Zobrazeno 1 - 10
of 835
pro vyhledávání: '"WHITE, COLIN"'
Autor:
White, Colin, Dooley, Samuel, Roberts, Manley, Pal, Arka, Feuer, Ben, Jain, Siddhartha, Shwartz-Ziv, Ravid, Jain, Neel, Saifullah, Khalid, Naidu, Siddartha, Hegde, Chinmay, LeCun, Yann, Goldstein, Tom, Neiswanger, Willie, Goldblum, Micah
Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render benchmarks obsolete. To mitigate this, many recent benchmarks crowdsource
Externí odkaz:
http://arxiv.org/abs/2406.19314
Autor:
Rahman, Md Ashiqur, George, Robert Joseph, Elleithy, Mogab, Leibovici, Daniel, Li, Zongyi, Bonev, Boris, White, Colin, Berner, Julius, Yeh, Raymond A., Kossaifi, Jean, Azizzadenesheli, Kamyar, Anandkumar, Anima
Existing neural operator architectures face challenges when solving multiphysics problems with coupled partial differential equations (PDEs) due to complex geometries, interactions between physical variables, and the limited amounts of high-resolutio
Externí odkaz:
http://arxiv.org/abs/2403.12553
Direct Preference Optimisation (DPO) is effective at significantly improving the performance of large language models (LLMs) on downstream tasks such as reasoning, summarisation, and alignment. Using pairs of preferred and dispreferred data, DPO mode
Externí odkaz:
http://arxiv.org/abs/2402.13228
Autor:
Feuer, Benjamin, Schirrmeister, Robin Tibor, Cherepanova, Valeriia, Hegde, Chinmay, Hutter, Frank, Goldblum, Micah, Cohen, Niv, White, Colin
While tabular classification has traditionally relied on from-scratch training, a recent breakthrough called prior-data fitted networks (PFNs) challenges this approach. Similar to large language models, PFNs make use of pretraining and in-context lea
Externí odkaz:
http://arxiv.org/abs/2402.11137
Publikováno v:
Thirty-seventh Conference on Neural Information Processing Systems, 2023
The vast majority of time-series forecasting approaches require a substantial training dataset. However, many real-life forecasting applications have very little initial observations, sometimes just 40 or fewer. Thus, the applicability of most foreca
Externí odkaz:
http://arxiv.org/abs/2311.01933
Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks. Since LLMs train on wide swaths of the internet, this practice raises concerns of data contamination, i.e.,
Externí odkaz:
http://arxiv.org/abs/2310.10628
Autor:
Tu, Renbo, White, Colin, Kossaifi, Jean, Bonev, Boris, Kovachki, Nikola, Pekhimenko, Gennady, Azizzadenesheli, Kamyar, Anandkumar, Anima
Neural operators, such as Fourier Neural Operators (FNO), form a principled approach for learning solution operators for PDEs and other mappings between function spaces. However, many real-world problems require high-resolution training data, and the
Externí odkaz:
http://arxiv.org/abs/2307.15034
Autor:
McElfresh, Duncan, Khandagale, Sujay, Valverde, Jonathan, C, Vishak Prasad, Feuer, Benjamin, Hegde, Chinmay, Ramakrishnan, Ganesh, Goldblum, Micah, White, Colin
Tabular data is one of the most commonly used types of data in machine learning. Despite recent advances in neural nets (NNs) for tabular data, there is still an active discussion on whether or not NNs generally outperform gradient-boosted decision t
Externí odkaz:
http://arxiv.org/abs/2305.02997
Autor:
White, Colin, Safari, Mahmoud, Sukthanker, Rhea, Ru, Binxin, Elsken, Thomas, Zela, Arber, Dey, Debadeepta, Hutter, Frank
In the past decade, advances in deep learning have resulted in breakthroughs in a variety of areas, including computer vision, natural language understanding, speech recognition, and reinforcement learning. Specialized, high-performing neural archite
Externí odkaz:
http://arxiv.org/abs/2301.08727