arXiv research

This paper improves RL for PDE control with function-valued actions.

Study lenient regret and good-action identification in Gaussian process bandits.

Enhances neural networks with prior function values to improve accuracy.

Many biological characteristics of evolutionary interest are not scalar variables but continuous functions. Here we use phylogenetic Gaussian process regression to model the evolution of simulated function-valued traits. Given function-valued data only from the tips of an evolutionary tree and utilising independent pri…

NP-PROV separates mean and variance spaces to improve function uncertainty.

This paper provides a block coordinate descent algorithm to solve unconstrained optimization problems. In our algorithm, computation of function values or gradients is not required. Instead, pairwise comparison of function values is used. Our algorithm consists of two steps; one is the direction estimate step and the o…

FFBO optimizes functions as inputs and outputs, improving on existing BO methods.

New method reveals true causal functions in nonlinear time series, not just scores.

The study connects circle actions, trigonometric polynomials, and thickenings of metric spaces.

Improved RCPs for MABs using normalized weight functions.

New kernels capture both local and non-local interactions efficiently.

Using the theory of group action, we first introduce the concept of the automorphism group of an exponential family or a graphical model, thus formalizing the general notion of symmetry of a probabilistic model. This automorphism group provides a precise mathematical framework for lifted inference in the general expone…

Paper develops bandit algorithms for nonstationary nonconvex optimization.

Stochastic methods tackle inexact Hessian and gradient computations in large-scale non-convex optimization.

Sobolev training helps neural nets fit function values and derivatives.

LUNO linearizes neural operators to quantify their predictive uncertainty.

Study uncovers complex critical points in tensor decomposition.

We consider derivative-free algorithms for stochastic and non-stochastic convex optimization problems that use only function values rather than gradients. Focusing on non-asymptotic bounds on convergence rates, we show that if pairs of function values are available, algorithms for $d$-dimensional optimization that use …

Study risk-sensitive reinforcement learning with entropic risk measures and generative models.

Paper introduces a method for operator learning using random features.

Bayesian optimization (BO) aims to minimize a given blackbox function using a model that is updated whenever new evidence about the function becomes available. Here, we address the problem of BO under partially right-censored response data, where in some evaluations we only obtain a lower bound on the function value. T…

In spite of the recent surge of interest in quantile regression, joint estimation of linear quantile planes remains a great challenge in statistics and econometrics. We propose a novel parametrization that characterizes any collection of non-crossing quantile planes over arbitrarily shaped convex predictor domains in a…

A new one-point feedback scheme improves ZO algorithms for black-box optimization.

This paper conditions non-linear infinite-dimensional diffusion processes.

Deep, wide ConvResNets can approximate functions and their smoothness.

The paper extends mixability theory to function-valued forecasts, proving various loss functions are mixable.

New algorithms solve non-convex optimization problems efficiently.

Derives an approximation algorithm for continuous submodular maximization without derivative information.

Many problems in financial engineering involve the estimation of unknown conditional expectations across a time interval. Often Least Squares Monte Carlo techniques are used for the estimation. One method that can be combined with Least Squares Monte Carlo is the "Regress-Later" method. Unlike conventional methods wher…

Generative models for function-valued data in infinite dimensions.

Study risk-sensitive reinforcement learning with optimized certainty equivalents.

Study pricing options on forward contracts using infinite-dimensional affine models.

Based on Colombeau's theory of algebras of generalized functions we introduce the concepts of generalized functions taking values in differentiable manifolds as well as of generalized vector bundle homomorphisms. We study their basic properties, in particular with respect to some new point value concepts for generalize…

Monotonicity helps in safely optimizing unknown functions.

One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations. Gradient quantization has been proposed as an effecti…

New convergence rates for shuffling gradient methods without strong convexity.

New algorithms find near-stationary points in convex optimization.

Develops a new quadrature method for Lebesgue integrals.

Algorithm optimizes non-convex functions using dueling comparisons.

In this paper we present a nonparametric method for extending functional regression methodology to the situation where more than one functional covariate is used to predict a functional response. Borrowing the idea from Kadri et al. (2010a), the method, which support mixed discrete and continuous explanatory variables,…

In this paper, we investigate the attractive properties of the proximal gradient algorithm with inertia. Notably, we show that using alternated inertia yields monotonically decreasing functional values, which contrasts with usual accelerated proximal gradient methods. We also provide convergence rates for the algorithm…

Study revisits AdaGrad convergence with relaxed noise assumptions.

The study compares econometric and deep learning models for forecasting COMEX copper futures volatility.

Studied SGD convergence under weak conditions.

New algorithms solve complex minimax problems without needing derivatives.

New method certifies neural network function space norms from point evaluations.

Techniques known as Nonlinear Set Membership prediction, Lipschitz Interpolation or Kinky Inference are approaches to machine learning that utilise presupposed Lipschitz properties to compute inferences over unobserved function values. Provided a bound on the true best Lipschitz constant of the target function is known…

New study shows acceleration in hyperbolic spaces is impossible for strongly geodesically convex functions.