arXiv research

Paper proposes robust reinforcement learning method for better real-world application.

New method avoids saddle points without gradients.

CyBeR-0 optimizes federated learning with Byzantine resilience and reduced communication costs.

A new gradient estimator for online optimization with two function evaluations.

Study optimizes zero-order strongly convex function minimization with higher order smoothness.

New algorithm optimizes convex functions with noisy evaluations in one dimension.

We consider the closely related problems of bandit convex optimization with two-point feedback, and zero-order stochastic convex optimization with two function evaluations per round. We provide a simple algorithm and analysis which is optimal for convex Lipschitz functions. This improves on \cite{dujww13}, which only p…

The paper analyzes the efficiency of gradient estimation methods in noisy function evaluations.

The problem of resource allocation of nonlinear networked control systems is investigated, where, unlike the well discussed case of triggering for stability, the objective is optimal triggering. An approximate dynamic programming approach is developed for solving problems with fixed final times initially and then it is…

A new method for distributed optimization with noisy function evaluations.

We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-quadratic systems, and study various settings of driving noise and reward feedback. We show that these methods provably converge to within a…

We show that the eigenvalues of the intrinsic Dirac operator on the boundary of a Euclidean domain can be obtained as the limits of eigenvalues of Euclidean Dirac operators, either in the domain with a MIT-bag type boundary condition or in the whole space, with a suitably chosen zero order mass term.

Derivative-free method solves stochastic optimization problems with noisy objectives and constraints.

This paper tackles the computational complexity of finding approximate stationary points in non-convex optimization.

Improved analysis and new algorithm for gradient-free optimization of smooth functions.

A stochastic model for pure-jump diffusion (the compound renewal process) can be used as a zero-order approximation and as a phenomenological description of tick-by-tick price fluctuations. This leads to an exact and explicit general formula for the martingale price of a European call option. A complete derivation of t…

We propose a novel interpretation of the collapsed variational Bayes inference with a zero-order Taylor expansion approximation, called CVB0 inference, for latent Dirichlet allocation (LDA). We clarify the properties of the CVB0 inference by using the alpha-divergence. We show that the CVB0 inference is composed of two…

Formula for Masur-Veech volumes in quadratic differentials with odd zeros.

This paper explores optimising acquisition functions in Bayesian optimisation.

In this small note we use results derived in Berestycki et al. to correct the celebrated formulae of Hagan et al. We derive explicitly the correct zero order term in the expansion of the implied volatility in time to maturity. The new term is consistent as $β\to 1$. Furthermore, numerical simulations show that it reduc…

Paper tackles dynamic pricing in a geometrically decaying environment, achieving better occupancy with lower rates.

Gradient-free optimization for additive models achieves optimal error.

New framework converts multi-objective to single-objective optimisation.

Unified Bayesian Optimisation for mixed variables improves performance.

A new method learns priors for Bayesian optimisation to improve performance.

The superior interpretability and uncertainty modeling ability of Takagi-Sugeno-Kang fuzzy system (TSK FS) make it possible to describe complex nonlinear systems intuitively and efficiently. However, classical TSK FS usually adopts the whole feature space of the data for model construction, which can result in lengthy …

The purpose of this paper is to prove the a priori estimates for constant scalar curvature Kaehler metrics with conic singularities along normal crossing divisors. The zero order estimates are proved by a reformulated version of Alexandrov's maximum principle. The higher order estimates follow from Chen-Cheng's frame …

Study improves Bayesian optimisation with ensemble transfer learning.

AdamZ optimiser improves neural network training efficiency.

Wind farm layout optimisation tackles space constraints with Bayesian multi-objective approach.

Book covers tools for zeroth-order convex optimisation.

Bayesian optimisation tackles high-dimensional categorical and mixed search spaces.

O3 optimizes samples from generative models without extra training.

A new optimisation method efficiently scales Hessian-vector products for neural networks.

Bayesian optimisation framework for graph functions.

Bayesian optimisation tackles expensive black-box functions with constraints.

MTL2L learns to adapt optimisation rules for unseen data.

Real world experiments are expensive, and thus it is important to reach a target in minimum number of experiments. Experimental processes often involve control variables that changes over time. Such problems can be formulated as a functional optimisation problem. We develop a novel Bayesian optimisation framework for s…

We consider spaces of smooth immersed plane curves (modulo translations and/or rotations), equipped with reparameterization invariant weak Riemannian metrics involving second derivatives. This includes the full $H^2$-metric without zero order terms. We find isometries (called $R$-transforms) from some of these spaces i…

Information-theoretic Bayesian optimisation techniques have demonstrated state-of-the-art performance in tackling important global optimisation problems. However, current information-theoretic approaches require many approximations in implementation, introduce often-prohibitive computational overhead and limit the choi…

Bayesian optimisation algorithm for unknown search spaces with sub-linear regret.

New methods improve global optimisation for expensive functions using lookahead strategies.

Unified algorithm for stochastic optimization with time-varying momentum converges under general conditions.

Deep Optimisation (DO) combines evolutionary search with Deep Neural Networks (DNNs) in a novel way - not for optimising a learning algorithm, but for finding a solution to an optimisation problem. Deep learning has been successfully applied to classification, regression, decision and generative tasks and in this paper…

One-pass optimisation for high-dimensional hyperparameters.

Bayesian optimisation is improved by incorporating expert prior through space warping.

We present an efficient block-diagonal ap- proximation to the Gauss-Newton matrix for feedforward neural networks. Our result- ing algorithm is competitive against state- of-the-art first order optimisation methods, with sometimes significant improvement in optimisation performance. Unlike first-order methods, for whic…

A novel optimisation framework through quadratic nonlinear projection is introduced for credit portfolio when the portfolio risk is measured by Conditional Value-at-Risk (CVaR). The whole optimisation procedure to search toward the optimal portfolio state is conducted by a series of single-step optimisations under the …