arXiv research

Unique continuation for X-ray transforms of one-forms with partial data.

This work characterizes reward function partial identifiability and its impact on policy optimization.

In this paper we consider the lens rigidity problem with partial data for conformal metrics in the presence of a magnetic field on a compact manifold of dimension $\geq 3$ with boundary. We show that one can uniquely determine the conformal factor and the magnetic field near a strictly convex (with respect to the magne…

Partial dependence curves (FPD) introduced by Friedman, are an important model interpretation tool, but are often not accessible to business analysts and scientists who typically lack the skills to choose, tune, and assess machine learning models. It is also common for the same partial dependence algorithm on the same …

Paper explores VRM for PSMLC with partially labeled medical images.

Study uses deep neural networks for inference in partially linear models with dependent data.

Two-dimensional Riemannian manifolds uniquely determined by boundary data.

Ranked data appear in many different applications, including voting and consumer surveys. There often exhibits a situation in which data are partially ranked. Partially ranked data is thought of as missing data. This paper addresses parameter estimation for partially ranked data under a (possibly) non-ignorable missing…

The paper presents a framework for estimating treatment effects using partial network data.

FDNet learns PDEs from data with fast predictions.

We prove uniqueness results for a Calderon type inverse problem for the Hodge Laplacian acting on graded forms on certain manifolds in three dimensions. In particular, we show that partial measurements of the relative-to-absolute or absolute-to-relative boundary value maps uniquely determine a zeroth order potential. T…

We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations. In this two part treatise, we present our developments in the context of solving two main classes …

A new deep metric learning method for defect classification in threaded pipe connections.

The article recovers tensor fields from partial data using weighted divergent ray transforms.

Robustly aligns datasets with partial GW distance to handle contamination.

Improved algorithm for partial recovery of tree-structured graphs with noisy data.

Proposes a topological model for partial equivariance in neural networks.

A new approach uses partial likelihood to improve tree-based density estimation and inference.

Proposes new methods for Markov chain choice models with panel data.

Reconstructing a planar domain from its Dirichlet-to-Neumann data

Develops a regression model for partially observed dynamic tensor data.

We solve the partial data Calderón problem for the connection Laplacian on Riemann surfaces.

New depth function for partial orders helps compare machine learning algorithms.

Deep learning within the context of point clouds has gained much research interest in recent years mostly due to the promising results that have been achieved on a number of challenging benchmarks, such as 3D shape recognition and scene semantic segmentation. In many realistic settings however, snapshots of the environ…

Proposes a method to create predictive sets from partially labeled data.

EnSF uses image inpainting to handle partial observations in data assimilation.

In this paper, we prove that there exists a dimensional constant $δ> 0$ such that given any background Kähler metric $ω$, the Calabi flow with initial data $u_0$ satisfying \begin{equation*} \partial \bar \partial u_0 \in L^\infty (M) \text{ and } (1- δ)ω< ω_{u_0} < (1+δ)ω, \end{equation*} admits a unique short time so…

FedAMD framework improves federated learning with partial client participation.

Automates discovering PDEs from data in dynamical systems.

We prove that the flat product metric on $D^n\times S^1$ is scattering rigid where $D^n$ is the unit ball in $\R^n$ and $n\geq 2$. The scattering data (loosely speaking) of a Riemannian manifold with boundary is map $S:U^+\partial M\to U^-\partial M$ from unit vectors $V$ at the boundary that point inward to unit vecto…

This paper demostrates a method for analysing almost CR geometries $(H,J)$, by uniquley defining a partially integrable structure $(H,K)$ from the same data. Thus two almost CR geometries $(H,J)$ and $(H',J')$ are equivalent if and and only if they generate isomorphic induced partially integrable CR geometries $(H,K)$ …

The paper calculates expected distances on partially oriented flag manifolds.

The paper explores partial identifiability in nonnegative matrix factorization under specific conditions.

Flexible DNN for survival data, avoiding proportional hazards assumption.

Let $B_1$ be the unit open disk in $\Real^2$ and $M$ be a closed Riemannian manifold. In this note, we first prove the uniqueness for weak solutions of the harmonic map heat flow in $H^1([0,T]\times B_1,M)$ whose energy is non-increasing in time, given initial data $u_0\in H^1(B_1,M)$ and boundary data $γ=u_0|_{\partia…

This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Mark…

Optimizes ranking of top-k players from partial comparison data.

The paper studies maps from pseudo-Hermitian to Kähler manifolds, proving harmonic map properties.

We present a simple, flexible, and general framework titled Partial Registration Network (PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning-based methods for registration, we use deep networks to tackle non-convexity of the alignment and partial correspondence problems. Whi…

This paper provides an analysis of the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data) in the context of reinforcement learning with partial observability. Our theoretical analysis formally characterizes that while potentially increasin…

New bounds for PDA using partial optimal transport improve domain alignment.

Annotating temporal relations (TempRel) between events described in natural language is known to be labor intensive, partly because the total number of TempRels is quadratic in the number of events. As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic …

CPPO learns policies from partial offline data in MDPs with structural assumptions.

Paper tackles group robustness with partially labeled data.

New method identifies causal variables from partially observed data.

Develops GNNs for incomplete graphs, improving learning from missing node attributes.

We propose a method to model multi-agent behaviors with limited observation and mechanical constraints.

In this paper, we examine the problem of approximating a general linear dimensionality reduction (LDR) operator, represented as a matrix $A \in \mathbb{R}^{m \times n}$ with $m < n$, by a partial circulant matrix with rows related by circular shifts. Partial circulant matrices admit fast implementations via Fourier tra…