Examples are not enough, learn to criticize! criticism for interpretability
Example-based explanations are widely used in the effort to improve the interpretability of
highly complex distributions. However, prototypes alone are rarely sufficient to represent the …
highly complex distributions. However, prototypes alone are rarely sufficient to represent the …
[HTML][HTML] MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites
Quality control of MRI is essential for excluding problematic acquisitions and avoiding bias in
subsequent image processing and analysis. Visual inspection is subjective and impractical …
subsequent image processing and analysis. Visual inspection is subjective and impractical …
Consistent binary classification with generalized performance metrics
OO Koyejo, N Natarajan… - Advances in neural …, 2014 - proceedings.neurips.cc
Performance metrics for binary classification are designed to capture tradeoffs between four
fundamental population quantities: true positives, false positives, true negatives and false …
fundamental population quantities: true positives, false positives, true negatives and false …
Consistent multilabel classification
OO Koyejo, N Natarajan… - Advances in Neural …, 2015 - proceedings.neurips.cc
Multilabel classification is rapidly developing as an important aspect of modern predictive
modeling, motivating study of its theoretical aspects. To this end, we propose a framework for …
modeling, motivating study of its theoretical aspects. To this end, we propose a framework for …
Multiclass performance metric elicitation
…, R Mehta, OO Koyejo - Advances in Neural …, 2019 - proceedings.neurips.cc
Metric Elicitation is a principled framework for selecting the performance metric that best
reflects implicit user preferences. However, available strategies have so far been limited to …
reflects implicit user preferences. However, available strategies have so far been limited to …
Sparse Bayesian structure learning with “dependent relevance determination” priors
In many problem settings, parameter vectors are not merely sparse, but dependent in such
a way that non-zero coefficients tend to cluster together. We refer to this form of dependency …
a way that non-zero coefficients tend to cluster together. We refer to this form of dependency …
On prior distributions and approximate inference for structured variables
We present a general framework for constructing prior distributions with structured variables.
The prior is defined as the information projection of a base distribution onto distributions …
The prior is defined as the information projection of a base distribution onto distributions …
Does adversarial transferability indicate knowledge transferability?
Despite the immense success that deep neural networks (DNNs) have achieved, \emph{adversarial
examples}, which are perturbed inputs that aim to mislead DNNs to make mistakes, …
examples}, which are perturbed inputs that aim to mislead DNNs to make mistakes, …
Generalized correspondence-LDA models (GC-LDA) for identifying functional regions in the brain
This paper presents Generalized Correspondence-LDA (GC-LDA), a generalization of the
Correspondence-LDA model that allows for variable spatial representations to be associated …
Correspondence-LDA model that allows for variable spatial representations to be associated …
Preference completion from partial rankings
S Gunasekar, OO Koyejo… - Advances in Neural …, 2016 - proceedings.neurips.cc
We propose a novel and efficient algorithm for the collaborative preference completion
problem, which involves jointly estimating individualized rankings for a set of entities over a …
problem, which involves jointly estimating individualized rankings for a set of entities over a …