Search Results for author:
Found 9 papers, 2 papers with code
Out-Of-Domain Unlabeled Data Improves Generalization
From a theoretical standpoint, we apply our framework on the classification problem of a mixture of two Gaussians in $\mathbb{R}^d$, where in addition to the $m$ independent and labeled samples from the true distribution, a set of $n$ (usually with $n\gg m$) out of domain and unlabeled samples are given as well.
Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes
Also, we theoretically show that in order to achieve this bound, it is sufficient to have $n\ge\left(K^2/\varepsilon^2\right)e^{\Omega\left(K/\mathrm{SNR}^2\right)}$ samples, where $\mathrm{SNR}$ stands for the signal-to-noise ratio.
Distributed Sparse Feature Selection in Communication-Restricted Networks
This paper aims to propose and theoretically analyze a new distributed scheme for sparse linear regression and feature selection.
Regularizing Recurrent Neural Networks via Sequence Mixup
In this paper, we extend a class of celebrated regularization techniques originally proposed for feed-forward neural networks, namely Input Mixup (Zhang et al., 2017) and Manifold Mixup (Verma et al., 2018), to the realm of Recurrent Neural Networks (RNN).
Robustness to Adversarial Perturbations in Learning from Incomplete Data
What is the role of unlabeled data in an inference problem, when the presumed underlying distribution is adversarially perturbed?
Manifold Mixup: Learning Better Representations by Interpolating Hidden States
Because the hidden states are learned, this has an important effect of encouraging the hidden states for a class to be concentrated in such a way so that interpolations within the same class or between two different classes do not intersect with the real data points from other classes.
On Statistical Learning of Simplices: Unmixing Problem Revisited
We study the sample complexity of learning a high-dimensional simplex from a set of points uniformly sampled from its interior.
Manifold Mixup: Better Representations by Interpolating Hidden States
Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples.
Ranked #18 on
Image Classification
on OmniBenchmark
Reliable Clustering of Bernoulli Mixture Models
A Bernoulli Mixture Model (BMM) is a finite mixture of random binary vectors with independent dimensions.
