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.
FEAST improves FNN's range accuracy in ocean waveguides.
Transformer model improves source code summarization.
Backdoors can be implanted in neural models of source code, and we detect and remove them.
Separating an audio scene into isolated sources is a fundamental problem in computer audition, analogous to image segmentation in visual scene analysis. Source separation systems based on deep learning are currently the most successful approaches for solving the underdetermined separation problem, where there are more …
Study homotopy groups of spaces of long links and knots, finding new generators.
pLSTM tackles long-range language modeling and computer vision tasks with parallelizable linear source transition mark networks.
Prototype extraction framework for domain adaptation.
AutoML serves as the bridge between varying levels of expertise when designing machine learning systems and expedites the data science process. A wide range of techniques is taken to address this, however there does not exist an objective comparison of these techniques. We present a benchmark of current open source Aut…
MFNets constructs efficient multifidelity surrogates from diverse information sources.
New WildMix dataset and Spectro-Temporal Transformer model for better monoaural audio source separation.
Solves a challenging problem in imaging and communication.
Apache Spark is a popular open-source platform for large-scale data processing that is well-suited for iterative machine learning tasks. In this paper we present MLlib, Spark's open-source distributed machine learning library. MLlib provides efficient functionality for a wide range of learning settings and includes sev…
MULTIPOLAR aggregates diverse source policies for efficient transfer RL.
Sparse Blind Source Separation (sparse BSS) is a key method to analyze multichannel data in fields ranging from medical imaging to astrophysics. However, since it relies on seeking the solution of a non-convex penalized matrix factorization problem, its performances largely depend on the optimization strategy. In this …
Investigates long-range dependencies in language and music.
Study analyzes foreign exchange rates using MFDFA, revealing multifractality and its sources.
Gaussian processes are a class of flexible nonparametric Bayesian tools that are widely used across the sciences, and in industry, to model complex data sources. Key to applying Gaussian process models is the availability of well-developed open source software, which is available in many programming languages. In this …
This paper addresses the problem of localizing audio sources using binaural measurements. We propose a supervised formulation that simultaneously localizes multiple sources at different locations. The approach is intrinsically efficient because, contrary to prior work, it relies neither on source separation, nor on mon…
Proposes a transfer learning framework for sparse SIMs without raw source data.
DDICA separates nonlinear mixed signals robustly.
New algorithm identifies best target arm with known additive relationship between source and target MAB instances.
Enhances source domain knowledge with target data for transfer learning.
When labeled data is scarce for a specific target task, transfer learning often offers an effective solution by utilizing data from a related source task. However, when transferring knowledge from a less related source, it may inversely hurt the target performance, a phenomenon known as negative transfer. Despite its p…
New method improves multi-fidelity Bayesian optimization by accounting for local correlations and varying noise.
SimTensor is a multi-platform, open-source software for generating artificial tensor data (either with CP/PARAFAC or Tucker structure) for reproducible research on tensor factorization algorithms. SimTensor is a stand-alone application based on MATALB. It provides a wide range of facilities for generating tensor data w…
TransNet improves community detection on target networks using privacy-preserved source networks.
We propose an optimum mechanism for providing monetary incentives to the data sources of a statistical estimator such as linear regression, so that high quality data is provided at low cost, in the sense that the sum of payments and estimation error is minimized. The mechanism applies to a broad range of estimators, in…
We test for departures from normal and independent and identically distributed (NIID) returns, when returns under the alternative hypothesis are self-affine. Self-affine returns are either fractionally integrated and long-range dependent, or drawn randomly from an L-stable distribution with infinite higher-order moment…
Machine learning detects subhalos in lensed images with high accuracy and low false positives.
A framework helps reinforcement learning agents understand and decompose tasks from human demonstrations.
LMGPs enable efficient, accurate data fusion across multiple data sources.
We define and discuss the first sparse coding algorithm based on closed-form EM updates and continuous latent variables. The underlying generative model consists of a standard `spike-and-slab' prior and a Gaussian noise model. Closed-form solutions for E- and M-step equations are derived by generalizing probabilistic P…
We propose a new blind source separation algorithm based on mixtures of alpha-stable distributions. Complex symmetric alpha-stable distributions have been recently showed to better model audio signals in the time-frequency domain than classical Gaussian distributions thanks to their larger dynamic range. However, infer…
This paper examines multifractal dynamics in cryptocurrencies using two methodologies.
New method to evaluate visual explanations from neural networks.
In this paper we study deep learning-based music source separation, and explore using an alternative loss to the standard spectrogram pixel-level L2 loss for model training. Our main contribution is in demonstrating that adding a high-level feature loss term, extracted from the spectrograms using a VGG net, can improve…
Neural language models are a powerful tool to embed words into semantic vector spaces. However, learning such models generally relies on the availability of abundant and diverse training examples. In highly specialised domains this requirement may not be met due to difficulties in obtaining a large corpus, or the limit…
OGB provides diverse graph datasets for robust ML research.
Solving inverse problems continues to be a challenge in a wide array of applications ranging from deblurring, image inpainting, source separation etc. Most existing techniques solve such inverse problems by either explicitly or implicitly finding the inverse of the model. The former class of techniques require explicit…
This paper studies a Nyström type subsampling approach to large kernel learning methods in the misspecified case, where the target function is not assumed to belong to the reproducing kernel Hilbert space generated by the underlying kernel. This case is less understood, in spite of its practical importance. To model su…
WRENCH benchmarks weak supervision datasets for machine learning.
Paper develops estimators for unbounded density ratios with applications in error control.
Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end source separation in the time-domain, which allows modelling phase information and…
Improves functional linear regression with shape transfer learning.
mlpy is a Python Open Source Machine Learning library built on top of NumPy/SciPy and the GNU Scientific Libraries. mlpy provides a wide range of state-of-the-art machine learning methods for supervised and unsupervised problems and it is aimed at finding a reasonable compromise among modularity, maintainability, repro…
Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited. The task is to classify an unlabeled `target' dataset by leveraging a labeled `source' dataset that comes from a slightly similar distribution. We propose metric-based adversarial discriminat…
TOYBOX creates new Atari environments for deep RL experiments.
New seq2seq model can copy entire spans, outperforming simpler models in editing tasks.