Zobrazeno 1 - 10
of 75
pro vyhledávání: '"Karnin, Zohar"'
Training large language models (LLMs) for external tool usage is a rapidly expanding field, with recent research focusing on generating synthetic data to address the shortage of available data. However, the absence of systematic data quality checks p
Externí odkaz:
http://arxiv.org/abs/2409.16341
Autor:
Khaki, Saeed, Aditya, Akhouri Abhinav, Karnin, Zohar, Ma, Lan, Pan, Olivia, Chandrashekar, Samarth Marudheri
Drift in machine learning refers to the phenomenon where the statistical properties of data or context, in which the model operates, change over time leading to a decrease in its performance. Therefore, maintaining a constant monitoring process for m
Externí odkaz:
http://arxiv.org/abs/2309.03831
Autor:
CORMODE, GRAHAM1 G.Cormode@warwick.ac.uk, KARNIN, ZOHAR2 zkarnin@gmail.com, LIBERTY, EDO3 edo@edoliberty.com, THALER, JUSTIN4 justin.thaler@georgetown.edu, VESELÝ, PAVEL5 vesely@iuuk.mff.cuni.cz
Publikováno v:
Journal of the ACM. Oct2023, Vol. 70 Issue 5, p1-48. 48p.
Autor:
Razdaibiedina, Anastasia, Khetan, Ashish, Karnin, Zohar, Khashabi, Daniel, Kapoor, Vishaal, Madan, Vivek
Fine-tuning contextualized representations learned by pre-trained language models remains a prevalent practice in NLP. However, fine-tuning can lead to representation degradation (also known as representation collapse), which may result in instabilit
Externí odkaz:
http://arxiv.org/abs/2205.11603
Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use various heuristics to successively shorten sequence length while trans
Externí odkaz:
http://arxiv.org/abs/2203.14380
Autor:
Nigenda, David, Karnin, Zohar, Zafar, Muhammad Bilal, Ramesha, Raghu, Tan, Alan, Donini, Michele, Kenthapadi, Krishnaram
With the increasing adoption of machine learning (ML) models and systems in high-stakes settings across different industries, guaranteeing a model's performance after deployment has become crucial. Monitoring models in production is a critical aspect
Externí odkaz:
http://arxiv.org/abs/2111.13657
Autor:
Qin, Fred, Madan, Vivek, Ratan, Ujjwal, Karnin, Zohar, Kapoor, Vishaal, Bhatia, Parminder, Kass-Hout, Taha
Sepsis is a life-threatening disease with high morbidity, mortality and healthcare costs. The early prediction and administration of antibiotics and intravenous fluids is considered crucial for the treatment of sepsis and can save potentially million
Externí odkaz:
http://arxiv.org/abs/2107.11094
Autor:
Das, Piali, Perrone, Valerio, Ivkin, Nikita, Bansal, Tanya, Karnin, Zohar, Shen, Huibin, Shcherbatyi, Iaroslav, Elor, Yotam, Wu, Wilton, Zolic, Aida, Lienart, Thibaut, Tang, Alex, Ahmed, Amr, Faddoul, Jean Baptiste, Jenatton, Rodolphe, Winkelmolen, Fela, Gautier, Philip, Dirac, Leo, Perunicic, Andre, Miladinovic, Miroslav, Zappella, Giovanni, Archambeau, Cédric, Seeger, Matthias, Dutt, Bhaskar, Rouesnel, Laurence
AutoML systems provide a black-box solution to machine learning problems by selecting the right way of processing features, choosing an algorithm and tuning the hyperparameters of the entire pipeline. Although these systems perform well on many datas
Externí odkaz:
http://arxiv.org/abs/2012.08483
We propose TabTransformer, a novel deep tabular data modeling architecture for supervised and semi-supervised learning. The TabTransformer is built upon self-attention based Transformers. The Transformer layers transform the embeddings of categorical
Externí odkaz:
http://arxiv.org/abs/2012.06678
Attribution methods have been shown as promising approaches for identifying key features that led to learned model predictions. While most existing attribution methods rely on a baseline input for performing feature perturbations, limited research ha
Externí odkaz:
http://arxiv.org/abs/2011.06015