Fine-grained theoretical analysis of federated zeroth-order optimization
Federated zeroth-order optimization (FedZO) algorithm enjoys the advantages of both zeroth-
order optimization and federated learning, and has shown exceptional performance on …
order optimization and federated learning, and has shown exceptional performance on …
Self-interpretable model with transformation equivariant interpretation
With the proliferation of machine learning applications in the real world, the demand for
explaining machine learning predictions continues to grow especially in high-stakes fields …
explaining machine learning predictions continues to grow especially in high-stakes fields …
Sparse modal additive model
Sparse additive models have been successfully applied to high-dimensional data analysis
due to the flexibility and interpretability of their representation. However, the existing …
due to the flexibility and interpretability of their representation. However, the existing …
Generalization bounds for sparse random feature expansions
Random feature methods have been successful in various machine learning tasks, are easy
to compute, and come with theoretical accuracy bounds. They serve as an alternative …
to compute, and come with theoretical accuracy bounds. They serve as an alternative …
On the stability and generalization of triplet learning
Triplet learning, ie learning from triplet data, has attracted much attention in computer vision
tasks with an extremely large number of categories, eg, face recognition and person re …
tasks with an extremely large number of categories, eg, face recognition and person re …
How to open a black box classifier for tabular data
A lack of transparency in machine learning models can limit their application. We show that
analysis of variance (ANOVA) methods extract interpretable predictive models from them …
analysis of variance (ANOVA) methods extract interpretable predictive models from them …
Sparse shrunk additive models
Most existing feature selection methods in literature are linear models, so that the nonlinear
relations between features and response variables are not considered. Meanwhile, in these …
relations between features and response variables are not considered. Meanwhile, in these …
Multi-task additive models for robust estimation and automatic structure discovery
Additive models have attracted much attention for high-dimensional regression estimation
and variable selection. However, the existing models are usually limited to the single-task …
and variable selection. However, the existing models are usually limited to the single-task …
A new large-scale learning algorithm for generalized additive models
Additive model plays an important role in machine learning due to its flexibility and
interpretability in the prediction function. However, solving large-scale additive models is a …
interpretability in the prediction function. However, solving large-scale additive models is a …
Compressed multi-scale feature fusion network for single image super-resolution
Recently, deep neural networks have made significant breakthroughs in the image super-
resolution (SR) field. Most deep learning-based image SR methods learn an end-to-end …
resolution (SR) field. Most deep learning-based image SR methods learn an end-to-end …