Search Results for author:
Found 16 papers, 1 papers with code
Generalization for slowly mixing processes
A bound uniform over various loss-classes is given for data generated by stationary and phi-mixing processes, where the mixing time (the time needed to obtain approximate independence) enters the sample complexity only in an additive way.
Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces
We formalize a framework to learn the Koopman operator from finite data trajectories of the dynamical system.
Concentration inequalities under sub-Gaussian and sub-exponential conditions
We prove analogues of the popular bounded difference inequality (also called McDiarmid's inequality) for functions of independent random variables under sub-gaussian and sub-exponential conditions.
Some Hoeffding- and Bernstein-type Concentration Inequalities
We prove concentration inequalities for functions of independent random variables {under} sub-gaussian and sub-exponential conditions.
Robust Unsupervised Learning via L-Statistic Minimization
Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance.
Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning
One way to reach this goal is by modifying the data representation in order to meet certain fairness constraints.
Estimating weighted areas under the ROC curve
Exponential bounds on the estimation error are given for the plug-in estimator of weighted areas under the ROC curve.
Learning Fair and Transferable Representations
Developing learning methods which do not discriminate subgroups in the population is a central goal of algorithmic fairness.
Uniform concentration and symmetrization for weak interactions
The method to derive uniform bounds with Gaussian and Rademacher complexities is extended to the case where the sample average is replaced by a nonlinear statistic.
Empirical bounds for functions with weak interactions
We provide sharp empirical estimates of expectation, variance and normal approximation for a class of statistics whose variation in any argument does not change too much when another argument is modified.
Bounds for Vector-Valued Function Estimation
Multi-task learning and one-vs-all multi-category learning are treated as examples.
A vector-contraction inequality for Rademacher complexities
The contraction inequality for Rademacher averages is extended to Lipschitz functions with vector-valued domains, and it is also shown that in the bounding expression the Rademacher variables can be replaced by arbitrary iid symmetric and sub-gaussian variables.
The Benefit of Multitask Representation Learning
In particular, focusing on the important example of half-space learning, we derive the regime in which multitask representation learning is beneficial over independent task learning, as a function of the sample size, the number of tasks and the intrinsic data dimensionality.
A chain rule for the expected suprema of Gaussian processes
The expected supremum of a Gaussian process indexed by the image of an index set under a function class is bounded in terms of separate properties of the index set and the function class.
An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning
From concentration inequalities for the suprema of Gaussian or Rademacher processes an inequality is derived.
Sparse coding for multitask and transfer learning
We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning.
