Search Results for author:
Found 13 papers, 3 papers with code
Measures of distortion for machine learning
We can show both in theory and in experiments that it satisfies all desirable properties and is a better candidate to evaluate distortion in the context of machine learning.
LARGE SCALE REPRESENTATION LEARNING FROM TRIPLET COMPARISONS
This problem has been studied in a sub-community of machine learning by the name "Ordinal Embedding".
On the optimality of kernels for high-dimensional clustering
This is the first work that provides such optimality guarantees for the kernel k-means as well as its convex relaxation.
Insights into Ordinal Embedding Algorithms: A Systematic Evaluation
However, there does not exist a fair and thorough assessment of these embedding methods and therefore several key questions remain unanswered: Which algorithms perform better when the embedding dimension is constrained or few triplet comparisons are available?
Graphon based Clustering and Testing of Networks: Algorithms and Theory
Using the proposed graph distance, we present two clustering algorithms and show that they achieve state-of-the-art results.
Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models
Despite the ubiquity of kernel-based clustering, surprisingly few statistical guarantees exist beyond settings that consider strong structural assumptions on the data generation process.
Causal Forecasting:Generalization Bounds for Autoregressive Models
Under causal sufficiency, the problem of causal generalization amounts to learning under covariate shifts, albeit with additional structure (restriction to interventional distributions under the VAR model).
Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks
While VC Dimension does result in trivial generalisation error bounds in this setting as well, we show that transductive Rademacher complexity can explain the generalisation properties of graph convolutional networks for stochastic block models.
Interpolation and Regularization for Causal Learning
If the confounding strength is negative, causal learning requires weaker regularization than statistical learning, interpolators can be optimal, and the optimal regularization can even be negative.
A Consistent Estimator for Confounding Strength
Regression on observational data can fail to capture a causal relationship in the presence of unobserved confounding.
Reinterpreting causal discovery as the task of predicting unobserved joint statistics
Here, causal discovery becomes more modest and better accessible to empirical tests than usual: rather than trying to find a causal hypothesis that is `true' a causal hypothesis is {\it useful} whenever it correctly predicts statistical properties of unobserved joint distributions.
Self-Compatibility: Evaluating Causal Discovery without Ground Truth
In this work, we propose a novel method for falsifying the output of a causal discovery algorithm in the absence of ground truth.
Explaining Kernel Clustering via Decision Trees
Despite the growing popularity of explainable and interpretable machine learning, there is still surprisingly limited work on inherently interpretable clustering methods.
