Search Results for author:
Found 19 papers, 8 papers with code
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild.
Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
Corresponding samples from the real dataset consist of two distinct photographs of the same subject.
An adaptive nearest neighbor rule for classification
We introduce a variant of the $k$-nearest neighbor classifier in which $k$ is chosen adaptively for each query, rather than supplied as a parameter.
Optimal Binary Classifier Aggregation for General Losses
We address the problem of aggregating an ensemble of predictors with known loss bounds in a semi-supervised binary classification setting, to minimize prediction loss incurred on the unlabeled data.
Scalable Semi-Supervised Aggregation of Classifiers
We present and empirically evaluate an efficient algorithm that learns to aggregate the predictions of an ensemble of binary classifiers.
Optimally Combining Classifiers Using Unlabeled Data
We develop a worst-case analysis of aggregation of classifier ensembles for binary classification.
Sequential Nonparametric Testing with the Law of the Iterated Logarithm
It is novel in several ways: (a) it takes linear time and constant space to compute on the fly, (b) it has the same power guarantee as a non-sequential version of the test with the same computational constraints up to a small factor, and (c) it accesses only as many samples as are required - its stopping time adapts to the unknown difficulty of the problem.
Linking Generative Adversarial Learning and Binary Classification
In this note, we point out a basic link between generative adversarial (GA) training and binary classification -- any powerful discriminator essentially computes an (f-)divergence between real and generated samples.
Learning to Abstain from Binary Prediction
A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often.
Optimal Binary Autoencoding with Pairwise Correlations
We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits.
The Utility of Abstaining in Binary Classification
We explore the problem of binary classification in machine learning, with a twist - the classifier is allowed to abstain on any datum, professing ignorance about the true class label without committing to any prediction.
Sharp Finite-Time Iterated-Logarithm Martingale Concentration
We give concentration bounds for martingales that are uniform over finite times and extend classical Hoeffding and Bernstein inequalities.
PAC-Bayes Iterated Logarithm Bounds for Martingale Mixtures
We give tight concentration bounds for mixtures of martingales that are simultaneously uniform over (a) mixture distributions, in a PAC-Bayes sense; and (b) all finite times.
PAC-Bayes with Minimax for Confidence-Rated Transduction
We consider using an ensemble of binary classifiers for transductive prediction, when unlabeled test data are known in advance.
The Fast Convergence of Incremental PCA
We consider a situation in which we see samples in $\mathbb{R}^d$ drawn i. i. d.
Learning transport cost from subset correspondence
Optimal transport (OT) is a principled approach to align datasets, but a key challenge in applying OT is that we need to specify a transport cost function that accurately captures how the two datasets are related.
Sharp finite-sample concentration of independent variables
We show an extension of Sanov's theorem on large deviations, controlling the tail probabilities of i. i. d.
p-value peeking and estimating extrema
A pervasive issue in statistical hypothesis testing is that the reported $p$-values are biased downward by data "peeking" -- the practice of reporting only progressively extreme values of the test statistic as more data samples are collected.
