Zobrazeno 1 - 10
of 32 664
pro vyhledávání: '"A Lobato"'
Recently, there has been an increasing interest in performing post-hoc uncertainty estimation about the predictions of pre-trained deep neural networks (DNNs). Given a pre-trained DNN via back-propagation, these methods enhance the original network b
Externí odkaz:
http://arxiv.org/abs/2412.04177
Autor:
Zhao, Jingyi, Ou, Yuxuan, Tripp, Austin, Rasoulianboroujeni, Morteza, Hernández-Lobato, José Miguel
Ionizable lipids are essential in developing lipid nanoparticles (LNPs) for effective messenger RNA (mRNA) delivery. While traditional methods for designing new ionizable lipids are typically time-consuming, deep generative models have emerged as a p
Externí odkaz:
http://arxiv.org/abs/2412.00807
Autor:
Ou, Yuxuan, Zhao, Jingyi, Tripp, Austin, Rasoulianboroujeni, Morteza, Hernández-Lobato, José Miguel
Lipid nanoparticles (LNPs) are vital in modern biomedicine, enabling the effective delivery of mRNA for vaccines and therapies by protecting it from rapid degradation. Among the components of LNPs, ionizable lipids play a key role in RNA protection a
Externí odkaz:
http://arxiv.org/abs/2412.00928
Bayesian optimization (BO) methods based on information theory have obtained state-of-the-art results in several tasks. These techniques heavily rely on the Kullback-Leibler (KL) divergence to compute the acquisition function. In this work, we introd
Externí odkaz:
http://arxiv.org/abs/2411.16586
Autor:
Cazenille, Leo, Toquebiau, Maxime, Lobato-Dauzier, Nicolas, Loi, Alessia, Macabre, Loona, Aubert-Kato, Nathanael, Genot, Anthony, Bredeche, Nicolas
This paper investigates the role of communication in improving coordination within robot swarms, focusing on a paradigm where learning and execution occur simultaneously in a decentralized manner. We highlight the role communication can play in addre
Externí odkaz:
http://arxiv.org/abs/2411.11616
Autor:
Shysheya, Aliaksandra, Diaconu, Cristiana, Bergamin, Federico, Perdikaris, Paris, Hernández-Lobato, José Miguel, Turner, Richard E., Mathieu, Emile
Modelling partial differential equations (PDEs) is of crucial importance in science and engineering, and it includes tasks ranging from forecasting to inverse problems, such as data assimilation. However, most previous numerical and machine learning
Externí odkaz:
http://arxiv.org/abs/2410.16415
Training generative models to sample from unnormalized density functions is an important and challenging task in machine learning. Traditional training methods often rely on the reverse Kullback-Leibler (KL) divergence due to its tractability. Howeve
Externí odkaz:
http://arxiv.org/abs/2410.12456
Autor:
Fromer, Jenna, Wang, Runzhong, Manjrekar, Mrunali, Tripp, Austin, Hernández-Lobato, José Miguel, Coley, Connor W.
Batched Bayesian optimization (BO) can accelerate molecular design by efficiently identifying top-performing compounds from a large chemical library. Existing acquisition strategies for batch design in BO aim to balance exploration and exploitation.
Externí odkaz:
http://arxiv.org/abs/2410.06333
Current methods for compressing neural network weights, such as decomposition, pruning, quantization, and channel simulation, often overlook the inherent symmetries within these networks and thus waste bits on encoding redundant information. In this
Externí odkaz:
http://arxiv.org/abs/2410.01309
Autor:
Sabanza-Gil, Víctor, Barbano, Riccardo, Gutiérrez, Daniel Pacheco, Luterbacher, Jeremy S., Hernández-Lobato, José Miguel, Schwaller, Philippe, Roch, Loïc
Multi-fidelity Bayesian Optimization (MFBO) is a promising framework to speed up materials and molecular discovery as sources of information of different accuracies are at hand at increasing cost. Despite its potential use in chemical tasks, there is
Externí odkaz:
http://arxiv.org/abs/2410.00544