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.
Optimal downsampling improves GLM performance in imbalanced classification.
Downsampling can improve generalization in ridgeless linear regression, especially with optimal sketching size.
We reduce training time in convolutional networks (CNNs) with a method that, for some of the mini-batches: a) scales down the resolution of input images via downsampling, and b) reduces the forward pass operations via pooling on the convolution filters. Training is performed in an interleaved fashion; some batches unde…
Sleep disorders are implicated in a growing number of health problems. In this paper, we present a signal-processing/machine learning approach to detecting arousals in the multi-channel polysomnographic recordings of the Physionet/CinC Challenge2018 dataset. Methods: Our network architecture consists of two components.…
Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution and the downsampling (pooling) operations for graphs. The method of …
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convoluti…
New deep learning method improves 4D Flow MRI super-resolution under domain shift.
PaGoDA reduces diffusion model training costs by 64x.
A hybrid ASR system using conformer architecture improves word-error-rate and training speed.
ThriftyNet uses a single convolutional layer recursively to maximize parameter usage.
AutoEmbedder clusters unlabeled data using semi-supervised DNN embedding.
Paper improves Oja's algorithm for Markovian data streams.
DNArch learns CNN architectures by backpropagation.
The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. Current Video Super-Resolution methods are not robust to mismatch between training and testing degradation models since they are trained against a single…
This paper simplifies diffusion models for high resolution images.
In this brief technical report we introduce the CINIC-10 dataset as a plug-in extended alternative for CIFAR-10. It was compiled by combining CIFAR-10 with images selected and downsampled from the ImageNet database. We present the approach to compiling the dataset, illustrate the example images for different classes, g…
Gaussian Process upsampling boosts OCR accuracy from low-res images.
New method samples DPPs efficiently without downsampling or low-rank approximations.
A new training method speeds up ResNet training by 3x with minimal accuracy loss.
HKT improves sequence processing with multi-scale attention and kernel analysis.
Study reveals significant performance flips in GLOD using repurposed graph classification datasets.
In this work we apply variations of ResNet architecture to the task of atrial fibrillation classification. Variations differ in number of filter after first convolution, ResNet block layout, number of filters in block convolutions and number of ResNet blocks between downsampling operations. We have found a range of mod…
Early detection is a crucial goal in the study of Alzheimer's Disease (AD). In this work, we describe several techniques to boost the performance of 3D deep convolutional neural networks (CNNs) trained to detect AD using structural brain MRI scans. Specifically, we provide evidence that (1) instance normalization outpe…
Efficient neural network for audio source separation.
Data augmentation methods improve worst-case model performance.
Stochastic optimization naturally arises in machine learning. Efficient algorithms with provable guarantees, however, are still largely missing, when the objective function is nonconvex and the data points are dependent. This paper studies this fundamental challenge through a streaming PCA problem for stationary time s…
Machine learning models classify celestial objects like pulsars and black holes.
PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at https://github.com/openai/pixel-cnn. Our implementation contains a number of modifications to the original model that both simplify its structure an…
This paper presents a novel deep learning-based method for learning a functional representation of mammalian neural images. The method uses a deep convolutional denoising autoencoder (CDAE) for generating an invariant, compact representation of in situ hybridization (ISH) images. While most existing methods for bio-ima…
RAD improves robustness to domain annotation noise without explicit domain annotations.
Graph convolutional neural networks (Graph-CNNs) extend traditional CNNs to handle data that is supported on a graph. Major challenges when working with data on graphs are that the support set (the vertices of the graph) do not typically have a natural ordering, and in general, the topology of the graph is not regular …
Image compression is an essential approach for decreasing the size in bytes of the image without deteriorating the quality of it. Typically, classic algorithms are used but recently deep-learning has been successfully applied. In this work, is presented a deep super-resolution work-flow for image compression that maps …
A new tensor-based layer reduces neural network dimensions without losing important features.
The paper verifies deep neural networks' ability to approximate functions on spheres.
Electronic records contain sequences of events, some of which take place all at once in a single visit, and others that are dispersed over multiple visits, each with a different timestamp. We postulate that fine temporal detail, e.g., whether a series of blood tests are completed at once or in rapid succession should n…
Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks. While novel approaches to learning node embeddings are highly suitable for node classification and link prediction, their application to graph…
Convolution and pooling improve kernel methods in image classification.
This paper develops efficient bounds on the Wasserstein metric for discrete measures.
NDMs enable non-linear transformations in diffusion models for better generative tasks.
Paper addresses CPA line forecasting in online advertising mid-flight.
Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampli…
MathNet uses wavelets for graph representation and learning.
Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. …
The paper tackles skeptical binary inferences in multi-label problems with sets of probabilities.
The paper tackles imbalance in production data by proposing sampling methods to improve model performance on underrepresented observations.
Graph Neural Networks (GNN) have been shown to work effectively for modeling graph structured data to solve tasks such as node classification, link prediction and graph classification. There has been some recent progress in defining the notion of pooling in graphs whereby the model tries to generate a graph level repre…
The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is crucial, e.g. traffic networks and financial transaction graphs. Despite the constant progress made on learning structured data, there is s…
Spectral Independence Criterion helps infer cause-effect relationships in time series.