Search Results for author:
Found 17 papers, 9 papers with code
Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
Estimating the ratio of two probability densities from finitely many samples, is a central task in machine learning and statistics.
SymbolicAI: A framework for logic-based approaches combining generative models and solvers
We conclude by introducing a quality measure and its empirical score for evaluating these computational graphs, and propose a benchmark that compares various state-of-the-art LLMs across a set of complex workflows.
On regularized Radon-Nikodym differentiation
We discuss the problem of estimating Radon-Nikodym derivatives.
Adaptive learning of density ratios in RKHS
Estimating the ratio of two probability densities from finitely many observations of the densities is a central problem in machine learning and statistics with applications in two-sample testing, divergence estimation, generative modeling, covariate shift adaptation, conditional density estimation, and novelty detection.
General regularization in covariate shift adaptation
Sample reweighting is one of the most widely used methods for correcting the error of least squares learning algorithms in reproducing kernel Hilbert spaces (RKHS), that is caused by future data distributions that are different from the training data distribution.
Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
Our method outperforms deep embedded validation (DEV) and importance weighted validation (IWV) on all datasets, setting a new state-of-the-art performance for solving parameter choice issues in unsupervised domain adaptation with theoretical error guarantees.
Domain Generalization by Functional Regression
The problem of domain generalization is to learn, given data from different source distributions, a model that can be expected to generalize well on new target distributions which are only seen through unlabeled samples.
Few-Shot Learning by Dimensionality Reduction in Gradient Space
We introduce SubGD, a novel few-shot learning method which is based on the recent finding that stochastic gradient descent updates tend to live in a low-dimensional parameter subspace.
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
In this survey, we provide a comprehensive systematization of poisoning attacks and defenses in machine learning, reviewing more than 100 papers published in the field in the last 15 years.
The balancing principle for parameter choice in distance-regularized domain adaptation
Our approach starts with the observation that the widely-used method of minimizing the source error, penalized by a distance measure between source and target feature representations, shares characteristics with regularized ill-posed inverse problems.
On Data Augmentation and Adversarial Risk: An Empirical Analysis
Data augmentation techniques have become standard practice in deep learning, as it has been shown to greatly improve the generalisation abilities of models.
ReLU Code Space: A Basis for Rating Network Quality Besides Accuracy
We propose a new metric space of ReLU activation codes equipped with a truncated Hamming distance which establishes an isometry between its elements and polyhedral bodies in the input space which have recently been shown to be strongly related to safety, robustness, and confidence.
Moment-Based Domain Adaptation: Learning Bounds and Algorithms
This thesis contributes to the mathematical foundation of domain adaptation as emerging field in machine learning.
On generalization in moment-based domain adaptation
Domain adaptation algorithms are designed to minimize the misclassification risk of a discriminative model for a target domain with little training data by adapting a model from a source domain with a large amount of training data.
Mixture Density Generative Adversarial Networks
Generative Adversarial Networks have surprising ability for generating sharp and realistic images, though they are known to suffer from the so-called mode collapse problem.
Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
A novel approach for unsupervised domain adaptation for neural networks is proposed.
Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
We prove that CMD is a metric on the set of probability distributions on a compact interval.
