Search Results for author:
Found 9 papers, 1 papers with code
Generalization Bounds for Inductive Matrix Completion in Low-noise Settings
We study inductive matrix completion (matrix completion with side information) under an i. i. d.
Beyond Smoothness: Incorporating Low-Rank Analysis into Nonparametric Density Estimation
In this paper we investigate the theoretical implications of incorporating a multi-view latent variable model, a type of low-rank model, into nonparametric density estimation.
Fine-grained Generalization Analysis of Inductive Matrix Completion
In this paper, we bridge the gap between the state-of-the-art theoretical results for matrix completion with the nuclear norm and their equivalent in \textit{inductive matrix completion}: (1) In the distribution-free setting, we prove bounds improving the previously best scaling of $O(rd^2)$ to $\widetilde{O}(d^{3/2}\sqrt{r})$, where $d$ is the dimension of the side information and $r$ is the rank.
Learning Interpretable Concept Groups in CNNs
We propose a novel training methodology -- Concept Group Learning (CGL) -- that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept.
Fine-grained Generalization Analysis of Structured Output Prediction
Existing generalization analysis implies generalization bounds with at least a square-root dependency on the cardinality $d$ of the label set, which can be vacuous in practice.
Fine-grained Generalization Analysis of Vector-valued Learning
In this paper, we initiate the generalization analysis of regularized vector-valued learning algorithms by presenting bounds with a mild dependency on the output dimension and a fast rate on the sample size.
Extreme Multi-Label Classification
General Classification
+2
Sharper Generalization Bounds for Pairwise Learning
Pairwise learning refers to learning tasks with loss functions depending on a pair of training examples, which includes ranking and metric learning as specific examples.
Orthogonal Inductive Matrix Completion
We propose orthogonal inductive matrix completion (OMIC), an interpretable approach to matrix completion based on a sum of multiple orthonormal side information terms, together with nuclear-norm regularization.
Norm-based generalisation bounds for multi-class convolutional neural networks
This holds even when formulating the bounds in terms of the $L^2$-norm of the weight matrices, where previous bounds exhibit at least a square-root dependence on the number of classes.
