B
Brendan O'Donoghue
Researcher at Google
Publications - 48
Citations - 5642
Brendan O'Donoghue is an academic researcher from Google. The author has contributed to research in topics: Reinforcement learning & Convex optimization. The author has an hindex of 22, co-authored 48 publications receiving 4408 citations. Previous affiliations of Brendan O'Donoghue include Stanford University.
Papers
More filters
Journal ArticleDOI
Clinically applicable deep learning for diagnosis and referral in retinal disease
Jeffrey De Fauw,Joseph R. Ledsam,Bernardino Romera-Paredes,Stanislav Nikolov,Nenad Tomasev,Sam Blackwell,Harry Askham,Xavier Glorot,Brendan O'Donoghue,Daniel Visentin,George van den Driessche,Balaji Lakshminarayanan,Clemens Meyer,Faith Mackinder,Simon Bouton,Kareem Ayoub,Reena Chopra,Dominic King,Alan Karthikesalingam,Cian Hughes,Rosalind Raine,Julian Hughes,Dawn A Sim,Catherine A Egan,Adnan Tufail,Hugh Montgomery,Demis Hassabis,Geraint Rees,Trevor Back,Peng T. Khaw,Mustafa Suleyman,Julien Cornebise,Pearse A. Keane,Olaf Ronneberger +33 more
TL;DR: A novel deep learning architecture performs device-independent tissue segmentation of clinical 3D retinal images followed by separate diagnostic classification that meets or exceeds human expert clinical diagnoses of retinal disease.
Journal ArticleDOI
Fast Alternating Direction Optimization Methods
TL;DR: This paper considers accelerated variants of two common alternating direction methods: the alternating direction method of multipliers (ADMM) and the alternating minimization algorithm (AMA), of the form first proposed by Nesterov for gradient descent methods.
Journal ArticleDOI
Adaptive Restart for Accelerated Gradient Schemes
TL;DR: In this paper, a simple heuristic adaptive restart technique that can dramatically improve the convergence rate of accelerated gradient schemes is proposed. But it is not known whether the adaptive restart interval is proportional to the square root of the local condition number of the objective function.
Journal ArticleDOI
Conic Optimization via Operator Splitting and Homogeneous Self-Dual Embedding
TL;DR: In this article, the alternating directions method of multipliers is used to solve the homogeneous self-dual embedding, an equivalent feasibility problem involving finding a nonzero point in the intersection of a subspace and a cone.
Posted Content
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
TL;DR: In this paper, the authors use adversarial risk as an objective, although it cannot easily be computed exactly, and frame commonly used attacks and evaluation metrics as defining a tractable surrogate objective to the true adversarial risks.