Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Samulowitz, Horst"'
Autor:
Khatiwada, Aamod, Kokel, Harsha, Abdelaziz, Ibrahim, Chaudhury, Subhajit, Dolby, Julian, Hassanzadeh, Oktie, Huang, Zhenhan, Pedapati, Tejaswini, Samulowitz, Horst, Srinivas, Kavitha
Enterprises have a growing need to identify relevant tables in data lakes; e.g. tables that are unionable, joinable, or subsets of each other. Tabular neural models can be helpful for such data discovery tasks. In this paper, we present TabSketchFM,
Externí odkaz:
http://arxiv.org/abs/2407.01619
Large Language Models (LLMs) have been observed to perform well on a wide range of downstream tasks when fine-tuned on domain-specific data. However, such data may not be readily available in many applications, motivating zero-shot or few-shot approa
Externí odkaz:
http://arxiv.org/abs/2406.13720
Online planner selection is the task of choosing a solver out of a predefined set for a given planning problem. As planning is computationally hard, the performance of solvers varies greatly on planning problems. Thus, the ability to predict their pe
Externí odkaz:
http://arxiv.org/abs/2402.04874
Autor:
Abbas, Momin, Zhou, Yi, Ram, Parikshit, Baracaldo, Nathalie, Samulowitz, Horst, Salonidis, Theodoros, Chen, Tianyi
In-context learning (ICL) is a new paradigm for natural language processing that utilizes Generative Pre-trained Transformer (GPT)-like models. This approach uses prompts that include in-context demonstrations to generate the corresponding output for
Externí odkaz:
http://arxiv.org/abs/2401.12406
Autor:
Lobo, Elita, Hassanzadeh, Oktie, Pham, Nhan, Mihindukulasooriya, Nandana, Subramanian, Dharmashankar, Samulowitz, Horst
Enterprises often own large collections of structured data in the form of large databases or an enterprise data lake. Such data collections come with limited metadata and strict access policies that could limit access to the data contents and, theref
Externí odkaz:
http://arxiv.org/abs/2309.11506
Autor:
Srinivas, Kavitha, Dolby, Julian, Abdelaziz, Ibrahim, Hassanzadeh, Oktie, Kokel, Harsha, Khatiwada, Aamod, Pedapati, Tejaswini, Chaudhury, Subhajit, Samulowitz, Horst
Within enterprises, there is a growing need to intelligently navigate data lakes, specifically focusing on data discovery. Of particular importance to enterprises is the ability to find related tables in data repositories. These tables can be unionab
Externí odkaz:
http://arxiv.org/abs/2307.04217
The recent efforts in automation of machine learning or data science has achieved success in various tasks such as hyper-parameter optimization or model selection. However, key areas such as utilizing domain knowledge and data semantics are areas whe
Externí odkaz:
http://arxiv.org/abs/2303.01378
We show, to our knowledge, the first theoretical treatments of two common questions in cross-validation based hyperparameter selection: (1) After selecting the best hyperparameter using a held-out set, we train the final model using {\em all} of the
Externí odkaz:
http://arxiv.org/abs/2301.05131
Data Scientists leverage common sense reasoning and domain knowledge to understand and enrich data for building predictive models. In recent years, we have witnessed a surge in tools and techniques for {\em automated machine learning}. While data sci
Externí odkaz:
http://arxiv.org/abs/2205.08018
Autor:
Zhou, Yi, Ram, Parikshit, Salonidis, Theodoros, Baracaldo, Nathalie, Samulowitz, Horst, Ludwig, Heiko
We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO). We introduce Federated Loss SuRface Aggregation (FLoRA), a general FL-HPO solution framework that can address use cases of tabular dat
Externí odkaz:
http://arxiv.org/abs/2202.08338