arXiv research

Study shows long-term solutions for complex equations on curved spaces.

New neural network models for functional data.

Papers learn from data to make decisions without interacting, improving on previous methods.

ENIAC method optimizes and explores complex RL problems with non-linear policies.

New neural network models for complex functional data analysis.

Quantum computing offers a quadratic speedup for estimating non-linear functionals.

New method for interpreting non-linear models using forward marginal effects.

New method optimizes non-linear functionals over probability measures.

New algorithm tackles non-linear utility in MNL bandits with $ilde{O}(\sqrt{T})$ regret.

New particle-based VI algorithm expands function class and improves scalability.

In that paper, we provide a new characterization of the solutions of specific reflected backward stochastic differential equations (or RBSDEs) whose driver $g$ is convex and has quadratic growth in its second variable: this is done by introducing the extended notion of $g$-Snell enveloppe. Then, in a second step, we re…

Adaptive NN method improves matrix completion for non-smooth data.

We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure or G-mean, and constrained training problems where the classifier needs to sati…

We study a non-linear statistical inverse learning problem, where we observe the noisy image of a quantity through a non-linear operator at some random design points. We consider the widely used Tikhonov regularization (or method of regularization, MOR) approach to reconstruct the estimator of the quantity for the non-…

The one-class kernel spectral regression (OC-KSR), the regression-based formulation of the kernel null-space approach has been found to be an effective Fisher criterion-based methodology for one-class classification (OCC), achieving state-of-the-art performance in one-class classification while providing relatively hig…

This paper proposes a new method to learn integration schemes for complex ODEs.

Broadens Jourdain and Martini's method to non-linear stochastic processes.

We propose a computationally efficient estimator, formulated as a convex program, for a broad class of non-linear regression problems that involve difference of convex (DC) non-linearities. The proposed method can be viewed as a significant extension of the "anchored regression" method formulated and analyzed in [10] f…

Let $(X,d,μ)$ be a complete metric measure space, with $μ$ a locally doubling measure, that supports a local weak $L^2$-Poincaré inequality. By assuming a heat semigroup type curvature condition, we prove that Cheeger-harmonic functions are Lipschitz continuous on $(X,d,μ)$. Gradient estimates for Cheeger-harmonic func…

Paper solves complex equations on noncompact manifolds.

The paper introduces a non-linear version of the process convolution formalism for building covariance functions for multi-output Gaussian processes. The non-linearity is introduced via Volterra series, one series per each output. We provide closed-form expressions for the mean function and the covariance function of t…

New framework for analyzing games with multi-dimensional singular controls and non-linear jumps.

Optimal algorithms for non-linear ridge bandits reduce burn-in cost.

We consider that the price of a firm follows a non linear stochastic delay differential equation. We also assume that any claim value whose value depends on firm value and time follows a non linear stochastic delay differential equation. Using self-financed strategy and replication we are able to derive a Random Partia…

Enhances Cox model for survival analysis with symbolic non-linear log-risk functions.

We show how the tangent functor extends from ordinary smooth maps to "microformal morphisms" (also called "thick morphisms") of supermanifolds. Microformal morphisms generalize ordinary maps and correspond to formal canonical relations between the cotangent bundles specified by generating functions depending on positio…

We study the existence of solutions of the non-linear differential equations on the compact Riemannian manifolds $(M^n,g), n\geq 2$, Δ_p u + a(x)u^{p-1} = λf(u,x), (E2) where $Δ_p$ is the $p-$laplacian, with $1<p<n$. The equation (E2) generalizes a equation considered by Aubin, where he has considered, a compact Rieman…

Privacy concern has been increasingly important in many machine learning (ML) problems. We study empirical risk minimization (ERM) problems under secure multi-party computation (MPC) frameworks. Main technical tools for MPC have been developed based on cryptography. One of limitations in current cryptographically priva…

This paper studies a class of exponential family models whose canonical parameters are specified as linear functionals of an unknown infinite-dimensional slope function. The optimal minimax rates of convergence for slope function estimation are established. The estimators that achieve the optimal rates are constructed …

Bayesian neural networks improve uncertainty quantification in non-linear dimensionality reduction.

The paper tackles noisy combinations of continuous and step functions, providing conditions for their identification.

Paper establishes estimates for solutions on compact manifolds.

Optimizes non-linear outcomes from summed contributions.

Adequate evaluation of an information retrieval system to estimate future performance is a crucial task. Area under the ROC curve (AUC) is widely used to evaluate the generalization of a retrieval system. However, the objective function optimized in many retrieval systems is the error rate and not the AUC value. This p…

A new model explains asset returns with a single factor, improving cross-sectional performance.

We address the problem of causal discovery from data, making use of the recently proposed causal modeling framework of modular structural causal models (mSCM) to handle cycles, latent confounders and non-linearities. We introduce σ-connection graphs (σ-CG), a new class of mixed graphs (containing undirected, bidirected…

Study Nash equilibrium in non-zero-sum game with Bermudan strategies.

Traditional linear methods for forecasting multivariate time series are not able to satisfactorily model the non-linear dependencies that may exist in non-Gaussian series. We build on the theory of learning vector-valued functions in the reproducing kernel Hilbert space and develop a method for learning prediction func…

Study non-linear combinatorial bandits with polynomial rewards, finding significant differences from linear cases.

We derive a priori estimates for solutions of a general class of fully non-linear equations on compact Hermitian manifolds. Our method is based on ideas that have been used for different specific equations, such as the complex Monge-Ampère, Hessian and inverse Hessian equations. As an application we solve a class of He…

In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-disti…

Analyzes Hessian spectrum for neural networks near optimal learning.

We prove a complete family of `cylindrical estimates' for solutions of a class of fully non-linear curvature flows, generalising the cylindrical estimate of Huisken-Sinestrari for the mean curvature flow. More precisely, we show that, for the class of flows considered, an $(m+1)$-convex ($0\leq m\leq n-2$) solution bec…

The goal of a recommendation system is to predict the interest of a user in a given item by exploiting the existing set of ratings as well as certain user/item features. A standard approach to modeling this problem is Inductive Matrix Completion where the predicted rating is modeled as an inner product of the user and …

Let $(M^n,g),~n\ge 3$ be a noncompact complete Riemannian manifold with compact boundary and $f$ a smooth function on $\partial M$. In this paper we show that for a large class of such manifolds, there exists a metric within the conformal class of $g$ that is complete, has zero scalar curvature on $M$ and has mean curv…

Unified diffusive bounds for non-linear parabolic equations.

Unified theory of $θ$-expectations derived from chaotic dynamics.

Study proves global existence and decay for complex wave equations.