63.6k citations
- Google (United States)US20 papers
- University of WaterlooCA7 papers
- Google DeepMind (United Kingdom)GB4 papers
- University of AlbertaCA4 papers
- Google (Switzerland)CH3 papers
- Google (United Kingdom)GB3 papers
- McGill UniversityCA3 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Duke UniversityUS2 papers
- École PolytechniqueFR2 papers
- Harvard UniversityUS2 papers
- Institut national de recherche en sciences et technologies du numériqueFR2 papers
11 papers · 1 filter
Nteasee: Understanding Needs in AI for Health in Africa -- A Mixed-Methods Study of Expert and General Population Perspectives
Mercy Nyamewaa Asiedu, Iskandar Haykel, Awa Dieng +7
Artificial Intelligence (AI) for health has the potential to significantly change and improve healthcare. However in most African countries, identifying culturally and contextually…
Globalizing Fairness Attributes in Machine Learning: A Case Study on Health in Africa
Mercy Nyamewaa Asiedu, Awa Dieng, Abigail Oppong +3
With growing machine learning (ML) applications in healthcare, there have been calls for fairness in ML to understand and mitigate ethical concerns these systems may pose. Fairness…
Retrieval-Enhanced Machine Learning
Hamed Zamani, Fernando Diaz, Mostafa Dehghani +2
Although information access systems have long supported people in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to inc…
Leveraging Non-uniformity in First-order Non-convex Optimization
Jincheng Mei, Yue Gao, Bo Dai +2
Classical global convergence results for first-order methods rely on uniform smoothness and the Łojasiewicz inequality. Motivated by properties of objective functions that arise in…
Variance Penalized On-Policy and Off-Policy Actor-Critic
Arushi Jain, Gandharv Patil, Ayush Jain +2
Reinforcement learning algorithms are typically geared towards optimizing the expected return of an agent. However, in many practical applications, low variance in the return is de…
Perfect density models cannot guarantee anomaly detection
Charline Le Lan, Laurent Dinh
Thanks to the tractability of their likelihood, several deep generative models show promise for seemingly straightforward but important applications like anomaly detection, uncerta…