Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Diamant, Nathaniel"'
Autor:
Uehara, Masatoshi, Zhao, Yulai, Black, Kevin, Hajiramezanali, Ehsan, Scalia, Gabriele, Diamant, Nathaniel Lee, Tseng, Alex M, Levine, Sergey, Biancalani, Tommaso
Diffusion models excel at modeling complex data distributions, including those of images, proteins, and small molecules. However, in many cases, our goal is to model parts of the distribution that maximize certain properties: for example, we may want
Externí odkaz:
http://arxiv.org/abs/2402.16359
Autor:
Uehara, Masatoshi, Zhao, Yulai, Black, Kevin, Hajiramezanali, Ehsan, Scalia, Gabriele, Diamant, Nathaniel Lee, Tseng, Alex M, Biancalani, Tommaso, Levine, Sergey
Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in the training dataset, we often are more concerned with other properties,
Externí odkaz:
http://arxiv.org/abs/2402.15194
Uncertainty estimation is critical in high-stakes machine learning applications. One effective way to estimate uncertainty is conformal prediction, which can provide predictive inference with statistical coverage guarantees. We present a new conforma
Externí odkaz:
http://arxiv.org/abs/2311.00774
Diffusion models have achieved state-of-the-art performance in generating many different kinds of data, including images, text, and videos. Despite their success, there has been limited research on how the underlying diffusion process and the final c
Externí odkaz:
http://arxiv.org/abs/2306.02957
Autor:
Grambow, Colin A., Weir, Hayley, Diamant, Nathaniel L., Scalia, Gabriele, Biancalani, Tommaso, Chuang, Kangway V.
Macrocyclic peptides are an emerging therapeutic modality, yet computational approaches for accurately sampling their diverse 3D ensembles remain challenging due to their conformational diversity and geometric constraints. Here, we introduce RINGER,
Externí odkaz:
http://arxiv.org/abs/2305.19800
Diffusion models achieve state-of-the-art performance in generating realistic objects and have been successfully applied to images, text, and videos. Recent work has shown that diffusion can also be defined on graphs, including graph representations
Externí odkaz:
http://arxiv.org/abs/2302.03790
Autor:
Diamant, Nathaniel, Tseng, Alex M., Chuang, Kangway V., Biancalani, Tommaso, Scalia, Gabriele
Deep graph generative modeling has proven capable of learning the distribution of complex, multi-scale structures characterizing real-world graphs. However, one of the main limitations of existing methods is their large output space, which limits gen
Externí odkaz:
http://arxiv.org/abs/2301.10857
Autor:
Atsango, Austin, Diamant, Nathaniel L., Lu, Ziqing, Biancalani, Tommaso, Scalia, Gabriele, Chuang, Kangway V.
Molecular shape and geometry dictate key biophysical recognition processes, yet many graph neural networks disregard 3D information for molecular property prediction. Here, we propose a new contrastive-learning procedure for graph neural networks, Mo
Externí odkaz:
http://arxiv.org/abs/2211.02130
Autor:
Shen, Max W., Hajiramezanali, Ehsan, Scalia, Gabriele, Tseng, Alex, Diamant, Nathaniel, Biancalani, Tommaso, Loukas, Andreas
How much explicit guidance is necessary for conditional diffusion? We consider the problem of conditional sampling using an unconditional diffusion model and limited explicit guidance (e.g., a noised classifier, or a conditional diffusion model) that
Externí odkaz:
http://arxiv.org/abs/2210.12192
Autor:
Diamant, Nathaniel, Reinertsen, Erik, Song, Steven, Aguirre, Aaron, Stultz, Collin, Batra, Puneet
Supervised machine learning applications in health care are often limited due to a scarcity of labeled training data. To mitigate this effect of small sample size, we introduce a pre-training approach, Patient Contrastive Learning of Representations
Externí odkaz:
http://arxiv.org/abs/2104.04569