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.
This work improves understanding of neural network reconstruction attacks and distillation.
System discovers new classes from unlabeled data, improving model performance.
RADAR uses diffusion models to detect anomalies without reconstruction, improving accuracy and efficiency.
DynamicVAE improves disentanglement and reconstruction accuracy without sacrificing one for the other.
KM-GPT automates IPD reconstruction from KM plots with high accuracy and scalability.
The shortage of high-resolution urban digital elevation model (DEM) datasets has been a challenge for modelling urban flood and managing its risk. A solution is to develop effective approaches to reconstruct high-resolution DEMs from their low-resolution equivalents that are more widely available. However, the current …
Reduces data leakage in distributed deep learning models.
NKI integrates obfuscated datasets using nonlinear kernels for improved data collaboration.
Paper proposes WGAIN for missing feature reconstruction.
Deep learning models reconstruct volatility surfaces from noisy data under no-arbitrage constraints.
Reconstruction-based learning produces uninformative features for perception tasks.
Single-cell gene expression data provide invaluable resources for systematic characterization of cellular hierarchy in multi-cellular organisms. However, cell lineage reconstruction is still often associated with significant uncertainty due to technological constraints. Such uncertainties have not been taken into accou…
A key problem in statistics and machine learning is the determination of network structure from data. We consider the case where the structure of the graph to be reconstructed is known to be scale-free. We show that in such cases it is natural to formulate structured sparsity inducing priors using submodular functions,…
POTATOES improves autoencoder UOD accuracy without tuning.
A hierarchical approach improves classification accuracy in large datasets.
Unified deep learning approach for time series forecasting using VMD-CNN-LSTM.
Noise2Filter improves 3D tomography reconstruction efficiency and accuracy.
A good representation for arbitrarily complicated data should have the capability of semantic generation, clustering and reconstruction. Previous research has already achieved impressive performance on either one. This paper aims at learning a disentangled representation effective for all of them in an unsupervised way…
Study shows survivorship bias inflates returns in India's small-cap index.
In text mining, information retrieval, and machine learning, text documents are commonly represented through variants of sparse Bag of Words (sBoW) vectors (e.g. TF-IDF). Although simple and intuitive, sBoW style representations suffer from their inherent over-sparsity and fail to capture word-level synonymy and polyse…
Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem. We introduce a pooling method for sets of feature vectors based on sorting features across elements of the set. This can be used to construct a permutation-equivariant auto-encoder that avoids this re…
The reconstruction of an object's shape or surface from a set of 3D points plays an important role in medical image analysis, e.g. in anatomy reconstruction from tomographic measurements or in the process of aligning intra-operative navigation and preoperative planning data. In such scenarios, one usually has to deal w…
This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to Mel-frequency and short-time Fourier transform spectrograms, and such perturbed spectrograms…
We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network. This mapping network can be used to reconstruct an object by applying its encoded transformation to points randomly sampled from a simple geo…
Un-trained neural networks outperform trained methods in MRI reconstruction.
IMPACT optimizes LLM compression by focusing on activation importance, reducing model size up to 55.4%.
The remarkable success of machine learning, especially deep learning, has produced a variety of cloud-based services for mobile users. Such services require an end user to send data to the service provider, which presents a serious challenge to end-user privacy. To address this concern, prior works either add noise to …
PAIN network improves imputation for mixed datasets.
Algorithms for Magnetic Resonance (MR) image reconstruction from undersampled measurements exploit prior information to compensate for missing k-space data. Deep learning (DL) provides a powerful framework for extracting such information from existing image datasets, through learning, and then using it for reconstructi…
Although the popular MNIST dataset [LeCun et al., 1994] is derived from the NIST database [Grother and Hanaoka, 1995], the precise processing steps for this derivation have been lost to time. We propose a reconstruction that is accurate enough to serve as a replacement for the MNIST dataset, with insignificant changes …
In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition. Specifically, we design a new model called Deep Reconstruction-Classification Network (DRCN), which jointly learns a shared encoding representation for two tasks: i) supervised classification…
A novel approach stores encoded images as centroids and covariance matrices to improve classification accuracy with less memory.
New benchmark for EEG-eye movement reconstruction from functional data.
ROAD-EnKFs use learned low-dimensional models to improve state reconstruction and forecasting.
SDSR reconstructs species trees from genetic markers efficiently.
MFSSA improves reconstruction accuracy of multivariate functional time series.
Method recovers particle orientations from cryo-EM projections.
New method reconstructs data subsets from limited published statistics.
SSMBA generates synthetic data to improve robustness in natural language tasks.
New methods improve feature extraction and representation quality in supervised and unsupervised DR.
Paper uses robust GMM to reconstruct missing data in Sentinel-2 images for crop monitoring.
Node embeddings have become an ubiquitous technique for representing graph data in a low dimensional space. Graph autoencoders, as one of the widely adapted deep models, have been proposed to learn graph embeddings in an unsupervised way by minimizing the reconstruction error for the graph data. However, its reconstruc…
Proposes a new framework for image generation using classification latent space representations.
Recommender systems have recently attracted many researchers in the deep learning community. The state-of-the-art deep neural network models used in recommender systems are typically multilayer perceptron and deep Autoencoder (DAE), among which DAE usually shows better performance due to its superior capability to reco…
Most real-world datasets, and particularly those collected from physical systems, are full of noise, packet loss, and other imperfections. However, most specification mining, anomaly detection and other such algorithms assume, or even require, perfect data quality to function properly. Such algorithms may work in lab c…
This paper develops a novel deep recurrent neural network for sequential signal reconstruction.
Recent literature on unsupervised learning focused on designing structural priors with the aim of learning meaningful features, but without considering the description length of the representations. In this thesis, first we introduce the metric that evaluates unsupervised models based on their reconstruction …
A primary concern of excessive reuse of test datasets in machine learning is that it can lead to overfitting. Multiclass classification was recently shown to be more resistant to overfitting than binary classification. In an open problem of COLT 2019, Feldman, Frostig, and Hardt ask to characterize the dependence of th…