no code implementations • 5 May 2023 • Patrick Emedom-Nnamdi, Abram L. Friesen, Bobak Shahriari, Nando de Freitas, Matt W. Hoffman
However, due to safety, ethical, and practicality constraints, this type of trial-and-error experimentation is often infeasible in many real-world domains such as healthcare and robotics.
no code implementations • 10 Oct 2022 • Lucio M. Dery, Abram L. Friesen, Nando de Freitas, Marc'Aurelio Ranzato, Yutian Chen
As machine learning permeates more industries and models become more expensive and time consuming to train, the need for efficient automated hyperparameter optimization (HPO) has never been more pressing.
no code implementations • 17 Feb 2022 • Anirudh Goyal, Abram L. Friesen, Andrea Banino, Theophane Weber, Nan Rosemary Ke, Adria Puigdomenech Badia, Arthur Guez, Mehdi Mirza, Peter C. Humphreys, Ksenia Konyushkova, Laurent SIfre, Michal Valko, Simon Osindero, Timothy Lillicrap, Nicolas Heess, Charles Blundell
In this paper we explore an alternative paradigm in which we train a network to map a dataset of past experiences to optimal behavior.
no code implementations • ICLR 2021 • Jessica B. Hamrick, Abram L. Friesen, Feryal Behbahani, Arthur Guez, Fabio Viola, Sims Witherspoon, Thomas Anthony, Lars Buesing, Petar Veličković, Théophane Weber
These results indicate where and how to utilize planning in reinforcement learning settings, and highlight a number of open questions for future MBRL research.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • NeurIPS 2020 • Yutian Chen, Abram L. Friesen, Feryal Behbahani, Arnaud Doucet, David Budden, Matthew W. Hoffman, Nando de Freitas
Many real-world problems, including multi-speaker text-to-speech synthesis, can greatly benefit from the ability to meta-learn large models with only a few task-specific components.
no code implementations • NeurIPS 2018 • Abram L. Friesen, Pedro M. Domingos
Natural scenes contain many layers of part-subpart structure, and distributions over them are thus naturally represented by stochastic image grammars, with one production per decomposition of a part.
1 code implementation • ICLR 2018 • Abram L. Friesen, Pedro Domingos
Based on this, we develop a recursive mini-batch algorithm for learning deep hard-threshold networks that includes the popular but poorly justified straight-through estimator as a special case.
no code implementations • 11 Nov 2016 • Abram L. Friesen, Pedro Domingos
We illustrate the power and generality of this approach by applying it to a new type of structured prediction problem: learning a nonconvex function that can be globally optimized in polynomial time.
no code implementations • 8 Nov 2016 • Abram L. Friesen, Pedro Domingos
Similarly to DPLL-style SAT solvers and recursive conditioning in probabilistic inference, our algorithm, RDIS, recursively sets variables so as to simplify and decompose the objective function into approximately independent sub-functions, until the remaining functions are simple enough to be optimized by standard techniques like gradient descent.
no code implementations • NeurIPS 2012 • Yanping Huang, Timothy Hanks, Mike Shadlen, Abram L. Friesen, Rajesh P. Rao
To explain this data, a second model has been proposed which assumes a time-varying influence of the prior.
no code implementations • NeurIPS 2011 • Joseph L. Austerweil, Abram L. Friesen, Thomas L. Griffiths
The object people perceive in an image can depend on its orientation relative to the scene it is in (its reference frame).