Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Golebiowski, Jacek"'
Techniques for knowledge graph (KGs) enrichment have been increasingly crucial for commercial applications that rely on evolving product catalogues. However, because of the huge search space of potential enrichment, predictions from KG completion (KG
Externí odkaz:
http://arxiv.org/abs/2406.07098
Pre-trained language models (PLM), for example BERT or RoBERTa, mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. However, their large size poses challenges in deploying them for inference in real-worl
Externí odkaz:
http://arxiv.org/abs/2405.02267
Large language models (LLMs) encode vast amounts of world knowledge. However, since these models are trained on large swaths of internet data, they are at risk of inordinately capturing information about dominant groups. This imbalance can propagate
Externí odkaz:
http://arxiv.org/abs/2310.14777
Off-policy evaluation (OPE) methods allow us to compute the expected reward of a policy by using the logged data collected by a different policy. OPE is a viable alternative to running expensive online A/B tests: it can speed up the development of ne
Externí odkaz:
http://arxiv.org/abs/2305.03954
Many state-of-the-art hyperparameter optimization (HPO) algorithms rely on model-based optimizers that learn surrogate models of the target function to guide the search. Gaussian processes are the de facto surrogate model due to their ability to capt
Externí odkaz:
http://arxiv.org/abs/2305.03623
Autor:
Wang, Cheng, Golebiowski, Jacek
Model miscalibration has been frequently identified in modern deep neural networks. Recent work aims to improve model calibration directly through a differentiable calibration proxy. However, the calibration produced is often biased due to the binnin
Externí odkaz:
http://arxiv.org/abs/2303.15057
Autor:
Sutton, Christopher, Ghiringhelli, Luca M., Yamamoto, Takenori, Lysogorskiy, Yury, Blumenthal, Lars, Hammerschmidt, Thomas, Golebiowski, Jacek, Liu, Xiangyue, Ziletti, Angelo, Scheffler, Matthias
Machine learning (ML) is increasingly used in the field of materials science, where statistical estimates of computed properties are employed to rapidly examine the chemical space for new compounds. However, a systematic comparison of several ML mode
Externí odkaz:
http://arxiv.org/abs/1812.00085
Autor:
Wang, Cheng, Golebiowski, Jacek
Miscalibration-the mismatch between predicted probability and the true correctness likelihood-has been frequently identified in modern deep neural networks. Recent work in the field aims to address this problem by training calibrated models directly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a26131bd33a4b5ba20a7c8437a37b13
http://arxiv.org/abs/2303.15057
http://arxiv.org/abs/2303.15057
Publikováno v:
In Procedia Engineering 2014 87:428-431
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.