Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Dieng, Adji Bousso"'
Autor:
Kannen, Nithish, Ahmad, Arif, Andreetto, Marco, Prabhakaran, Vinodkumar, Prabhu, Utsav, Dieng, Adji Bousso, Bhattacharyya, Pushpak, Dave, Shachi
Text-to-Image (T2I) models are being increasingly adopted in diverse global communities where they create visual representations of their unique cultures. Current T2I benchmarks primarily focus on faithfulness, aesthetics, and realism of generated im
Externí odkaz:
http://arxiv.org/abs/2407.06863
Autor:
Yang, Yulong, Feng, Bowen, Wang, Keqin, Leonard, Naomi, Dieng, Adji Bousso, Allen-Blanchette, Christine
From pedestrians to Kuramoto oscillators, interactions between agents govern how a multitude of dynamical systems evolve in space and time. Discovering how these agents relate to each other can improve our understanding of the often complex dynamics
Externí odkaz:
http://arxiv.org/abs/2406.14746
Autor:
Li, Kangming, Rubungo, Andre Niyongabo, Lei, Xiangyun, Persaud, Daniel, Choudhary, Kamal, DeCost, Brian, Dieng, Adji Bousso, Hattrick-Simpers, Jason
Scientific machine learning (ML) endeavors to develop generalizable models with broad applicability. However, the assessment of generalizability is often based on heuristics. Here, we demonstrate in the materials science setting that heuristics based
Externí odkaz:
http://arxiv.org/abs/2406.06489
The diffusion model has shown success in generating high-quality and diverse solutions to trajectory optimization problems. However, diffusion models with neural networks inevitably make prediction errors, which leads to constraint violations such as
Externí odkaz:
http://arxiv.org/abs/2406.00990
This paper introduces alternators, a novel family of non-Markovian dynamical models for sequences. An alternator features two neural networks: the observation trajectory network (OTN) and the feature trajectory network (FTN). The OTN and the FTN work
Externí odkaz:
http://arxiv.org/abs/2405.11848
Autor:
Nguyen, Quan, Dieng, Adji Bousso
Experimental design techniques such as active search and Bayesian optimization are widely used in the natural sciences for data collection and discovery. However, existing techniques tend to favor exploitation over exploration of the search space, wh
Externí odkaz:
http://arxiv.org/abs/2405.02449
Optimal trajectory design is computationally expensive for nonlinear and high-dimensional dynamical systems. The challenge arises from the non-convex nature of the optimization problem with multiple local optima, which usually requires a global searc
Externí odkaz:
http://arxiv.org/abs/2403.05571
Autor:
Oala, Luis, Maskey, Manil, Bat-Leah, Lilith, Parrish, Alicia, Gürel, Nezihe Merve, Kuo, Tzu-Sheng, Liu, Yang, Dror, Rotem, Brajovic, Danilo, Yao, Xiaozhe, Bartolo, Max, Rojas, William A Gaviria, Hileman, Ryan, Aliment, Rainier, Mahoney, Michael W., Risdal, Meg, Lease, Matthew, Samek, Wojciech, Dutta, Debojyoti, Northcutt, Curtis G, Coleman, Cody, Hancock, Braden, Koch, Bernard, Tadesse, Girmaw Abebe, Karlaš, Bojan, Alaa, Ahmed, Dieng, Adji Bousso, Noy, Natasha, Reddi, Vijay Janapa, Zou, James, Paritosh, Praveen, van der Schaar, Mihaela, Bollacker, Kurt, Aroyo, Lora, Zhang, Ce, Vanschoren, Joaquin, Guyon, Isabelle, Mattson, Peter
Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will adva
Externí odkaz:
http://arxiv.org/abs/2311.13028
The prediction of crystal properties plays a crucial role in the crystal design process. Current methods for predicting crystal properties focus on modeling crystal structures using graph neural networks (GNNs). Although GNNs are powerful, accurately
Externí odkaz:
http://arxiv.org/abs/2310.14029
Autor:
Pasarkar, Amey P., Dieng, Adji Bousso
Measuring diversity accurately is important for many scientific fields, including machine learning (ML), ecology, and chemistry. The Vendi Score was introduced as a generic similarity-based diversity metric that extends the Hill number of order q=1 b
Externí odkaz:
http://arxiv.org/abs/2310.12952