A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Early training of deep neural networks leads to small, directionally converging weights.
The skip-connections used in residual networks have become a standard architecture choice in deep learning due to the increased training stability and generalization performance with this architecture, although there has been limited theoretical understanding for this improvement. In this work, we analyze overparameter…
The paper studies neural networks' convergence near origin and saddle points.
A new test optimizes detecting small communities in large networks.
Learning with noisy labels is one of the hottest problems in weakly-supervised learning. Based on memorization effects of deep neural networks, training on small-loss instances becomes very promising for handling noisy labels. This fosters the state-of-the-art approach "Co-teaching" that cross-trains two deep neural ne…
Physics-enhanced NNs improve predictive accuracy in small data scenarios.
Algorithm recovers large causal tree from small samples.
The densification of small-cell base stations in a 5G architecture is a promising approach to enhance the coverage area and facilitate the ever increasing capacity demand of end users. However, the bottleneck is an intelligent management of a backhaul/fronthaul network for these small-cell base stations. This involves …
Sketch-based approach detects community events in evolving networks.
EnLSTM network improves log generation from small datasets.
A new test for IRG models using KSD for small networks.
Generative model initializes 2-layer network weights for small datasets.
Deep Neural Networks (DNNs) are usually over-parameterized, causing excessive memory and interconnection cost on the hardware platform. Existing pruning approaches remove secondary parameters at the end of training to reduce the model size; but without exploiting the intrinsic network property, they still require the f…
Training large and highly accurate deep learning (DL) models is computationally costly. This cost is in great part due to the excessive number of trained parameters, which are well-known to be redundant and compressible for the execution phase. This paper proposes a novel transformation which changes the topology of th…
Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from teacher to student during knowledge distillation. We find that a large amount of robu…
SHADOWCAST generates graphs with user-specified attributes.
We propose a new deep learning approach for medical imaging that copes with the problem of a small training set, the main bottleneck of deep learning, and apply it for classification of healthy and cancer cells acquired by quantitative phase imaging. The proposed method, called transferring of pre-trained generative ad…
We present a deep-learning network that detects multiple small objects (hundreds to thousands) in a scene while simultaneously estimating their x,y pixel locations together with a characteristic feature-set (for instance, target orientation and color). All estimations are performed in a single, forward pass which makes…
SFCNeXt estimates brain age from small MRI datasets.
EASIER-net uses sparse networks to improve prediction accuracy for high-dimensional data.
We define the intrinsic scale at which a network begins to reveal its identity as the scale at which subgraphs in the network (created by a random walk) are distinguishable from similar sized subgraphs in a perturbed copy of the network. We conduct an extensive study of intrinsic scale for several networks, ranging fro…
Stochastic gradient descent with a large initial learning rate is widely used for training modern neural net architectures. Although a small initial learning rate allows for faster training and better test performance initially, the large learning rate achieves better generalization soon after the learning rate is anne…
Deep neural network solves portfolio optimization with MGARCH and small transaction costs.
Gradient-trained shallow networks can generalize well but are vulnerable to small-radius adversarial attacks.
Gradient descent fails to learn simple neural networks efficiently.
Small neural networks embed arbitrary metric spaces into Gaussian mixtures.
This comment reexamines Simard et al.'s work in [D. Simard, L. Nadeau, H. Kroger, Phys. Lett. A 336 (2005) 8-15]. We found that Simard et al. calculated mistakenly the local connectivity lengths Dlocal of networks. The right results of Dlocal are presented and the supervised learning performance of feedforward neural n…
Deep Neural Network (DNN) acoustic models have yielded many state-of-the-art results in Automatic Speech Recognition (ASR) tasks. More recently, Recurrent Neural Network (RNN) models have been shown to outperform DNNs counterparts. However, state-of-the-art DNN and RNN models tend to be impractical to deploy on embedde…
Graph neural networks denote a group of neural network models introduced for the representation learning tasks on graph data specifically. Graph neural networks have been demonstrated to be effective for capturing network structure information, and the learned representations can achieve the state-of-the-art performanc…
Proposes Causal-Batle for estimating treatment effects in small high-dimensional datasets.
Conventional deep learning classifiers are static in the sense that they are trained on a predefined set of classes and learning to classify a novel class typically requires re-training. In this work, we address the problem of Low-Shot network expansion learning. We introduce a learning framework which enables expandin…
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to…
This study investigates how gradient-based methods bias neural networks trained on high-dimensional data.
Most random ReLU networks are vulnerable to small, Euclidean adversarial perturbations.
Deep networks can approximate functions with fewer learnable parameters than previously thought.
Neural networks trained with backpropagation, the standard algorithm of deep learning which uses weight transport, are easily fooled by existing gradient-based adversarial attacks. This class of attacks are based on certain small perturbations of the inputs to make networks misclassify them. We show that less biologica…
Empirical evidence suggests that neural networks with ReLU activations generalize better with over-parameterization. However, there is currently no theoretical analysis that explains this observation. In this work, we provide theoretical and empirical evidence that, in certain cases, overparameterized convolutional net…
The paper investigates why GNNs struggle to generalize from small to large graphs.
Biological networks are a very convenient modelling and visualisation tool to discover knowledge from modern high-throughput genomics and postgenomics data sets. Indeed, biological entities are not isolated, but are components of complex multi-level systems. We go one step further and advocate for the consideration of …
We propose to study neural networks' loss surfaces by methods of topological data analysis. We suggest to apply barcodes of Morse complexes to explore topology of loss surfaces. An algorithm for calculations of the loss function's barcodes of local minima is described. We have conducted experiments for calculating barc…
New method finds smaller networks with similar performance to large models in fewer epochs.
This work finds a point with small test error in polynomial time for mildly overparameterized neural nets.
The paper analyzes neural network dynamics after weights escape the origin.
Neural net reconstructs dark matter density from halo velocities.
The structure of the control network of transnational corporations affects global market competition and financial stability. So far, only small national samples were studied and there was no appropriate methodology to assess control globally. We present the first investigation of the architecture of the international …
Propagation of balance-sheet or cash-flow insolvency across financial institutions may be modeled as a cascade process on a network representing their mutual exposures. We derive rigorous asymptotic results for the magnitude of contagion in a large financial network and give an analytical expression for the asymptotic …
We demonstrate that graphs embedded on surfaces are a powerful and practical tool to generate, characterize and simulate networks with a broad range of properties. Remarkably, the study of topologically embedded graphs is non-restrictive because any network can be embedded on a surface with sufficiently high genus. The…
Paper proposes a method to evaluate SME credit risk using meta paths.