Search
Search Funnelback University
- Refined by:
- Date: Past 3 months
Did you mean economiespast |u:mlg.eng.cam.ac.uk?
21 -
40 of
45
search results for Economics test |u:mlg.eng.cam.ac.uk
where 12
match all words and 33
match some words.
Results that match 1 of 2 words
-
Evaluating and Aggregating Feature-based Model Explanations
https://mlg.eng.cam.ac.uk/adrian/IJCAI20_EvaluatingAndAggregating.pdf19 Jun 2024: For Iris [Dua and Graff, 2017], we train our modelto 96% test accuracy. ... 45). Table 2: Faithfulness µF averaged over a test set: (Zero Baseline,Training Average Baseline). -
The Geometry of Random Features Krzysztof Choromanski∗1 Mark…
https://mlg.eng.cam.ac.uk/adrian/geometry.pdf19 Jun 2024: pre-dictive distribution obtained by an exactly-trained GP, and(ii) predictive RMSE on test sets. ... Figure 8: Approximate GP regression results on Bostondataset. Reported numbers are average test RMSE, alongwith bootstrap estimates of standard error -
What Keeps a Bayesian Awake At Night? Part 2: Night Time · Cambridge…
https://mlg.eng.cam.ac.uk/blog/2021/03/31/what-keeps-a-bayesian-awake-at-night-part-2.html12 Apr 2024: Practitioners should also test the hell out of their inference schemes to gain confidence in them. ... The acid test is whether your inference scheme works on the real world data you care about, so test cases also need to replicate aspects of this -
Leader Stochastic Gradient Descent for DistributedTraining of Deep…
https://mlg.eng.cam.ac.uk/adrian/NeurIPS2019_LSGD_preprint.pdf19 Jun 2024: Test error for the center variableversus wall-clock time (original plot on the left and zoomed onthe right). ... Test loss is reported in Figure 13 in the Supplement. Finally, in Figure 6 we report theempirical results for ResNet50run on ImageNet. -
What Keeps a Bayesian Awake At Night? Part 1: Day Time · Cambridge…
https://mlg.eng.cam.ac.uk/blog/2021/03/31/what-keeps-a-bayesian-awake-at-night-part-1.html12 Apr 2024: Examples include inferring the mass of the Higgs boson ($X$) from collider data ($D$); estimating the prevalence of Covid 19 infections ($X$) from PCR test data ($D$); or reconstructing files ($X$) ... One way to view them is as unit tests that the -
Bounding the Integrality Distance ofLP Relaxations for Structured…
https://mlg.eng.cam.ac.uk/adrian/OPT2016_paper_3.pdf19 Jun 2024: Thus, the more training data we have, the better we can estimate theexpected integrality distance at test time.Remark 1. ... 9] O. Meshi, M. Mahdavi, A. Weller, and D. Sontag. Train and test tightness of LP relaxations instructured prediction. -
One-network Adversarial Fairness
https://mlg.eng.cam.ac.uk/adrian/AAAI2019_OneNetworkAdversarialFairness.pdf19 Jun 2024: To test significance, we perform a paired t-test withsignificance level at 5%. ... Totest significance, we perform a paired t-test with significance level at 5%. -
Understanding the Bethe Approximation: When and How can it ...
https://mlg.eng.cam.ac.uk/adrian/abc.pdf19 Jun 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. -
2018 Formatting Instructions for Authors Using LaTeX
https://mlg.eng.cam.ac.uk/adrian/AIES18-crowd_signals.pdf19 Jun 2024: For training our classifiers, we use 5-fold cross-validation.In each test, the original sample is partitioned into 5 sub-samples, out of which 4 are used as training data, ... The processis then repeated 5 times, with each of the 5 sub-samplesused -
Blind Justice: Fairness with Encrypted Sensitive Attributes
https://mlg.eng.cam.ac.uk/adrian/ICML18-BlindJustice.pdf19 Jun 2024: Figure 2 shows the test set accuracyover the constraint value. By design, the synthetic datasetexhibits a clear trade-off between accuracy and fairness. ... Biddle, D. Adverse impact and test validation: A practi-tioner’s guide to valid and defensible -
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.pdf19 Jun 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. -
Geometrically Coupled Monte Carlo Sampling Mark Rowland∗University of …
https://mlg.eng.cam.ac.uk/adrian/NeurIPS18-gcmc.pdf19 Jun 2024: 5.2 Variance-reduced ELBO estimation for deep generative models. In this section, we test GCMC sampling strategies on a deep generative modelling application. ... 10. Arthur Gretton, Karsten M. Borgwardt, Malte J. Rasch, Bernhard Schölkopf, and -
Unifying Orthogonal Monte Carlo Methods
https://mlg.eng.cam.ac.uk/adrian/ICML2019-unified.pdf19 Jun 2024: 3, 4. Approximating kernel matrices: We test the relative er-ror of kernel matrix estimation for the above estimators forthe Gaussian kernel (following the setting of Choromanski& Sindhwani, 2016). ... A kernel two-sample test. J. Mach. Learn.Res., -
Tightness of LP Relaxations for Almost Balanced Models Adrian ...
https://mlg.eng.cam.ac.uk/adrian/tricam.pdf19 Jun 2024: Tightness of LP Relaxations for Almost Balanced Models. Adrian Weller Mark Rowland David SontagUniversity of Cambridge University of Cambridge New York University. Abstract. Linear programming (LP) relaxations are widelyused to attempt to identify a -
THIS VERSION FIXES A TYPO IN THE STATEMENT OF ...
https://mlg.eng.cam.ac.uk/adrian/Weller15_revisit_fixed.pdf19 Jun 2024: We shall first prove sufficiency then necessity of the condi-tion. In order to test whether a derived NMRF is perfect, weuse Theorem 1, hence must check for possible odd holes -
Structured Evolution with Compact Architectures for Scalable Policy…
https://mlg.eng.cam.ac.uk/adrian/structured_icml_full.pdf19 Jun 2024: Monte Carlo gradient estimators. We test all three vari-ants of the Monte Carlo gradient estimator discussed in thepaper, namely: antithetic ES, forward finite-difference ESand vanilla ES. -
Ode to an ODE Krzysztof Choromanski ∗Robotics at Google ...
https://mlg.eng.cam.ac.uk/adrian/NeurIPS20-ODEtoODE.pdf19 Jun 2024: Table 1: Test accuracy comparison of different methods. Postfix terms refer to hidden depth for Dense,trigonometric polynomial degree for NANODE, and number of gates for HyperNet and ODEtoODE. -
Conditions Beyond Treewidth for Tightness of Higher-order LP…
https://mlg.eng.cam.ac.uk/adrian/conditions.pdf19 Jun 2024: To detect if a graphis almost balanced, and if so then to find a distinguishedvertex, may be performed efficiently (simply hold out onevariable at a time and test the remainder to -
Understanding the Bethe Approximation: When and How can it go Wrong?
https://mlg.eng.cam.ac.uk/adrian/pabc.pdf19 Jun 2024: Wolfe used for all runs, aftervalidating against smaller test set usingdual decomposition with guaranteed-approx mesh method (Weller andJebara, 2014). -
Characterizing Tightness of LP Relaxations by Forbidding Signed Minors
https://mlg.eng.cam.ac.uk/adrian/pminor.pdf19 Jun 2024: test. REFERENCES. B. Guenin. A characterization of weakly bipartite graphs. Journal of Combinatorial Theory, Series B, 83(1):112–168, 2001.
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.