arXiv research

In this paper, we propose a phase shift deep neural network (PhaseDNN) which provides a wideband convergence in approximating a high dimensional function during its training of the network. The PhaseDNN utilizes the fact that many DNN achieves convergence in the low frequency range first, thus, a series of moderately-s…

FreSh shifts model's initial frequency spectrum to match target signal, improving neural representation performance.

Paper extends SI method for detecting CPs in complex systems' frequency domain.

New method calibrates models under covariate shifts.

Motivated by recently published methods using frequency decompositions of convolutions (e.g. Octave Convolutions), we propose a novel convolution scheme to stabilize the training and reduce the likelihood of a mode collapse. The basic idea of our approach is to split convolutional filters into additive high and low fre…

Using high-frequency time series of stock prices and share volumes sizes from January 2002-May 2009, this paper investigates whether the effects of the onset of high-frequency trading, most prominent since 2005, are apparent in the dynamics of the dollar traded volume. Indeed it is found in almost all of 14 heavily tra…

In this paper we present a novel model of the primary visual cortex (V1) based on orientation, frequency and phase selective behavior of the V1 simple cells. We start from the first level mechanisms of visual perception: receptive profiles. The model interprets V1 as a fiber bundle over the 2-dimensional retinal plane …

This paper explores a variety of models for frame-based music transcription, with an emphasis on the methods needed to reach state-of-the-art on human recordings. The translation-invariant network discussed in this paper, which combines a traditional filterbank with a convolutional neural network, was the top-performin…

We present a sparse and invariant representation with low asymptotic complexity for robust unsupervised transient and onset zone detection in noisy environments. This unsupervised approach is based on wavelet transforms and leverages the scattering network from Mallat et al. by deriving frequency invariance. This frequ…

The paper addresses instability in CNNs' first layer by proving max pooling's shift invariance.

FredNormer improves time series forecasting by adapting to frequency domain patterns.

Many spectral unmixing methods rely on the non-negative decomposition of spectral data onto a dictionary of spectral templates. In particular, state-of-the-art music transcription systems decompose the spectrogram of the input signal onto a dictionary of representative note spectra. The typical measures of fit used to …

Bird sounds possess distinctive spectral structure which may exhibit small shifts in spectrum depending on the bird species and environmental conditions. In this paper, we propose using convolutional recurrent neural networks on the task of automated bird audio detection in real-life environments. In the proposed metho…

Minimal token perturbations reveal how Transformer models process information.

Neural network based architectures used for sound recognition are usually adapted from other application domains such as image recognition, which may not harness the time-frequency representation of a signal. The ConditionaL Neural Networks (CLNN) and its extension the Masked ConditionaL Neural Networks (MCLNN) are des…

We theoretically and empirically study portfolio optimization under transaction costs and establish a link between turnover penalization and covariance shrinkage with the penalization governed by transaction costs. We show how the ex ante incorporation of transaction costs shifts optimal portfolios towards regularized …

The paper develops methods to estimate frequencies in large discrete data sets with improved coverage and robustness.

We analyze the structure of the \emph{frequency space} $Q(F)$ of a nonabelian free group $F=F(a_1,...,a_k)$ consisting of all shift-invariant Borel probability measures on $\partial F$ and construct a natural action of $Out(F)$ on $Q(F)$. In particular we prove that for any outer automorphism $φ$ of $F$ the \emph{conju…

DSLOB creates synthetic LOB data for benchmarking forecasting algorithms under distributional shifts.

High frequency limit for most of wave phenomena is known as quasiclassical limit or ray optics limit. Propagation of waves in this limit is described in terms of wave fronts and rays. Wave front is a surface of constant phase whose points are moving along rays. As it appears, their motion can be described by Hamilton e…

Adaptive method for prediction sets under changing data distributions.

Typically, operational risk losses are reported above some threshold. This paper studies the impact of ignoring data truncation on the 0.999 quantile of the annual loss distribution for operational risk for a broad range of distribution parameters and truncation levels. Loss frequency and severity are modelled by the P…

Proposes a new method to improve CNNs' shift invariance and accuracy.

Deep neural network architectures designed for application domains other than sound, especially image recognition, may not optimally harness the time-frequency representation when adapted to the sound recognition problem. In this work, we explore the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural N…

Framework improves classifier calibration under differential privacy for domain shift.

We generalize the recently proposed quantum model for the stock market by Zhang and Huang to make it consistent with the discrete nature of the stock price. In this formalism, the price of the stock and its trend satisfy the generalized uncertainty relation and the corresponding generalized Hamiltonian contains an addi…

The basic model for high-frequency data in finance is considered, where an efficient price process is observed under microstructure noise. It is shown that this nonparametric model is in Le Cam's sense asymptotically equivalent to a Gaussian shift experiment in terms of the square root of the volatility function $σ$. A…

Tests factor models by decomposing market into body and tail legs, revealing inconsistent results.

The ConditionaL Neural Networks (CLNN) and the Masked ConditionaL Neural Networks (MCLNN) exploit the nature of multi-dimensional temporal signals. The CLNN captures the conditional temporal influence between the frames in a window and the mask in the MCLNN enforces a systematic sparseness that follows a filterbank-lik…

NFM models time-series data directly in the Fourier domain, achieving state-of-the-art performance.

HANET combines LSTM and attention mechanisms for better financial forecasting.

Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain transfer often operate on data on which the modes of the distribution are well-matched, for instance have the same frequencies of classes b…

SHIFT method optimally estimates heterogeneous discrete distributions with limited communication.

A new model for imputing missing values in time series data across domains.

We analyse the temporal changes in the cross correlations of returns on the New York Stock Exchange. We show that lead-lag relationships between daily returns of stocks vanished in less than twenty years. We have found that even for high frequency data the asymmetry of time dependent cross-correlation functions has a d…

New method certifies risks of LLM outputs, improving accuracy and reliability.

Study finds anomalies in high-frequency S&P 500 price changes.

Estimating signals with linear recurrence relations under Gaussian noise is nearly as hard as sparse signals.

Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across corruption types. Indeed increasing performance in the presence of random noise is oft…

Sound event detection systems typically consist of two stages: extracting hand-crafted features from the raw audio waveform, and learning a mapping between these features and the target sound events using a classifier. Recently, the focus of sound event detection research has been mostly shifted to the latter stage usi…

Volatility estimation based on high-frequency data is key to accurately measure and control the risk of financial assets. A Lévy process with infinite jump activity and microstructure noise is considered one of the simplest, yet accurate enough, models for financial data at high-frequency. Utilizing this model, we prop…

Alternative wavelet analysis method for financial signals.

Proposes a new framework to manage venture capital portfolio risk by focusing on deal-level correlations.

Paper predicts bearing degradation stages for pharmaceutical industry maintenance.

Quantum theory reinterprets financial pricing by focusing on observable price transitions.

We develop a definitive physical-space scattering theory for the scalar wave equation on Kerr exterior backgrounds in the general subextremal case |a|<M. In particular, we prove results corresponding to "existence and uniqueness of scattering states" and "asymptotic completeness" and we show moreover that the resulting…

A musical instrument based on moduli spaces lets users hear geometric concepts.

Analyzed Bitcoin market index volatility changes over two distinct periods using anomalous diffusion and multifractal analysis.