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.
A two-network architecture learns intractable exponential family models.
It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what representations do deep neural networks learn. In this work, we move a tiny step to…
JoCoR improves deep learning with noisy labels by reducing network diversity.
Given two networks with the same training loss on a dataset, when would they have drastically different test losses and errors? Better understanding of this question of generalization may improve practical applications of deep networks. In this paper we show that with cross-entropy loss it is surprisingly simple to ind…
MSNet uses high frequency residual learning for efficient multi-scale image classification.
NetOTC compares and aligns directed or undirected networks via random walk transitions.
We follow the main stocks belonging to the New York Stock Exchange and to Nasdaq from 2003 to 2012, through years of normality and of crisis, and study the dynamics of networks built on two measures expressing relations between those stocks: correlation, which is symmetric and measures how similar two stocks behave, an…
RARTS improves neural architecture search efficiency and accuracy.
SGD-trained models' disagreement predicts test error.
Recurrent neural networks like long short-term memory (LSTM) are important architectures for sequential prediction tasks. LSTMs (and RNNs in general) model sequences along the forward time direction. Bidirectional LSTMs (Bi-LSTMs) on the other hand model sequences along both forward and backward directions and are gene…
New method for verifying deep neural networks' differences efficiently.
IMM generates high-quality samples in few steps with stable training.
This paper proposes a new algorithmic framework, predictor-verifier training, to train neural networks that are verifiable, i.e., networks that provably satisfy some desired input-output properties. The key idea is to simultaneously train two networks: a predictor network that performs the task at hand,e.g., predicting…
A new test statistic counts tree co-occurrences to detect edge correlation between networks.
Machine learning approaches hold great potential for the automated detection of lung nodules in chest radiographs, but training the algorithms requires vary large amounts of manually annotated images, which are difficult to obtain. Weak labels indicating whether a radiograph is likely to contain pulmonary nodules are t…
Generative model improves audio synthesis from TF features.
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…
Learning informative representations of data is one of the primary goals of deep learning, but there is still little understanding as to what representations a neural network actually learns. To better understand this, subspace match was recently proposed as a method for assessing the similarity of the representations …
Gradient descent memorizes many Gaussians efficiently.
The paper tests for association between latent community memberships in multi-view network data.
Transforms between neural networks using manifold-learning techniques.
This paper proposes an online knowledge distillation method that transfers feature map information in addition to class probabilities.
Semantic image segmentation is one the most demanding task, especially for analysis of traffic conditions for self-driving cars. Here the results of application of several deep learning architectures (PSPNet and ICNet) for semantic image segmentation of traffic stereo-pair images are presented. The images from Cityscap…
NeuroDiff improves neural network equivalence verification with fine-grained approximations.
Study optimal market making in Hawkes LOB market using impulse control and RL.
We construct two examples of shareholder networks in which shareholders are connected if they have shares in the same company. We do this for the shareholders in Turkish companies and we compare this against the network formed from the shareholdings in Dutch companies. We analyse the properties of these two networks in…
We study the problem of identifying different behaviors occurring in different parts of a large heterogenous network. We zoom in to the network using lenses of different sizes to capture the local structure of the network. These network signatures are then weighted to provide a set of predicted labels for every node. W…
Calendar graph neural networks model user behavior with location and time data.
GANs involve training two networks in an adversarial game, where each network's task depends on its adversary. Recently, several works have framed GAN training as an online or continual learning problem. We focus on the discriminator, which must perform classification under an (adversarially) shifting data distribution…
This study presents a new lossy image compression method that utilizes the multi-scale features of natural images. Our model consists of two networks: multi-scale lossy autoencoder and parallel multi-scale lossless coder. The multi-scale lossy autoencoder extracts the multi-scale image features to quantized variables a…
A new method compares synthetic power networks to actual ones using multiscale flat norm.
We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation network maps samples from stochastic latent variables to the data space while the inference network maps training examples in data space to the sp…
Neural network estimates mutual information for ICA.
We applied Generative Adversarial Networks (GANs) to learn a model of DOOM levels from human-designed content. Initially, we analysed the levels and extracted several topological features. Then, for each level, we extracted a set of images identifying the occupied area, the height map, the walls, and the position of ga…
Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…
We study graph matching with correlated Gaussian features and find thresholds for exact recovery.
Develops a novel method to estimate non-Gaussian hydraulic conductivities efficiently.
Neural networks can memorize and learn complex functions with minimal parameters.
Extracts controllable models from videos of real-world activities.
Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this problem is to retrain the networks using those adversarial examples, namely adversa…
Consider two networks on overlapping, non-identical vertex sets. Given vertices of interest in the first network, we seek to identify the corresponding vertices, if any exist, in the second network. While in moderately sized networks graph matching methods can be applied directly to recover the missing correspondences,…
Meta-learning with network pruning reduces overfitting and improves few-shot learning.
Self-teaching networks improve deep neural networks' generalization.
This paper shows neural networks can learn non-linear sparse parities.
New method reconstructs images from fMRI data using unlabeled data.
We design a dispatch system to improve the peak service quality of video on demand (VOD). Our system predicts the hot videos during the peak hours of the next day based on the historical requests, and dispatches to the content delivery networks (CDNs) at the previous off-peak time. In order to scale to billions of vide…
The cross-correlations between the exchange rate fluctuations of 74 currencies over the period 1995-2012 are analyzed in this paper. The eigenvalue distribution of the cross-correlation matrix exhibits a bulk which approximately matches the bounds predicted from random matrices constructed using mutually uncorrelated t…
Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects of deep neural networks show that they would first memorize training data of cl…