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.
Characterizes learnability of multioutput functions in various settings.
Enhances fairness in multi-output models using optimal transport.
The paper presents a novel approach to multi-output regression using probabilistic circuits.
Improves Gaussian process models for large datasets.
The paper explores the identifiability and interpretability of Gaussian process models using different kernel structures.
Adaptive Group Lasso selects important features in neural networks.
Early approaches to multiple-output Gaussian processes (MOGPs) relied on linear combinations of independent, latent, single-output Gaussian processes (GPs). This resulted in cross-covariance functions with limited parametric interpretation, thus conflicting with the ability of single-output GPs to understand lengthscal…
Shallow Art presents, implements, and tests the use of simple single-output classification and regression models for the purpose of art generation. Various machine learning algorithms are trained on collections of computer generated images, artworks from Vincent van Gogh, and artworks from Rembrandt van Rijn. These mod…
We consider the problem of impulse response estimation of stable linear single-input single-output systems. It is a well-studied problem where flexible non-parametric models recently offered a leap in performance compared to the classical finite-dimensional model structures. Inspired by this development and the success…
A novel double-space tensor-product RKHS framework for hybrid uncertainty sensitivity analysis.
A Bayesian factor graph reduced to normal form consists in the interconnection of diverter units (or equal constraint units) and Single-Input/Single-Output (SISO) blocks. In this framework localized adaptation rules are explicitly derived from a constrained maximum likelihood (ML) formulation and from a minimum KL-dive…
MO-GP models fill gaps in biophysical data with across-domain info transfer.
In this paper, we describe our method for DCASE2019 task3: Sound Event Localization and Detection (SELD). We use four CRNN SELDnet-like single output models which run in a consecutive manner to recover all possible information of occurring events. We decompose the SELD task into estimating number of active sources, est…
We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single output sequence for a given input sequence. However, in the context of a story,…
We use smoothed analysis techniques to provide guarantees on the training loss of Multilayer Neural Networks (MNNs) at differentiable local minima. Specifically, we examine MNNs with piecewise linear activation functions, quadratic loss and a single output, under mild over-parametrization. We prove that for a MNN with …
We present the first treatment of the arc length of the Gaussian Process (GP) with more than a single output dimension. GPs are commonly used for tasks such as trajectory modelling, where path length is a crucial quantity of interest. Previously, only paths in one dimension have been considered, with no theoretical con…
The paper improves GP regression for sparse sensor data in structural mode shape reconstruction.
MAPIE provides uncertainty quantification for ML models.
In this work, a deep learning-based method for log-likelihood ratio (LLR) lossy compression and quantization is proposed, with emphasis on a single-input single-output uncorrelated fading communication setting. A deep autoencoder network is trained to compress, quantize and reconstruct the bit log-likelihood ratios cor…
We consider higher-order linear-chain conditional random fields (HO-LC-CRFs) for sequence modelling, and use sum-product networks (SPNs) for representing higher-order input- and output-dependent factors. SPNs are a recently introduced class of deep models for which exact and efficient inference can be performed. By com…
Normative modeling has recently been proposed as an alternative for the case-control approach in modeling heterogeneity within clinical cohorts. Normative modeling is based on single-output Gaussian process regression that provides coherent estimates of uncertainty required by the method but does not consider spatial c…
Gaussian processes (GPs), or distributions over arbitrary functions in a continuous domain, can be generalized to the multi-output case: a linear model of coregionalization (LMC) is one approach. LMCs estimate and exploit correlations across the multiple outputs. While model estimation can be performed efficiently for …
We propose a simple yet highly effective method that addresses the mode-collapse problem in the Conditional Generative Adversarial Network (cGAN). Although conditional distributions are multi-modal (i.e., having many modes) in practice, most cGAN approaches tend to learn an overly simplified distribution where an input…
Conformal prediction sets can lead to unfair outcomes.
Automatic methods for Neural Architecture Search (NAS) have been shown to produce state-of-the-art network models. Yet, their main drawback is the computational complexity of the search process. As some primal methods optimized over a discrete search space, thousands of days of GPU were required for convergence. A rece…
FLORAS uses orthogonal sequences for SISO FL, offering both DP and convergence guarantees.
This paper addresses the problem of active learning of a multi-output Gaussian process (MOGP) model representing multiple types of coexisting correlated environmental phenomena. In contrast to existing works, our active learning problem involves selecting not just the most informative sampling locations to be observed …
Neural networks learn to mimic brain neurons with two-input activation functions, improving performance and robustness.
The paper analyzes the generalizability of linear autoencoders and multivariate linear regression.
Recently there has been an increasing interest in methods that deal with multiple outputs. This has been motivated partly by frameworks like multitask learning, multisensor networks or structured output data. From a Gaussian processes perspective, the problem reduces to specifying an appropriate covariance function tha…
A new method for forming learning objectives using the sum of ranked range.
Background: Statistical mechanics results (Dauphin et al. (2014); Choromanska et al. (2015)) suggest that local minima with high error are exponentially rare in high dimensions. However, to prove low error guarantees for Multilayer Neural Networks (MNNs), previous works so far required either a heavily modified MNN mod…
Unified framework for set-valued classification tackles ambiguous multi-class datasets.
The Jacobian matrix (or the gradient for single-output networks) is directly related to many important properties of neural networks, such as the function landscape, stationary points, (local) Lipschitz constants and robustness to adversarial attacks. In this paper, we propose a recursive algorithm, RecurJac, to comput…
Introduces SoRR for aggregating losses in supervised learning.
Quantifying similarity between data objects is an important part of modern data science. Deciding what similarity measure to use is very application dependent. In this paper, we combine insights from systems theory and machine learning, and investigate the weighted cepstral distance, which was previously defined for si…
Neural network predicts turbulence from wall shear stress.
We tackle causal inference under conditional moment restrictions using importance weighting.
New method improves calibration in multi-output probabilistic models.
Neural network predicts weather probabilities with added uncertainty.
Study restrictions on digitally continuous functions and their effects.
This paper proposes a method to train multiple neural networks with shared parameters using a reconstruction loss.
The study bounds quantum eigenfunctions on complex manifolds.
Bayesian inference on structured models typically relies on the ability to infer posterior distributions of underlying hidden variables. However, inference in implicit models or complex posterior distributions is hard. A popular tool for learning implicit models are generative adversarial networks (GANs) which learn pa…
We address the restriction problem for viscosity subsolutions of a fully nonlinear PDE on a manifold Z. The constraints on the restrictions of smooth subsolutions to a submanifold X in Z determine a restricted subequation on X. The problem is to show that general (upper semi-continuous) subsolutions restrict to satisfy…
We investigate some basic questions concerning the relationship between the restricted Grassmannian and the theory of Banach Lie-Poisson spaces. By using universal central extensions of Lie algebras, we find that the restricted Grassmannian is symplectomorphic to symplectic leaves in certain Banach Lie-Poisson spaces, …
New findings restrict Heegaard Floer homology for certain rational homology spheres.
Introduces a restricted Chen-Nagano variational principle for the Einstein-Hilbert functional.