Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Shwartz-Ziv, Ravid"'
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:
Roush, Allen, Shabazz, Yusuf, Balaji, Arvind, Zhang, Peter, Mezza, Stefano, Zhang, Markus, Basu, Sanjay, Vishwanath, Sriram, Fatemi, Mehdi, Shwartz-Ziv, Ravid
We introduce OpenDebateEvidence, a comprehensive dataset for argument mining and summarization sourced from the American Competitive Debate community. This dataset includes over 3.5 million documents with rich metadata, making it one of the most exte
Externí odkaz:
http://arxiv.org/abs/2406.14657
Autor:
Shwartz-Ziv, Ravid, Goldblum, Micah, Bansal, Arpit, Bruss, C. Bayan, LeCun, Yann, Wilson, Andrew Gordon
It is widely believed that a neural network can fit a training set containing at least as many samples as it has parameters, underpinning notions of overparameterized and underparameterized models. In practice, however, we only find solutions accessi
Externí odkaz:
http://arxiv.org/abs/2406.11463
Autor:
Schaeffer, Rylan, Lecomte, Victor, Pai, Dhruv Bhandarkar, Carranza, Andres, Isik, Berivan, Unell, Alyssa, Khona, Mikail, Yerxa, Thomas, LeCun, Yann, Chung, SueYeon, Gromov, Andrey, Shwartz-Ziv, Ravid, Koyejo, Sanmi
Maximum Manifold Capacity Representations (MMCR) is a recent multi-view self-supervised learning (MVSSL) method that matches or surpasses other leading MVSSL methods. MMCR is intriguing because it does not fit neatly into any of the commonplace MVSSL
Externí odkaz:
http://arxiv.org/abs/2406.09366
Entropy minimization (EM) is frequently used to increase the accuracy of classification models when they're faced with new data at test time. EM is a self-supervised learning method that optimizes classifiers to assign even higher probabilities to th
Externí odkaz:
http://arxiv.org/abs/2405.05012
Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling
Externí odkaz:
http://arxiv.org/abs/2312.02517
Most interpretability research in NLP focuses on understanding the behavior and features of a fully trained model. However, certain insights into model behavior may only be accessible by observing the trajectory of the training process. We present a
Externí odkaz:
http://arxiv.org/abs/2309.07311
Transfer learning plays a key role in advancing machine learning models, yet conventional supervised pretraining often undermines feature transferability by prioritizing features that minimize the pretraining loss. In this work, we adapt a self-super
Externí odkaz:
http://arxiv.org/abs/2306.13292
Self-supervised learning (SSL) is a powerful tool in machine learning, but understanding the learned representations and their underlying mechanisms remains a challenge. This paper presents an in-depth empirical analysis of SSL-trained representation
Externí odkaz:
http://arxiv.org/abs/2305.15614
Autor:
Shwartz-Ziv, Ravid, LeCun, Yann
Deep neural networks excel in supervised learning tasks but are constrained by the need for extensive labeled data. Self-supervised learning emerges as a promising alternative, allowing models to learn without explicit labels. Information theory, and
Externí odkaz:
http://arxiv.org/abs/2304.09355