no code implementations • 28 May 2025 • Youssef Mroueh, Nicolas Dupuis, Brian Belgodere, Apoorva Nitsure, Mattia Rigotti, Kristjan Greenewald, Jiri Navratil, Jerret Ross, Jesus Rios
We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes.
no code implementations • 9 Jun 2024 • Igor Melnyk, Youssef Mroueh, Brian Belgodere, Mattia Rigotti, Apoorva Nitsure, Mikhail Yurochkin, Kristjan Greenewald, Jiri Navratil, Jerret Ross
Thanks to the one-dimensional nature of the resulting optimal transport problem and the convexity of the cost, it has a closed-form solution via sorting on empirical measures.
no code implementations • 4 Apr 2024 • Jerret Ross, Brian Belgodere, Samuel C. Hoffman, Vijil Chenthamarakshan, Jiri Navratil, Youssef Mroueh, Payel Das
Our analyses reveal that training data memorization and novelty in generations are impacted by the quality and scale of the training data; duplication bias in training data can enhance memorization at the cost of lowering novelty.
no code implementations • 11 Oct 2023 • Apoorva Nitsure, Youssef Mroueh, Mattia Rigotti, Kristjan Greenewald, Brian Belgodere, Mikhail Yurochkin, Jiri Navratil, Igor Melnyk, Jerret Ross
Using this framework, we formally develop a risk-aware approach for foundation model selection given guardrails quantified by specified metrics.
no code implementations • 21 Apr 2023 • Brian Belgodere, Pierre Dognin, Adam Ivankay, Igor Melnyk, Youssef Mroueh, Aleksandra Mojsilovic, Jiri Navratil, Apoorva Nitsure, Inkit Padhi, Mattia Rigotti, Jerret Ross, Yair Schiff, Radhika Vedpathak, Richard A. Young
We introduce a holistic auditing framework that comprehensively evaluates synthetic datasets and AI models.
1 code implementation • 17 Jun 2021 • Jerret Ross, Brian Belgodere, Vijil Chenthamarakshan, Inkit Padhi, Youssef Mroueh, Payel Das
Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design.
1 code implementation • 3 Nov 2020 • Inkit Padhi, Yair Schiff, Igor Melnyk, Mattia Rigotti, Youssef Mroueh, Pierre Dognin, Jerret Ross, Ravi Nair, Erik Altman
This results in two architectures for tabular time series: one for learning representations that is analogous to BERT and can be pre-trained end-to-end and used in downstream tasks, and one that is akin to GPT and can be used for generation of realistic synthetic tabular sequences.
no code implementations • 19 Jun 2020 • Adam Block, Youssef Mroueh, Alexander Rakhlin, Jerret Ross
Recently, the task of image generation has attracted much attention.
no code implementations • ICLR 2020 • Mingrui Liu, Youssef Mroueh, Jerret Ross, Wei zhang, Xiaodong Cui, Payel Das, Tianbao Yang
Then we propose an adaptive variant of OSG named Optimistic Adagrad (OAdagrad) and reveal an \emph{improved} adaptive complexity $O\left(\epsilon^{-\frac{2}{1-\alpha}}\right)$, where $\alpha$ characterizes the growth rate of the cumulative stochastic gradient and $0\leq \alpha\leq 1/2$.
no code implementations • NeurIPS 2020 • Mingrui Liu, Wei zhang, Youssef Mroueh, Xiaodong Cui, Jerret Ross, Tianbao Yang, Payel Das
Despite recent progress on decentralized algorithms for training deep neural networks, it remains unclear whether it is possible to train GANs in a decentralized manner.
1 code implementation • 13 Feb 2019 • Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Cicero dos Santos, Tom Sercu
In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters.