‎let $x=left(‎ ‎begin{array}{llll}‎ ‎ x_1 & ldots & x_{n-1}& x_n‎ ‎ x_2& ldots & x_n & x_{n+1}‎ ‎end{array}right)$ be the hankel matrix of size $2times n$ and let $g$ be a closed graph on the vertex set $[n].$ we study the binomial ideal $i_gsubset k[x_1,ldots,x_{n+1}]$ which is generated by all the $2$-minors of $x$ which correspond to the edges of $g.$ we show that...

Abstract A common challenge encountered when using Deep Neural Network models for automatic ICD coding is their potential inability to effectively handle unseen clinical texts, especially these are only trained on a limited number of examples. This because rely solely the patterns and relationships present in training data, may not be able incorporate additional knowledge about between medical ...

In this paper, we propose novel Gradient Estimation black-box attacks to generate adversarial examples with query access to the target model’s class probabilities, which do not rely on transferability. We also propose strategies to decouple the number of queries required to generate each adversarial example from the dimensionality of the input. An iterative variant of our attack achieves close ...

We leverage recent insights from second-order optimisation for neural networks to construct a Kronecker factored Laplace approximation to the posterior over the weights of a trained network. Our approximation requires no modification of the training procedure, enabling practitioners to estimate the uncertainty of their models currently used in production without having to retrain them. We exten...

Training methods for neural networks are primarily variants on stochastic gradient descent. Techniques that use (approximate) second-order information are rarely used because of the computational cost and noise associated with those approaches in deep learning contexts. We can show that feedforward and recurrent neural networks exhibit an outer product derivative structure but that convolutiona...

Deep neural network pruning forms a compressed network by discarding “unimportant” weights or filters. Standard evaluation metrics have shown their remarkable speedup and prediction accuracy in test time, but their adversarial robustness remains unexplored even though it is an important security feature in deployment. We study the robustness of pruned neural networks under adversarial attacks. ...

This work aims to provide comprehensive landscape analysis of empirical risk in deep neural networks (DNNs), including the convergence behavior of its gradient, its stationary points and the empirical risk itself to their corresponding population counterparts, which reveals how various network parameters determine the convergence performance. In particular, for an l-layer linear neural network ...

We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic message-passing inference algorithms with their neural-network counterparts, we define a graph neural network architecture that generalizes several of the recentl...