David Scott Krueger
机构: University Assistant Professor, University of Cambridge
每年引用次数
引用次数
引用: 7,813
H-指数: 25
I10-指数 : 31
出版物: 62
Regularizing RNNs by Stabilizing Activations
Roland Memisevic , David Krueger
arXiv: Neural and Evolutionary Computing
78
2015
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
David Krueger , Tegan Maharaj , János Kramár , Mohammad Pezeshki
arXiv: Neural and Evolutionary Computing
337
2016
2016
Bayesian Hypernetworks
Alexandre Lacoste , Aaron Courville , David Krueger , Ryan Turner
arXiv: Machine Learning
123
2017
Nested LSTMs.
Joel Ruben Antony Moniz , David Krueger ,
arXiv: Computation and Language
63
2018
Neural Autoregressive Flows
Alexandre Lacoste , Aaron Courville , David Krueger , Chin-Wei Huang
arXiv: Learning
383
2018
Scalable agent alignment via reward modeling: a research direction.
Tom Everitt , Shane Legg , Jan Leike , David Krueger
arXiv: Learning
139
2018
A closer look at memorization in deep networks
Yoshua Bengio , Devansh Arpit , Asja Fischer , Stanisław Jastrzębski
international conference on machine learning 70 233 -242
1,274
2017
NICE: Non-linear Independent Components Estimation
Yoshua Bengio , Laurent Dinh , David Krueger
international conference on learning representations
1,542
2014
Reserve Output Units for Deep Open-Set Learning
David Krueger , Tegan Maharaj
2018
Out-of-Distribution Generalization via Risk Extrapolation (REx)
Jonathan Binas , Aaron Courville , David Krueger , Amy Zhang
arXiv: Learning
354
2021
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
Miles Brundage , Shahar Avin , Jasmine Wang , Haydn Belfield
arXiv: Computers and Society
189
2020
AI Research Considerations for Human Existential Safety (ARCHES)
David Krueger , Andrew Critch
arXiv: Computers and Society
23
2020
Goal misgeneralization in deep reinforcement learning
Lauro Langosco , Jack Koch , Lee Sharkey , Jacob Pfau
Smpte Journal 12004 -12019
7
2022
Assistance with large language models
Dmitrii Krasheninnikov , Egor Krasheninnikov , David Krueger
Smpte Journal
1
2022
Broken neural scaling laws
Ethan Caballero , Kshitij Gupta , Irina Rish , David Krueger
arXiv preprint arXiv:2210.14891
2
2022
Harms from Increasingly Agentic Algorithmic Systems
Alan Chan , Rebecca Salganik , Alva Markelius , Chris Pang
Smpte Journal 651 -666
2023
On The Fragility of Learned Reward Functions
Lev McKinney , Yawen Duan , David Krueger , Adam Gleave
arXiv preprint arXiv:2301.03652
2023
Domain Generalization for Robust Model-Based Offline Reinforcement Learning
Alan Clark , Shoaib Ahmed Siddiqui , Robert Kirk , Usman Anwar
arXiv preprint arXiv:2211.14827
2022
Metadata archaeology: Unearthing data subsets by leveraging training dynamics
Shoaib Ahmed Siddiqui , Nitarshan Rajkumar , Tegan Maharaj , David Krueger
arXiv preprint arXiv:2209.10015
2022
Tegan Maharaj Yoshua Bengio Aaron Courville Nicolas Ballas Alexandre Lacoste Stanisław Jastrzębski Devansh Arpit Asja Fischer Max Kanwal Emmanuel Bengio Jan Leike Dmitrii Krasheninnikov Laurent Dinh Simon Lacoste-Julien Ethan Caballero Chin-Wei Huang Lauro Langosco Jörn-Henrik Jacobsen Amy Zhang Jonathan Binas