Search
Search Funnelback University
- Refined by:
- Date: 2024
1 -
20 of
23
search results for Economics middle test |u:mlg.eng.cam.ac.uk
where 2
match all words and 21
match some words.
Fully-matching results
-
Orthogonal Estimation of Wasserstein Distances Mark Rowland∗1 Jiri…
https://mlg.eng.cam.ac.uk/adrian/AISTATS19-slicedwasserstein.pdf16 Jul 2024: physics (Jordan et al., 1998) and economics(Galichon, 2016), and are increasingly used in machinelearning (Arjovsky et al., 2017; Gulrajani et al., 2017;Peyré and Cuturi, 2018). ... 5.1 Distance estimation. We begin with a test bed of small-scale -
Methods for Inference in Graphical Models
https://mlg.eng.cam.ac.uk/adrian/phd_FINAL.pdf16 Jul 2024: 91. 7.6.2 Test sets. 93. 7.7 Conclusions. 95. 8 Clamping Variables and Approximate Inference 96. ... 7.2 Log partition function and approximations for ABC triangle. 86. 7.3 Bethe free energy ESB with stationary points highlighted (top), then entropy SB Results that match 2 of 3 words
-
What should we, Humanity, do about Climate Change?
https://mlg.eng.cam.ac.uk/carl/climate/do.html14 Jul 2024: Note, that both the low emitters and the large emitters will feel an economic pressure to emit less. ... Next year's price is the median (the middle value) of all the price votes. -
Bayesian Deep Learning via Subnetwork Inference · Cambridge MLG Blog
https://mlg.eng.cam.ac.uk/blog/2021/07/21/subnetwork-inference.html12 Apr 2024: Figure 9: Results on the rotated MNIST benchmark, showing the mean $pm$ std of the test error (top) and log-likelihood (bottom) across three different seeds. ... methods. Figure 10: Results on the corrupted CIFAR-10 benchmark, showing the mean $pm$ std -
Discovering Interpretable Representations for Both Deep Generative…
https://mlg.eng.cam.ac.uk/adrian/ICML18-Discovering.pdf16 Jul 2024: Significant re-sults are identified using a paired t-test with p = 0.05. ... The SVHN dataset contains 73,257training digits (instances) and 26,032 test digits. -
Who owns the atmosphere?
https://mlg.eng.cam.ac.uk/carl/climate/eacc.html14 Jul 2024: Such a scheme would immediately put economic pressure on all users to reduce their utilisation of the common atmospheric resource. ... In the following years, low per capita emitters will gain immediate economic benefit from joining. -
Natural-Gradient Variational Inference 2: ImageNet-scale · Cambridge…
https://mlg.eng.cam.ac.uk/blog/2021/11/24/ngvi-bnns-part-2.html12 Apr 2024: Top middle plot: VOGN is about twice as slow (total time) compared to SGD and Adam. ... Reducing the prior precision $delta$ results in higher validation accuracy, but also a larger train-test gap, corresponding to more overfitting. -
TibGM: A Transferable and Information-Based Graphical Model Approach…
https://mlg.eng.cam.ac.uk/adrian/ICML2019-TibGM.pdf16 Jul 2024: Thick linesin the middle of each curve indicate the average performance,while the standard deviations over 50 random seeds are shownby the shaded regions. ... Significance is tested usingthe same paired t-test described above. TibGM ProMP -
From Parity to Preference-based Notionsof Fairness in Classification…
https://mlg.eng.cam.ac.uk/adrian/NeurIPS17-from-parity-to-preference.pdf16 Jul 2024: In this paper, we draw inspiration from the fair-division and envy-freeness literature in economics and game theory and proposepreference-based notions of fairness—given the choice between various sets ... Finally,we train the five classifiers -
https://mlg.eng.cam.ac.uk/blog/feed.xml
https://mlg.eng.cam.ac.uk/blog/feed.xml12 Apr 2024: middle-ground between expressivity and efficient determinant estimation. -
Adrian Weller
https://mlg.eng.cam.ac.uk/adrian/16 Jul 2024: Adrian serves on the boards of several organizations. He is a member of the World Economic Forum Global Future Council on the Future of AI, and is co-director of the ... Train and Test Tightness of LP Relaxations in Structured Prediction. -
Transparency: Motivations and Challenges? Adrian…
https://mlg.eng.cam.ac.uk/adrian/transparency.pdf16 Jul 2024: truth.”. Defining criteria and tests for practical faithfulness are important open pro-blems. ... 53. Prat, A.: The wrong kind of transparency. American Economic Review 95(3),862–877 (2005). -
Exploring Properties of the Deep Image Prior Andreas…
https://mlg.eng.cam.ac.uk/adrian/NeurIPS_2019_DIP7.pdf16 Jul 2024: To test the nature of these outputs we introduce a novel saliencymap approach, termed MIG-SG. ... To test this, we evaluated the sensitivity of DIP to changes innetwork architecture. -
Understanding the Bethe Approximation: When and How can it ...
https://mlg.eng.cam.ac.uk/adrian/abc.pdf16 Jul 2024: Ex-periments are described in 6, where we examine test cases.Conclusions are discussed in 7. ... Given this performance, we used FW for all Bethe opti-mizations on the test cases. -
The Geometry of Random Features Krzysztof Choromanski∗1 Mark…
https://mlg.eng.cam.ac.uk/adrian/geometry.pdf16 Jul 2024: On the left: Gaussian kernel, inthe middle: kernel defined by the PD function φ(‖z‖) =(1 ‖z‖2. ... pre-dictive distribution obtained by an exactly-trained GP, and(ii) predictive RMSE on test sets. -
The Case for Process Fairness in Learning:Feature Selection for ...
https://mlg.eng.cam.ac.uk/adrian/grgic.pdf16 Jul 2024: 3. Prior literature in social, economic, legal, and political sciences distinguishing between directdiscrimination and indirect discrimination makes similar observations as we do in this paper. ... For each of the classifiers, we also compute -
A Unified Approach to Quantifying Algorithmic Unfairness: Measuring…
https://mlg.eng.cam.ac.uk/adrian/KDD2018_inequality_indices.pdf16 Jul 2024: In this paper, we propose to quantify unfairness using inequal-ity indices that have been extensively studied in economics andsocial welfare [3, 10, 19]. ... For all experiments, we repeatedly split the data into 70%-30%train-test sets 10 times and -
Human Perceptions of Fairness in Algorithmic Decision Making: A Case…
https://mlg.eng.cam.ac.uk/adrian/WWW18-HumanPerceptions.pdf16 Jul 2024: We draw these latentproperties from the existing literature in social-economic-political-moral sciences, philosophy, and the law, as detailed below.I. ... To evaluate the model, we randomly split thedata into 50%/50% train/test folds five times, and -
You Shouldn’t Trust Me: Learning Models WhichConceal Unfairness From…
https://mlg.eng.cam.ac.uk/adrian/ECAI20-You_Shouldn%E2%80%99t_Trust_Me.pdf16 Jul 2024: Each histogramrepresents the ranking across the test set assigned by the designated feature importance method. ... These results suggest that ourattack is successful in generalising across unseen test points. -
Beyond Distributive Fairness in Algorithmic Decision Making: Feature…
https://mlg.eng.cam.ac.uk/adrian/AAAI18-BeyondDistributiveFairness.pdf16 Jul 2024: 2011). For all reported results, we ran-domly split the data into 50%/50% train/test folds 5 times and re-port average statistics. ... In Univer-sity of Michigan Law & Economics Research Paper No. 16012.Ahmed, F.; Dickerson, J.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.