arXiv research

Novel framework finds globally optimal energy-efficient power control in wireless networks.

Proposes glocal hypergradient estimation for hyperparameter optimization.

HALO uses local Lipschitz constants to optimize functions efficiently.

Develops an SSBO algorithm for global optimization of expensive models.

Efficient algorithm for global optimization of multivariate Lipschitz functions.

TREGO improves EGO for global optimization of high-dimensional problems.

Bayesian optimization improved for large-scale problems.

Some methods based on simple regularizing geometric element transformations have heuristically been shown to give runtime efficient and quality effective smoothing algorithms for meshes. We describe the mathematical framework and a systematic approach to global optimization-based versions of such methods for mixed volu…

Bayesian Optimization (BO) has become a core method for solving expensive black-box optimization problems. While much research focussed on the choice of the acquisition function, we focus on online length-scale adaption and the choice of kernel function. Instead of choosing hyperparameters in view of maximum likelihood…

StochasticRank optimizes ranking metrics efficiently and guarantees global convergence.

New framework optimizes complex systems decisions via simulation.

New algorithm optimizes Hölder continuous functions efficiently.

SOBER optimizes and quadrates efficiently in parallel for diverse tasks.

Robust estimation methods find global minima efficiently via quasi-gradients.

Bayesian optimization reduces computational effort in aircraft design optimization.

Combines global and local search for efficient global optimization with Gaussian processes.

Efficient binary sampling method for global optimization of univariate functions with low regret.

GOPC algorithm finds global optimal clusters efficiently.

New perspective on federated learning as posterior inference, improving optimization.

Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently. Conventional DL solvers, however, have not been developed intentionally to seek for such global optimality. In this paper we propose a novel approximation algorithm, BPGrad, towards optimizing deep models glo…

Optimizes expensive experiments by incorporating expert knowledge.

Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.

A new algorithm optimizes Gaussian process posterior mean functions efficiently.

We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, and despite recent progress, our understanding of this loss surface is still incomplete. For deep linear networks, we present necessary and s…

Improves Bayesian optimization using Gaussian process Thompson sampling.

Mixed membership factorization is a popular approach for analyzing data sets that have within-sample heterogeneity. In recent years, several algorithms have been developed for mixed membership matrix factorization, but they only guarantee estimates from a local optimum. Here, we derive a global optimization (GOP) algor…

Contemporary global optimization algorithms are based on local measures of utility, rather than a probability measure over location and value of the optimum. They thus attempt to collect low function values, not to learn about the optimum. The reason for the absence of probabilistic global optimizers is that the corres…

LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.

Adaptive personalized federated learning improves local model personalization.

Paper proposes a new method for efficient hyperparameter optimization.

Bayesian optimization is a powerful global optimization technique for expensive black-box functions. One of its shortcomings is that it requires auxiliary optimization of an acquisition function at each iteration. This auxiliary optimization can be costly and very hard to carry out in practice. Moreover, it creates ser…

New AI algorithm improves multi-layer optical film design efficiency.

A new L-BFGS method tackles large-scale optimization with fewer evaluations.

GLIS uses IDW and RBF for efficient global optimization.

New method trains quantized neural networks to global optimality.

New method optimizes Bayesian optimization for high-dimensional posterior samples.

This paper analyzes local optimizers in Bayesian optimization for expensive functions.

Regularization affects sample efficiency in neural nets, as shown by a specific example.

Bayesian optimization improves efficiency with semi-supervised learning.

Advocates a local feedback approach for RL in unknown systems.

Enhances BO in high dimensions with Newton methods.

ECPv2 optimizes Lipschitz functions efficiently and scalably.

The paper provides global optimization algorithms for two particularly difficult nonconvex problems raised by hybrid system identification: switching linear regression and bounded-error estimation. While most works focus on local optimization heuristics without global optimality guarantees or with guarantees valid only…

Proposes efficient FOBO algorithms for global maxima of expensive functions.

LOAD discovers optimal adjustments locally for scalable causal inference.

We propose a novel information-theoretic approach for Bayesian optimization called Predictive Entropy Search (PES). At each iteration, PES selects the next evaluation point that maximizes the expected information gained with respect to the global maximum. PES codifies this intractable acquisition function in terms of t…

Bayesian optimization improves with nonstationary covariance functions.

Efficiently learns distributions corrupted by both global and local adversarial modifications.