Tootfinder

Conformer-based Ultrasound-to-Speech Conversion
Ibrahim Ibrahimov, Zaink\'o Csaba, G\'abor Gosztolya
https://arxiv.org/abs/2506.03831 https://

Conformer-based Ultrasound-to-Speech Conversion
Deep neural networks have shown promising potential for ultrasound-to-speech conversion task towards Silent Speech Interfaces. In this work, we applied two Conformer-based DNN architectures (Base and one with bi-LSTM) for this task. Speaker-specific models were trained on the data of four speakers from the Ultrasuite-Tal80 dataset, while the generated mel spectrograms were synthesized to audio waveform using a HiFi-GAN vocoder. Compared to a standard 2D-CNN baseline, objective measurements (MSE…

This https://arxiv.org/abs/2308.02636 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Learning from Topology: Cosmological Parameter Estimation from the Large-scale Structure
The topology of the large-scale structure of the universe contains valuable information on the underlying cosmological parameters. While persistent homology can extract this topological information, the optimal method for parameter estimation from the tool remains an open question. To address this, we propose a neural network model to map persistence images to cosmological parameters. Through a parameter recovery test, we demonstrate that our model makes accurate and precise estimates, consider…

Rapid yet accurate Tile-circuit and device modeling for Analog In-Memory Computing
J. Luquin, C. Mackin, S. Ambrogio, A. Chen, F. Baldi, G. Miralles, M. J. Rasch, J. B\"uchel, M. Lalwani, W. Ponghiran, P. Solomon, H. Tsai, G. W. Burr, P. Narayanan
https://arxiv.org/abs/2506.00004

Rapid yet accurate Tile-circuit and device modeling for Analog In-Memory Computing
Analog In-Memory Compute (AIMC) can improve the energy efficiency of Deep Learning by orders of magnitude. Yet analog-domain device and circuit non-idealities -- within the analog ``Tiles'' performing Matrix-Vector Multiply (MVM) operations -- can degrade neural-network task accuracy. We quantify the impact of low-level distortions and noise, and develop a mathematical model for Multiply-ACcumulate (MAC) operations mapped to analog tiles. Instantaneous-current IR-drop (the most significant circ…

New paper on ArXiv:
“Uncertainty quantification and posterior sampling for network reconstruction”
TL;DR; We present an efficient method to sample the entire ensemble of possible network reconstructions that are compatible with an indirect observation, e.g. a dynamics.
https://arxiv.org/abs/2503.07736…

This https://arxiv.org/abs/2412.17820 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Hyperbolic embedding of brain networks can predict the surgery outcome in temporal lobe epilepsy
Epilepsy surgery, particularly for temporal lobe epilepsy (TLE), remains a vital treatment option for patients with drug-resistant seizures. However, accurately predicting surgical outcomes remains a significant challenge. This study introduces a novel biomarker derived from brain connectivity, analyzed using non-Euclidean network geometry, to predict the surgery outcome in TLE. Using structural and diffusion magnetic resonance imaging (MRI) data from 51 patients, we examined differences in str…

This https://arxiv.org/abs/2505.22371 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Adaptive tail index estimation: minimal assumptions and non-asymptotic guarantees
A notoriously difficult challenge in extreme value theory is the choice of the number $k\ll n$, where $n$ is the total sample size, of extreme data points to consider for inference of tail quantities. Existing theoretical guarantees for adaptive methods typically require second-order assumptions or von Mises assumptions that are difficult to verify and often come with tuning parameters that are challenging to calibrate. This paper revisits the problem of adaptive selection of $k$ for the Hill…

This https://arxiv.org/abs/2203.01664 has been replaced.
link: https://scholar.google.com/scholar?q=a

Tail-GAN: Learning to Simulate Tail Risk Scenarios
The estimation of loss distributions for dynamic portfolios requires the simulation of scenarios representing realistic joint dynamics of their components. We propose a novel data-driven approach for simulating realistic, high-dimensional multi-asset scenarios, focusing on accurately representing tail risk for a class of static and dynamic trading strategies. We exploit the joint elicitability property of Value-at-Risk (VaR) and Expected Shortfall (ES) to design a Generative Adversarial Network…

Adaptive tail index estimation: minimal assumptions and non-asymptotic guarantees
Johannes Lederer, Anne Sabourin, Mahsa Taheri
https://arxiv.org/abs/2505.22371

Adaptive tail index estimation: minimal assumptions and non-asymptotic guarantees
A notoriously difficult challenge in extreme value theory is the choice of the number $k\ll n$, where $n$ is the total sample size, of extreme data points to consider for inference of tail quantities. Existing theoretical guarantees for adaptive methods typically require second-order assumptions or von Mises assumptions that are difficult to verify and often come with tuning parameters that are challenging to calibrate. This paper revisits the problem of adaptive selection of $k$ for the Hill…

This https://arxiv.org/abs/2505.07719 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hep…

Training neural control variates using correlated configurations
Neural control variates (NCVs) have emerged as a powerful tool for variance reduction in Monte Carlo (MC) simulations, particularly in high-dimensional problems where traditional control variates are difficult to construct analytically. By training neural networks to learn auxiliary functions correlated with the target observable, NCVs can significantly reduce estimator variance while preserving unbiasedness. However, a critical but often overlooked aspect of NCV training is the role of autocor…