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 54 for “"Efficient inference"”.

  1. A*-Decoding: Token-Efficient Inference Scaling

    Inference-time scaling has emerged as a powerful alternative to parameter scaling for improving language model performance on complex reasoning tasks. While existing methods have shown strong performance gains under fixed compute budgets, there has been little focus on optimally utilizing that …

    mit Repository record for A*-Decoding: Token-Efficient Inference Scaling (opens in a new tab)

  2. 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 …

    oxford-brookes Repository record for Efficient inference and learning for computer vision labelling problems (opens in a new tab)

  3. 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 …

    uiuc Repository record for Cross-layer methods for energy-efficient inference using in-memory architectures (opens in a new tab)

  4. Efficient inference of convolutional neural networks on general purpose hardware using weight repetition

    … weight repetition can be harnessed improve DNN inference efficiency in an accelerator/ASIC context. This thesis develops new techniques so that weight repetition leads to an efficiency gain on general-purpose and programmable SIMD-based architectures such as CPUs equipped with vector extensions. …

    uiuc Repository record for Efficient inference of convolutional neural networks on general purpose hardware using weight repetition (opens in a new tab)

  5. Bayesian multiple-network multi-layer exponential random graph models (MNML-ERGMs): developing efficient inference and application to neuroimaging

    … networks. Furthermore, we use variational inference to enable efficient ERGM inference within a hierarchical Bayesian setup. In the first part of this thesis, we address the under-exploration of weighted ERGMs, for which most developed methods originate from diverse backgrounds. We …

    cambridge Repository record for Bayesian multiple-network multi-layer exponential random graph models (MNML-ERGMs): developing efficient inference and application to neuroimaging (opens in a new tab)

  6. Structured learning and inference with neural networks and generative models

    … neural networks are flexible and support efficient inference, but rely on large quantities of labeled training data. Probabilistic models can learn from fewer examples, but in many cases remain limited by time-consuming inference algorithms. Thus, both classes of models have drawbacks that …

    mit Repository record for Structured learning and inference with neural networks and generative models (opens in a new tab)

  7. Distributed inference : combining variational inference with distributed computing

    The study of inference techniques and their use for solving complicated models has taken off in recent years, but as the models we attempt to solve become more complex, there is a worry that our inference techniques will be unable to produce results. Many problems are difficult to solve using …

    mit Repository record for Distributed inference : combining variational inference with distributed computing (opens in a new tab)

  8. Algorithm–Hardware Co-Design Of Digital Compute-In-Memory Architecture Supporting Flexible And Temporal N:M Sparsity

    … algorithm–hardware co-design approaches for efficient inference, with structured N:M sparsity emerging as a promising method to reduce overhead. However, fixed sparsity configurations across layers and decoding steps can limit model expressivity and degrade accuracy, while supporting multiple …

    gatech Repository record for Algorithm–Hardware Co-Design Of Digital Compute-In-Memory Architecture Supporting Flexible And Temporal N:M Sparsity (opens in a new tab)

  9. Bayesian nonparametric learning with semi-Markovian dynamics

    … and develop posterior sampling algorithms for efficient inference. We also develop novel sampling inference for the Bayesian version of the classical explicit-duration Hidden semi-Markov Model. We demonstrate the utility of the HDP-HSMM and our inference methods on synthetic data as well as …

    mit Repository record for Bayesian nonparametric learning with semi-Markovian dynamics (opens in a new tab)

  10. Evaluating summarization and inference techniques for high energy physics applications

    … and computational requirements of traditional inference procedures can become intractable. The problem of scalable inference appears in many fields, and thus it is an area of continuous development in computer science. With the proliferation of improved methods for data summarization and …

    mit Repository record for Evaluating summarization and inference techniques for high energy physics applications (opens in a new tab)

  11. Morphological segmentation : an unsupervised method and application to Keyword Spotting

    … that is simple and can be used to perform fast, efficient inference on new words. We evaluate our model on a standard morphological segmentation dataset, and obtain large performance gains of up to 18.4% over an existing state-of-the-art system, Morfessor. Second, we explore the impact of …

    mit Repository record for Morphological segmentation : an unsupervised method and application to Keyword Spotting (opens in a new tab)

  12. A multiscale framework for Bayesian inference in elliptic problems

    The Bayesian approach to inference problems provides a systematic way of updating prior knowledge with data. A likelihood function involving a forward model of the problem is used to incorporate data into a posterior distribution. The standard method of sampling this distribution is Markov chain …

    mit Repository record for A multiscale framework for Bayesian inference in elliptic problems (opens in a new tab)

  13. Flexible Energy-Aware Image and Transformer Processors for Edge Computing

    Machine learning inference on edge devices for image and language processing has become increasingly common in recent years, but faces challenges associated with high memory and computation requirements, coupled with limited energy resources. This work applies different quantization schemes and …

    mit Repository record for Flexible Energy-Aware Image and Transformer Processors for Edge Computing (opens in a new tab)

  14. Extending expectation propagation for graphical models

    … to wireless signal detection. However, efficient inference and learning techniques for graphical models are needed to handle complex models, such as hybrid Bayesian networks. This thesis proposes extensions of expectation propagation, a powerful generalization of loopy belief …

    mit Repository record for Extending expectation propagation for graphical models (opens in a new tab)

  15. Cause, Composition, and Structure in Language

    … within which a repertoire of compositional inference motifs support efficient inference. I begin with a targeted case study showing how native speakers follow principles of noisy-channel inference in resolving subject-verb agreement mismatches such as "The gift for the kids are hidden under …

    mit Repository record for Cause, Composition, and Structure in Language (opens in a new tab)

  16. Messaging for large-scale distributed computation with factor graphs

    … abstraction that has been popularly utilized for efficient inference in the framework of probabilistic graphical models cf. [22, 15, 30]. We show that message passing over Factor Graphs is Turing-complete. As an important contribution of this work, we show that a Factor Graph can be realized using …

    mit Repository record for Messaging for large-scale distributed computation with factor graphs (opens in a new tab)

  17. A hierarchical framework for constructing computationally efficient algorithms for distributed inference problems

    … a methodology for designing computationally efficient algorithms for large-scale inference systems on system architectures with distributed autonomous agents. The principle of information-based computation is the underlying idea driving elements of this methodology. The methodology consists …

    mit Repository record for A hierarchical framework for constructing computationally efficient algorithms for distributed inference problems (opens in a new tab)

  18. Bayesian nonparametric learning of complex dynamical phenomena

    … analytic techniques are available. However, inference on standard nonlinear models quickly becomes intractable. In some cases, Markov switching processes, with switches between a set of simpler models, are employed to describe the observed dynamics. Such models typically rely on …

    mit Repository record for Bayesian nonparametric learning of complex dynamical phenomena (opens in a new tab)

Page 1 of 3