Search
Search Funnelback University
- Refined by:
- Date: Past fortnight
31 -
40 of
51
search results for TALK:PC53 20 |u:mlg.eng.cam.ac.uk
where 0
match all words and 51
match some words.
Results that match 1 of 2 words
-
Clamping Variables and Approximate Inference Adrian WellerColumbia…
https://mlg.eng.cam.ac.uk/adrian/NeurIPS14-clamp.pdf19 Jun 2024: 00.5. 1. 00.5. 10. 10. 20. qj. v=1/Qij, W=3. qi. (b) W=3. ... 10. 20. 30. 40. max. Originalavg ClampmaxW Clampbest Clampworst ClampMpower. interaction strength W. -
Ode to an ODE Krzysztof Choromanski ∗Robotics at Google ...
https://mlg.eng.cam.ac.uk/adrian/NeurIPS20-ODEtoODE.pdf19 Jun 2024: CoRR, abs/2005.01906, 2020. [20] Emilien Dupont, Arnaud Doucet, and Yee Whye Teh. ... SIAM J. Matrix Analysis Applications, 20(2):303–353, 1998. [22] Chris Finlay, Jörn-Henrik Jacobsen, Levon Nurbekyan, and Adam M. -
Human Perceptions of Fairness in Algorithmic Decision Making: A Case…
https://mlg.eng.cam.ac.uk/adrian/WWW18-HumanPerceptions.pdf19 Jun 2024: Substance Abuse 4.84 0.08 0.07 0.10 0.24 0.07 0.68 0.26 0.22 0.20 0.07 0.284. ... Criminal Attitudes 3.63 0.22 0.12 0.16 0.51 0.09 0.40 0.20 0.11 0.09 0.03 0.157. -
One-network Adversarial Fairness
https://mlg.eng.cam.ac.uk/adrian/AAAI2019_OneNetworkAdversarialFairness.pdf19 Jun 2024: disc(P0,P1) disc(P̂0,P̂1). RadD0(Err(H)). 2+. log(1/δ). n. RadD1(Err(H)). 2+. log(1/δ). n(20). disc(P0,P1) disc(P̂0,P̂1) 2. ... of 60% of the data is reserved for training, 20%for validation and 20% for testing. -
From Parity to Preference-based Notionsof Fairness in Classification…
https://mlg.eng.cam.ac.uk/adrian/NeurIPS17-from-parity-to-preference.pdf19 Jun 2024: classifier. 6. Acc : 0.87. B0 : 0.16; B1 : 0.77B0 : 0.20; B1 : 0.85. ... Roth. Fairness in Learning: Classic and Contextual Bandits.In NIPS, 2016. [20] F. -
Uprooting and Rerooting Higher-Order GraphicalModels Mark…
https://mlg.eng.cam.ac.uk/adrian/uprooting-higher-order.pdf19 Jun 2024: Figure 2: Error in estimating log Z for random models with various pure k-potentials over 20 runs. ... In International Conference on Machine Learning(ICML), 2016. [20] A. Weller and J. -
A Unified Approach to Quantifying Algorithmic Unfairness: Measuring…
https://mlg.eng.cam.ac.uk/adrian/KDD2018_inequality_indices.pdf19 Jun 2024: pun. fair. ness. (2 β). Within-group. 0.00.20.40.60.81.0Covariance threshold. 0.06. 0.08. 0.10. ... 0.00.20.40.60.81.0Covariance threshold. 0.160. 0.165. 0.170. 0.175. Indi. vidu. alun. fair. ness. ( -
Leader Stochastic Gradient Descent for DistributedTraining of Deep…
https://mlg.eng.cam.ac.uk/adrian/NeurIPS2019_LSGD_preprint.pdf19 Jun 2024: Landscape symmetries are commonin a plethora of non-convex problems [18, 19, 20, 21, 22], including deep learning [23, 24, 25, 26]. ... 7.7 Proofs from Section 3.2. Theorem 20. Let i be the set of points (x1,. -
Working Draft 1 Accountability of AI Under the Law: ...
https://mlg.eng.cam.ac.uk/adrian/SSRN-id3064761-Dec19.pdf19 Jun 2024: 20 See House of Lords, Select Committee on Artificial Intelligence, Report of Session 2017-19, AI in the UK: Ready, Willing, and Able? ... 23 House of Lords, AI in the UK, supra note 20, 95-100. -
Discovering Interpretable Representations for Both Deep Generative…
https://mlg.eng.cam.ac.uk/adrian/ICML18-Discovering.pdf19 Jun 2024: Each model is rendered from 62viewpoints: 31 azimuth angles (with a step of 11) and 2 elevation angles (20 and 30), with a fixed distance to the chair(Dosovitskiy et al.,
Refine your results
clear all
Date
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.