arXiv research

Flexible deep learning models for dynamic accuracy and speed trade-offs.

Crochet creates precise 2D shapes from 1D material.

Paper proves flexibility of specific relations using convex integration.

Novel deep learning model improves AUC prediction for tacrolimus dosing.

A new R package for high-dimensional regression and precision matrix estimation.

A new framework for adaptive behavior using reusable value profiles.

We consider the problem of learning a Gaussian variational approximation to the posterior distribution for a high-dimensional parameter, where we impose sparsity in the precision matrix to reflect appropriate conditional independence structure in the model. Incorporating sparsity in the precision matrix allows the Gaus…

Extends ONNX for quantized neural networks with new formats and operators.

Graph convolutional deep kernel machine learns representations for graph tasks.

New framework identifies strongly identifiable models from flexible generators.

LI-ITR combines flexible ML with interpretable approximations for personalized treatment rules.

At the core of interpretable machine learning is the question of whether humans are able to make accurate predictions about a model's behavior. Assumed in this question are three properties of the interpretable output: coverage, precision, and effort. Coverage refers to how often humans think they can predict the model…

We show that the presence of a plastikstufe induces a certain degree of flexibility in contact manifolds of dimension 2n+1>3. More precisely, we prove that every Legendrian knot whose complement contains a "nice" plastikstufe can be destabilized (and, as a consequence, is loose). As an application, it follows in certai…

Adaptive batch sizes improve active learning efficiency and flexibility.

New methods use RL and DA to improve dosing precision and reduce side effects.

We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100. Our approach is based on differentiable abstract interpretation and introduces two novel concepts: (i) abstract layers for fine-tuning the precision and scalabilit…

Deep Transformed Gaussian Processes extend TGPs with variational inference for scalable multi-layer modeling.

Adaptive Prespecification improves precision in randomized trials.

Determinantal point processes (DPPs) offer a powerful approach to modeling diversity in many applications where the goal is to select a diverse subset. We study the problem of learning the parameters (the kernel matrix) of a DPP from labeled training data. We make two contributions. First, we show how to reparameterize…

The present paper proposes generalized Gaussian kernel adaptive filtering, where the kernel parameters are adaptive and data-driven. The Gaussian kernel is parametrized by a center vector and a symmetric positive definite (SPD) precision matrix, which is regarded as a generalization of the scalar width parameter. These…

This paper solves the convergence problem for estimating MGGD parameters with a convex formulation.

The Hull-Strominger system for supersymmetric vacua of the heterotic string allows general unitary Hermitian connections with torsion and not just the Chern unitary connection. Solutions on unimodular Lie groups exploiting this flexibility were found by T. Fei and S.T. Yau. The Anomaly flow is a flow whose stationary p…

A new method models individual survival curves using conditional normalizing flows.

Diffusion models adapt to low-dimensional data regardless of coefficient choices.

Many open problems and important theorems in low-dimensional topology have been formulated as statements about certain 2--complexes called gropes. This paper describes a precise correspondence between embedded gropes in 4--manifolds and the failure of the Whitney move in terms of iterated `towers' of Whitney disks. The…

Today, despite decades of developments in medicine and the growing interest in precision healthcare, vast majority of diagnoses happen once patients begin to show noticeable signs of illness. Early indication and detection of diseases, however, can provide patients and carers with the chance of early intervention, bett…

Study increasing profits in a flexible financial market model.

The paper proposes a method to estimate treatment effects using CAR designs with additional covariates.

Deep neural network improves cancer mutation calls with confidence.

Bayesian method learns graph structures from Gaussian data efficiently.

We forecast S&P 500 excess returns using a flexible Bayesian econometric state space model with non-Gaussian features at several levels. More precisely, we control for overparameterization via novel global-local shrinkage priors on the state innovation variances as well as the time-invariant part of the state space mod…

I report a new statistical distribution formulated to confront the infamous, long-standing, computational/modeling challenge presented by highly skewed and/or leptokurtic ("fat- or heavy-tailed") data. The distribution is straightforward, flexible and effective. Even when working with far fewer data points than are rou…

Stein-Encoder isolates genetic signals in multi-modal biomedical data.

This paper improves fraud prevention rule sets in fintech by generating diverse rules and finding Pareto-optimal subsets.

This paper proposes CodeX, an end-to-end framework that facilitates encoding, bitwidth customization, fine-tuning, and implementation of neural networks on FPGA platforms. CodeX incorporates nonlinear encoding to the computation flow of neural networks to save memory. The encoded features demand significantly lower sto…

We develop a scalable method for Bayesian neural networks with stochastic differential equations.

This paper tackles multi-modal label disentanglement in partition-based XMC.

Study predicts intraday stock trading volume using ML models.

Sentiment analysis consists of evaluating opinions or statements from the analysis of text. Among the methods used to estimate the degree in which a text expresses a given sentiment, are those based on Gaussian Processes. However, traditional Gaussian Processes methods use a predefined kernel with hyperparameters that …

Paper extends Bayes Theorem for interval probability estimates.

Algorithm compresses large matrices by approximating them as low rank and low precision factors.

Unified and simplified signature method for multivariate time series.

In this paper we define and study flexible links and flexible isotopy in projective space. Flexible links are meant to capture the topological properties of real algebraic links. We classify all flexible links up to flexible isotopy using Ekholms interpretation of Viros encomplexed writhe.

The authors characterize flexibility in power and energy markets considering time, spatiality, resource, and risk.

GENOT matches cells across data modalities using neural OT solvers.

A new copula model for multi-attribute data using optimal transport.

Enhances demand models with deep learning for personalized pricing.

Federated learning improves by training central model with client model outputs.