Expressive Sketch Structured Transform for Efficient Inference
… losing accuracy, suggesting the benefit of more efficient transformations. Among variants of weight matrices, structured ones have limitations in expressivity and quality-efficiency tradeoffs. Unstructured matrices are incompatible with modern hardware, leading to slower training and inference. …
-
Efficient inference and learning for computer vision labelling problems
… tool for computer vision problems. It enables inference of the maximum a posteriori solutions of Markov and conditional random fields which can be used to model labelling problems in vision. When formulating such problems in an energy minimization framework there are three main issues that need …
-
Persistency algorithms for efficient inference in Markov Random Fields
… denoising, during the past 20 years. Despite the inference problem being NP-hard, a large number of approximation algorithms, e.g., graphcuts, have been studied, although all of these methods are computationally expensive. We observed that most problems in practice contains a large easy part and a …
-
Integrating representative and non-representative survey data for efficient inference
… survey to reduce uncertainty in now-casting and inference estimates while simultaneously retaining the empirical credible interval coverage. Ultimately, we are able to conceptually obtain the properties of a large sample unbiased survey if the assumed unbiased survey, used to anchor the …
-
Compression Algorithms for Efficient Inference and Adaptation of Foundation Models
… to deploy at scale and challenging to adapt efficiently. This thesis presents novel algorithms for compressing foundation models, enabling faster and more efficient inference as well as adaptation. By making these models more accessible to both individuals and organizations, this work seeks …
-
Efficient Inference and Dominant-Set Based Clustering for Functional Data
… problems for functional data analysis: (1) To do efficient inference for the functional mean model accounting for within-subject correlation, we propose the refined and bias-corrected empirical likelihood method. (2) To identify functional subjects potentially from different populations, we …
-
Efficient Inference for High Dimensional Data Under Physical and Human Constraints
… data requires the system to be both efficient and "online", i.e., to be able to update models and estimates on the fly.</p><p>The variety of data includes both data types and data dynamics. Big data often come in multiple sources. For example, healthcare record data may include …
-
Cross-layer methods for energy-efficient inference using in-memory architectures
In the near future, we will be surrounded by intelligent devices that transform the way we interact with the world. These devices need to acquire and process data to derive actions and interpretations in order to automate/monitor many tasks without human intervention. Such tasks require the …
-
Efficient Inference of Transformers in Natural Language Processing: Early Exiting and Beyond
… parameters and being slow in both training and inference, making deployment difficult when inference time and resources are limited. Therefore, model efficiency has become a more important and urgent problem in the transformer era. In this thesis, we propose and innovate methods for efficient …
Page 1 of 8