Although kernel methods are widely used in many learning problems, they have poor scalability to large datasets. To address this problem, sketching and stochastic gradient methods are the most commonly used techniques to derive efficient large-scale learning algorithms. In this study, we consider solving a binary classification problem using random features and stochastic gradient descent. In recent research, an exponential convergence rate of the expected classification error under the strong low-noise condition has been shown. We extend these analyses to a random features setting, analyzing the error induced by the approximation of random features in terms of the distance between the generated hypothesis including population risk minimizers and empirical risk minimizers when using general Lipschitz loss functions, to show that an exponential convergence of the expected classification error is achieved even if random features approximation is applied. Additionally, we demonstrate that the convergence rate does not depend on the number of features and there is a significant computational benefit in using random features in classification problems because of the strong low-noise condition.

The main result of this paper is: {\bf Theorem.} Let $f:\mathbb{R}^k\rightarrow \mathbb{R}$ be a $C^{1}$ function, so that $\nabla f$ is locally Lipschitz continuous. Assume moreover that $f$ is $C^2$ near its generalised saddle points. Fix real numbers $\delta_0>0$ and $0<\alpha <1$. Then there is a smooth function $h:\mathbb{R}^k\rightarrow (0,\delta_0]$ so that the map $H:\mathbb{R}^k\rightarrow \mathbb{R}^k$ defined by $H(x)=x-h(x)\nabla f(x)$ has the following property: (i) For all $x\in \mathbb{R}^k$, we have $f(H(x)))-f(x)\leq -\alpha h(x)||\nabla f(x)||^2$. (ii) For every $x_0\in \mathbb{R}^k$, the sequence $x_{n+1}=H(x_n)$ either satisfies $\lim_{n\rightarrow\infty}||x_{n+1}-x_n||=0$ or $ \lim_{n\rightarrow\infty}||x_n||=\infty$. Each cluster point of $\{x_n\}$ is a critical point of $f$. If moreover $f$ has at most countably many critical points, then $\{x_n\}$ either converges to a critical point of $f$ or $\lim_{n\rightarrow\infty}||x_n||=\infty$. (iii) There is a set $\mathcal{E}_1\subset \mathbb{R}^k$ of Lebesgue measure $0$ so that for all $x_0\in \mathbb{R}^k\backslash \mathcal{E}_1$, the sequence $x_{n+1}=H(x_n)$, {\bf if converges}, cannot converge to a {\bf generalised} saddle point. (iv) There is a set $\mathcal{E}_2\subset \mathbb{R}^k$ of Lebesgue measure $0$ so that for all $x_0\in \mathbb{R}^k\backslash \mathcal{E}_2$, any cluster point of the sequence $x_{n+1}=H(x_n)$ is not a saddle point, and more generally cannot be an isolated generalised saddle point. Some other results are proven.

We introduce the use of a Gated Recurrent Unit (GRU) for influenza prediction at the state- and city-level in the US, and experiment with the inclusion of real-time flu-related Internet search data. We find that a GRU has lower prediction error than current state-of-the-art methods for data-driven influenza prediction at time horizons of over two weeks. In contrast with other machine learning approaches, the inclusion of real-time Internet search data does not improve GRU predictions.

Signal processing is crucial in many data science tasks. As soon as we start handling audio files, images or even biological measurements, it is useful to know techniques to process such data. In this article, I will introduce three algorithms you can use for two use cases: Principal Components Analysis (PCA) for dimensionality reduction and feature extraction, Independent Components Analysis (ICA) and Nonnegative Matrix Factorization (NMF) for source separation. All three methods have ready-to-use implementations on scikit-learn which are useful for your projects, but for the purpose of this article I will show how you can implement these methods from scratch, using only OpenCV to open and save images, and NumPy to handle matrices. I will provide code snippets throughout the article, and you can find the full code as well as the example datasets on Github.

In another post, we covered the nuts and bolts of Stochastic Gradient Descent and how to address problems like getting stuck in a local minima or a saddle point. In this post, we take a look at another problem that plagues training of neural networks, pathological curvature. While local minima and saddle points can stall our training, pathological curvature can slow down training to an extent that the machine learning practitioner might think that search has converged to a sub-optimal minma. Let us understand in depth what pathological curvature is. Consider the following loss contour.

Now that we now better understand what Artificial Intelligence means we can take a closer look at Machine Learning and Deep Learning and make a clearer distinguishment between these two. Machine Learning incorporates " classical" algorithms for various kinds of tasks such as clustering, regression or classification. Machine Learning algorithms must be trained on data. The more data you provide to your algorithm, the better it gets. The "training" part of a Machine Learning model means that this model tries to optimize along a certain dimension.

One of the fundamental problems in supervised classification and in machine learning in general, is the modelling of non-parametric invariances that exist in data. Most prior art has focused on enforcing priors in the form of invariances to parametric nuisance transformations that are expected to be present in data. Learning non-parametric invariances directly from data remains an important open problem. In this paper, we introduce a new architectural layer for convolutional networks which is capable of learning general invariances from data itself. This layer can learn invariance to non-parametric transformations and interestingly, motivates and incorporates permanent random connectomes, thereby being called Permanent Random Connectome Non-Parametric Transformation Networks (PRC-NPTN). PRC-NPTN networks are initialized with random connections (not just weights) which are a small subset of the connections in a fully connected convolution layer. Importantly, these connections in PRC-NPTNs once initialized remain permanent throughout training and testing. Permanent random connectomes make these architectures loosely more biologically plausible than many other mainstream network architectures which require highly ordered structures. We motivate randomly initialized connections as a simple method to learn invariance from data itself while invoking invariance towards multiple nuisance transformations simultaneously. We find that these randomly initialized permanent connections have positive effects on generalization, outperform much larger ConvNet baselines and the recently proposed Non-Parametric Transformation Network (NPTN) on benchmarks that enforce learning invariances from the data itself.

Time delay estimation (TDE) is a critical and challenging step in all ultrasound elastography methods. A growing number of TDE techniques require an approximate but robust and fast method to initialize solving for TDE. Herein, we present a fast method for calculating an approximate TDE between two radio frequency (RF) frames of ultrasound. Although this approximate TDE can be useful for several algorithms, we focus on GLobal Ultrasound Elastography (GLUE), which currently relies on Dynamic Programming (DP) to provide this approximate TDE. We exploit Principal Component Analysis (PCA) to find the general modes of deformation in quasi-static elastography, and therefore call our method PCA-GLUE. PCA-GLUE is a data-driven approach that learns a set of TDE principal components from a training database in real experiments. In the test phase, TDE is approximated as a weighted sum of these principal components. Our algorithm robustly estimates the weights from sparse feature matches, then passes the resulting displacement field to GLUE as initial estimates to perform a more accurate displacement estimation. PCA-GLUE is more than ten times faster than DP in estimation of the initial displacement field and yields similar results.

To overcome the high dimensionality of data, learning latent feature representations for clustering has been widely studied recently. However, it is still challenging to learn "cluster-friendly" latent representations due to the unsupervised fashion of clustering. In this paper, we propose Disentangling Latent Space Clustering (DLS-Clustering), a new clustering mechanism that directly learning cluster assignment during the disentanglement of latent spacing without constructing the "cluster-friendly" latent representation and additional clustering methods. We achieve the bidirectional mapping by enforcing an inference network (i.e. encoder) and the generator of GAN to form a deterministic encoder-decoder pair with a maximum mean discrepancy (MMD)-based regularization. We utilize a weight-sharing procedure to disentangle latent space into the one-hot discrete latent variables and the continuous latent variables. The disentangling process is actually performing the clustering operation. Eventually the one-hot discrete latent variables can be directly expressed as clusters, and the continuous latent variables represent remaining unspecified factors. Experiments on six benchmark datasets of different types demonstrate that our method outperforms existing state-of-the-art methods. We further show that the latent representations from DLS-Clustering also maintain the ability to generate diverse and high-quality images, which can support more promising application scenarios.

We introduce Negative Sampling in Semi-Supervised Learning (NS3L), a simple, fast, easy to tune algorithm for semi-supervised learning (SSL). NS3L is motivated by the success of negative sampling/contrastive estimation. We demonstrate that adding the NS3L loss to state-of-the-art SSL algorithms, such as the Virtual Adversarial Training (VAT), significantly improves upon vanilla VAT and its variant, VAT with Entropy Minimization. By adding the NS3L loss to MixMatch, the current state-of-the-art approach on semi-supervised tasks, we observe significant improvements over vanilla MixMatch. We conduct extensive experiments on the CIFAR10, CIFAR100, SVHN and STL10 benchmark datasets.