Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Husain, Hisham"'
Autor:
Husain, Hisham, Monteil, Julien
Latent variable collaborative filtering methods have been a standard approach to modelling user-click interactions due to their simplicity and effectiveness. However, there is limited work on analyzing the mathematical properties of these methods in
Externí odkaz:
http://arxiv.org/abs/2410.03064
The ubiquity of missing data has sparked considerable attention and focus on tabular data imputation methods. Diffusion models, recognized as the cutting-edge technique for data generation, demonstrate significant potential in tabular data imputation
Externí odkaz:
http://arxiv.org/abs/2407.18013
Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. The predominant approach is to alter the supervised learning pipeline by augmenting typical loss functions, letting model rejection i
Externí odkaz:
http://arxiv.org/abs/2405.18686
Semi-supervised learning is a critical tool in reducing machine learning's dependence on labeled data. It has been successfully applied to structured data, such as images and natural language, by exploiting the inherent spatial and semantic structure
Externí odkaz:
http://arxiv.org/abs/2206.05880
Autor:
Mashrur Ahmed Yafi, Md. Hasibul Husain Hisham, Francisco Grisanti, James F. Martin, Atif Rahman, Md. Abul Hassan Samee
Publikováno v:
Genome Biology, Vol 25, Iss 1, Pp 1-17 (2024)
Abstract A critical challenge of single-cell spatial transcriptomics (sc-ST) technologies is their panel size. Being based on fluorescence in situ hybridization, they are typically limited to panels of about a thousand genes. This constrains research
Externí odkaz:
https://doaj.org/article/5a6db1aa711c4b0fa1cb3075008b7125
The study of robustness has received much attention due to its inevitability in data-driven settings where many systems face uncertainty. One such example of concern is Bayesian Optimization (BO), where uncertainty is multi-faceted, yet there only ex
Externí odkaz:
http://arxiv.org/abs/2203.02128
Autor:
Husain, Hisham, Balle, Borja
Robustness of deep neural networks against adversarial perturbations is a pressing concern motivated by recent findings showing the pervasive nature of such vulnerabilities. One method of characterizing the robustness of a neural network model is thr
Externí odkaz:
http://arxiv.org/abs/2102.08093
Entropic regularization of policies in Reinforcement Learning (RL) is a commonly used heuristic to ensure that the learned policy explores the state-space sufficiently before overfitting to a local optimal policy. The primary motivation for using ent
Externí odkaz:
http://arxiv.org/abs/2101.07012
We introduce a boosting algorithm to pre-process data for fairness. Starting from an initial fair but inaccurate distribution, our approach shifts towards better data fitting while still ensuring a minimal fairness guarantee. To do so, it learns the
Externí odkaz:
http://arxiv.org/abs/2012.00188
Continual Learning (CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks. Designing CL algorithms that perform reliably and avoid so-called catastrophic forgetting has proven a persistent challe
Externí odkaz:
http://arxiv.org/abs/2006.05188