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.
R package psvmSDR simplifies SDR computation for machine learning.
New method for nonlinear SDR of complex non-Euclidean data.
This paper reviews SDR methods for multivariate response regression.
GenSDR tackles SDR by leveraging generative models to fully recover lower-dimensional structures.
Multi-layer neural networks have lead to remarkable performance on many kinds of benchmark tasks in text, speech and image processing. Nonlinear parameter estimation in hierarchical models is known to be subject to overfitting and misspecification. One approach to these estimation and related problems (local minima, co…
Solves a fundamental problem in statistics and imaging with new methods.
Reservoir subspace injection improves online ICA by preserving injected features.
Neural networks simplify SDR in regression tasks.
Enhances SDR via Hellinger correlation for better data dependency understanding.
We present the Shortfall Deviation Risk (SDR), a risk measure that represents the expected loss that occurs with certain probability penalized by the dispersion of results that are worse than such an expectation. SDR combines Expected Shortfall (ES) and Shortfall Deviation (SD), which we also introduce, contemplating t…
FlowSDR learns a low-dimensional projection preserving the response's conditional distribution.
Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement. Denoising networks learn mapping from noisy speech to clean one directly, or to a spectrum mask which is the ratio between clean and noisy spectra. In either case, the network is optimized by minimizi…
SDR outperforms IDR in multimodal data analysis, especially with fewer samples.
POTD estimates SDR subspace using optimal transport for binary response.
We consider the problem of sufficient dimensionality reduction (SDR), where the high-dimensional observation is transformed to a low-dimensional sub-space in which the information of the observations regarding the label variable is preserved. We propose DVSDR, a deep variational approach for sufficient dimensionality r…
Survey of SDR methods for high-dimensional regression and embedding.
Recently, deep neural network (DNN) has made a breakthrough in monaural source enhancement. Through a training step by using a large amount of data, DNN estimates a mapping between mixed signals and clean signals. At this time, we use an objective function that numerically expresses the quality of a mapping by DNN. In …
Sufficient dimension reduction (SDR) using distance covariance (DCOV) was recently proposed as an approach to dimension-reduction problems. Compared with other SDR methods, it is model-free without estimating link function and does not require any particular distributions on predictors (see Sheng and Yin, 2013, 2016). …
A method for reducing dimensions in Fréchet regression models.
Maximum a posteriori (MAP) inference over discrete Markov random fields is a fundamental task spanning a wide spectrum of real-world applications, which is known to be NP-hard for general graphs. In this paper, we propose a novel semidefinite relaxation formulation (referred to as SDR) to estimate the MAP assignment. A…
The purpose of sufficient dimension reduction (SDR) is to find the low-dimensional subspace of input features that is sufficient for predicting output values. In this paper, we propose a novel distribution-free SDR method called sufficient component analysis (SCA), which is computationally more efficient than existing …
Singing Voice Separation (SVS) tries to separate singing voice from a given mixed musical signal. Recently, many U-Net-based models have been proposed for the SVS task, but there were no existing works that evaluate and compare various types of intermediate blocks that can be used in the U-Net architecture. In this pap…
In this paper, we propose a two-step training procedure for source separation via a deep neural network. In the first step we learn a transform (and it's inverse) to a latent space where masking-based separation performance using oracles is optimal. For the second step, we train a separation module that operates on the…
Paper improves SDR estimation speed and conditions.
Fast and cheaper next generation sequencing technologies will generate unprecedentedly massive and highly-dimensional genomic and epigenomic variation data. In the near future, a routine part of medical record will include the sequenced genomes. A fundamental question is how to efficiently extract genomic and epigenomi…
This paper proposes RAS, a novel unsupervised loss function for speech separation.
We found hidden convexity in FPCA and developed a faster algorithm.
We reformulate unsupervised dimension reduction problem (UDR) in the language of tempered distributions, i.e. as a problem of approximating an empirical probability density function by another tempered distribution, supported in a -dimensional subspace. We show that this task is connected with another classical prob…
Paper develops KMS Wasserstein for high-dimensional data reduction.
Deep clustering is a recently introduced deep learning architecture that uses discriminatively trained embeddings as the basis for clustering. It was recently applied to spectrogram segmentation, resulting in impressive results on speaker-independent multi-speaker separation. In this paper we extend the baseline system…
CIR method preserves relation for case-control studies.
SMAVE optimizes SDR by projecting onto a low-dimensional subspace on a Riemannian manifold.
A new geometry-preserving method for interpreting compositional data.
This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within a deep network. Previous approaches, rather than computing a loss on the recons…
Combines deep and statistical learning for structured data.
A theory of sufficient dimension reduction (SDR) is developed from an optimizational perspective. In our formulation of the problem, instead of dealing with raw data, we assume that our ground truth includes a mapping and a probability distribution function over…
When designing fully-convolutional neural network, there is a trade-off between receptive field size, number of parameters and spatial resolution of features in deeper layers of the network. In this work we present a novel network design based on combination of many convolutional and recurrent layers that solves these …
Conventional multiuser detection techniques either require a large number of antennas at the receiver for a desired performance, or they are too complex for practical implementation. Moreover, many of these techniques, such as successive interference cancellation (SIC), suffer from errors in parameter estimation (user …
In this letter, we propose enhanced factored three way restricted Boltzmann machines (EFTW-RBMs) for speech detection. The proposed model incorporates conditional feature learning by multiplying the dynamical state of the third unit, which allows a modulation over the visible-hidden node pairs. Instead of stacking prev…
We study the problem of source separation for music using deep learning with four known sources: drums, bass, vocals and other accompaniments. State-of-the-art approaches predict soft masks over mixture spectrograms while methods working on the waveform are lagging behind as measured on the standard MusDB benchmark. Ou…
FPCA optimizes fairness in target vectors' span.
Hybrid model improves music source separation by 1.4 dB.
A new neural network separates vocals from music accompaniment.
Fair representations are a powerful tool for establishing criteria like statistical parity, proxy non-discrimination, and equality of opportunity in learned models. Existing techniques for learning these representations are typically model-agnostic, as they preprocess the original data such that the output satisfies so…
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…
End-to-end learning of communications systems is a fascinating novel concept that has so far only been validated by simulations for block-based transmissions. It allows learning of transmitter and receiver implementations as deep neural networks (NNs) that are optimized for an arbitrary differentiable end-to-end perfor…
TinyLSTMs reduces speech enhancement model size and latency for hearing aids.
Unfulfilled expectations from macro-economic initiatives during the Great Recession and the massive shift into globalization echo today with political upheaval, anti-establishment propaganda, and looming trade/currency wars that threaten domestic and international value chains. Once stable entities like the EU now look…