Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Ross, Jerret"'
Autor:
Melnyk, Igor, Mroueh, Youssef, Belgodere, Brian, Rigotti, Mattia, Nitsure, Apoorva, Yurochkin, Mikhail, Greenewald, Kristjan, Navratil, Jiri, Ross, Jerret
Current LLM alignment techniques use pairwise human preferences at a sample level, and as such, they do not imply an alignment on the distributional level. We propose in this paper Alignment via Optimal Transport (AOT), a novel method for distributio
Externí odkaz:
http://arxiv.org/abs/2406.05882
Autor:
Ross, Jerret, Belgodere, Brian, Hoffman, Samuel C., Chenthamarakshan, Vijil, Mroueh, Youssef, Das, Payel
Transformer-based models trained on large and general purpose datasets consisting of molecular strings have recently emerged as a powerful tool for successfully modeling various structure-property relations. Inspired by this success, we extend the pa
Externí odkaz:
http://arxiv.org/abs/2405.04912
Autor:
Nitsure, Apoorva, Mroueh, Youssef, Rigotti, Mattia, Greenewald, Kristjan, Belgodere, Brian, Yurochkin, Mikhail, Navratil, Jiri, Melnyk, Igor, Ross, Jerret
We propose a distributional framework for benchmarking socio-technical risks of foundation models with quantified statistical significance. Our approach hinges on a new statistical relative testing based on first and second order stochastic dominance
Externí odkaz:
http://arxiv.org/abs/2310.07132
Autor:
Belgodere, Brian, Dognin, Pierre, Ivankay, Adam, Melnyk, Igor, Mroueh, Youssef, Mojsilovic, Aleksandra, Navratil, Jiri, Nitsure, Apoorva, Padhi, Inkit, Rigotti, Mattia, Ross, Jerret, Schiff, Yair, Vedpathak, Radhika, Young, Richard A.
Real-world data often exhibits bias, imbalance, and privacy risks. Synthetic datasets have emerged to address these issues. This paradigm relies on generative AI models to generate unbiased, privacy-preserving data while maintaining fidelity to the o
Externí odkaz:
http://arxiv.org/abs/2304.10819
Autor:
Ross, Jerret, Belgodere, Brian, Chenthamarakshan, Vijil, Padhi, Inkit, Mroueh, Youssef, Das, Payel
Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Various supervised machine learning models have demonstrated promising performance, but the vast
Externí odkaz:
http://arxiv.org/abs/2106.09553
Autor:
Padhi, Inkit, Schiff, Yair, Melnyk, Igor, Rigotti, Mattia, Mroueh, Youssef, Dognin, Pierre, Ross, Jerret, Nair, Ravi, Altman, Erik
Tabular datasets are ubiquitous in data science applications. Given their importance, it seems natural to apply state-of-the-art deep learning algorithms in order to fully unlock their potential. Here we propose neural network models that represent t
Externí odkaz:
http://arxiv.org/abs/2011.01843
Recently, the task of image generation has attracted much attention. In particular, the recent empirical successes of the Markov Chain Monte Carlo (MCMC) technique of Langevin Dynamics have prompted a number of theoretical advances; despite this, sev
Externí odkaz:
http://arxiv.org/abs/2006.11166
Autor:
Liu, Mingrui, Mroueh, Youssef, Ross, Jerret, Zhang, Wei, Cui, Xiaodong, Das, Payel, Yang, Tianbao
Adaptive gradient algorithms perform gradient-based updates using the history of gradients and are ubiquitous in training deep neural networks. While adaptive gradient methods theory is well understood for minimization problems, the underlying factor
Externí odkaz:
http://arxiv.org/abs/1912.11940
Autor:
Liu, Mingrui, Zhang, Wei, Mroueh, Youssef, Cui, Xiaodong, Ross, Jerret, Yang, Tianbao, Das, Payel
Generative Adversarial Networks (GANs) are a powerful class of generative models in the deep learning community. Current practice on large-scale GAN training utilizes large models and distributed large-batch training strategies, and is implemented on
Externí odkaz:
http://arxiv.org/abs/1910.12999
In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters. Optimal transport metrics, such as the Wasserstein distance, allow incorporating semantic side information such
Externí odkaz:
http://arxiv.org/abs/1902.04999