J
Jerret Ross
Researcher at IBM
Publications - 11
Citations - 162
Jerret Ross is an academic researcher from IBM. The author has contributed to research in topics: Language model & Closed captioning. The author has an hindex of 6, co-authored 10 publications receiving 86 citations.
Papers
More filters
Proceedings Article
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
TL;DR: This is the first work for establishing adaptive complexity in non-convexnon-concave min-max optimization and shows that indeed adaptive gradient algorithms outperform their non-adaptive counterparts in GAN training.
Posted Content
Tabular Transformers for Modeling Multivariate Time Series
Inkit Padhi,Yair Schiff,Igor Melnyk,Mattia Rigotti,Youssef Mroueh,Pierre L. Dognin,Jerret Ross,Ravi Nair,Erik R. Altman +8 more
TL;DR: Two architectures for tabular time series are proposed: one for learning representations that 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.
Posted Content
Improved Image Captioning with Adversarial Semantic Alignment.
TL;DR: A new conditional GAN for image captioning is proposed that enforces semantic alignment between images and captions through a co-attentive discriminator and a context-aware LSTM sequence generator and a new semantic score with strong correlation to human judgement is introduced.
Proceedings Article
Wasserstein barycenter model ensembling
Pierre L. Dognin,Igor Melnyk,Youssef Mroueh,Jerret Ross,Cicero Nogueira dos Santos,Tom Sercu +5 more
TL;DR: This paper proposes to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters to find the consensus between models, and shows applications of W. baryCenters in attribute-based classification, multilab learning and image captioning generation.
Posted Content
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets.
TL;DR: In this article, an adaptive variant of Optimistic Stochastic Gradient (OSG) was proposed to solve non-convex nonconcave min-max problems.