The goal of data attribution is to trace model predictions back to training data. Despite a long
line of work towards this goal, existing approaches to data attribution tend to force users to …

We consider supervised learning problems within the positive-definite kernel framework,
such as kernel ridge regression, kernel logistic regression or the support vector machine …

Density-based representations of atomic environments that are invariant under Euclidean
symmetries have become a widely used tool in the machine learning of interatomic …

Linear models are ubiquitous in data science, but are particularly prone to overfitting and
data memorization in high dimensions. To guarantee the privacy of training data, differential …

In reinforcement learning, state representations are used to tractably deal with large problem
spaces. State representations serve both to approximate the value function with few …

In recent years, neural network approaches have been widely adopted for machine learning
tasks, with applications in computer vision. More recently, unsupervised generative models …

Compressed Learning (CL) is a joint signal processing and machine learning framework for
inference from a signal, using a small number of measurements obtained by linear …

Kernel clustering algorithms have the ability to capture the non-linear structure inherent in
many real world data sets and thereby, achieve better clustering performance than …

Learning parameters from voluminous data can be prohibitive in terms of memory and
computational requirements. We propose a 'compressive learning'framework, where we …

Dimensionality reduction is a popular approach for dealing with high dimensional data that
leads to substantial computational savings. Random projections are a simple and effective …