Optimizes function networks by selectively evaluating parts of the network, reducing costs.
problem Optimizing expensive function networks where full evaluations are costly.
method Knowledge gradient acquisition function for cost-aware partial evaluations.
result Outperforms existing BOFN methods and benchmarks across various problems.
Genetic algorithms optimize chess evaluation functions with mentor assistance.
problem Optimizing complex evaluation functions for superior performance.
method Genetic algorithms with mentor-assisted evolution.
result Programs evolved with mentors outperform top chess champions.
Accelerates Bayesian optimization of function networks with partial evaluations.
problem Optimizing expensive-to-evaluate function networks with varying node costs.
method Proposes an accelerated algorithm that uses global Monte Carlo simulations to select node-specific candidate inputs.
result Achieves up to a 16x speedup over the original p-KGFN algorithm while maintaining competitive query efficiency.
New method improves SACOBRA's performance on high-conditioning optimization problems.
problem High-conditioning optimization problems with expensive objective functions.
method Online whitening applied to SACOBRA in the black-box optimization paradigm.
result Online whitening reduces optimization error by a factor of 10 to 1e12 compared to plain SACOBRA.
CONE evaluates treatment assignment functions using networked observational data to mitigate hidden confounding bias.
problem Evaluate treatment assignment functions using networked observational data with hidden confounders.
method CONE framework that learns partial representations of latent confounders and combines them for counterfactual evaluation.
result Network information mitigates hidden confounding bias in counterfactual evaluation.
Grading function evaluates Bach-style chorales, outperforming human experts.
problem Difficulty in automatically evaluating musical style correctness.
method Introduces a grading function for evaluating four-part chorales in the style of J.S. Bach.
result Transformer model output is outperformed by the grading function at discriminating Bach chorales.
Framework combines symbolic expressions and black-box function evaluations for neural programming.
problem Lack of generalization performance on complex programs and large domains.
method Tree LSTMs and tree encoding for integrating symbolic expressions and function evaluations.
result Framework achieves high accuracies and better generalization to higher depth expressions.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
Bayesian optimization speeds up function optimization over long evaluation times.
problem Optimizing functions that take long to evaluate over continuous domains.
method Bayesian approach using Gaussian process regression and acquisition functions.
result Bayesian optimization can handle stochastic noise and multiple optimization tasks.
The paper discusses challenges and proposed solutions for evaluating model explanations.
problem Challenges in evaluating model explanations for interpretability.
method Proposes a distinction between descriptive and persuasive explanations and discusses potential research directions.
result Evaluating model explanations using functional metrics may perpetuate cognitive bias.
Paper evolves a grandmaster-level chess evaluation function.
problem Creating a chess program that can play at grandmaster level.
method Combining supervised and unsupervised learning with genetic algorithms.
result The evolved program outperforms a two-time World Computer Chess Champion.
Cost-aware multi-objective Bayesian optimization for non-uniformly expensive functions.
problem Non-uniform cost of function evaluations in Bayesian optimization.
method Introduces cost-aware constraints and a new acquisition function to optimize multi-objective functions with varying costs.
result Demonstrates improved optimization in hyperparameter tuning of neural networks and random forests.
This paper optimizes off-policy evaluation in reinforcement learning with function approximation.
problem Estimating cumulative value of a new policy from logged data generated by an unknown policy.
method Regression-based fitted Q iteration method, equivalent to estimating conditional mean embedding of transition operator.
result The method is minimax-optimal, with nearly minimal estimation error.
This paper provides lower bounds on the convergence rate of Derivative Free Optimization (DFO) with noisy function evaluations, exposing a fundamental and unavoidable gap between the performance of algorithms with access to gradients and those with access to only function evaluations. However, there are situations in w…
SVRG reduces gradient evaluations for policy evaluation in reinforcement learning.
problem Policy evaluation in reinforcement learning with high computational costs.
method Two variants of SVRG for policy evaluation that reduce gradient calculations.
result Significant reduction in the number of gradient evaluations while preserving linear convergence speed.
Adaptive loss function improves performance by aligning training and evaluation metrics.
problem Loss-metric mismatch in machine learning training.
method Adaptive loss alignment through meta-learning of a dynamic loss function.
result Significant performance improvements across various tasks and data.
Expert-driven genetic algorithms improve chess evaluation functions.
problem Creating efficient evaluation functions for complex systems.
method Using genetic algorithms with expert guidance to evolve evaluation functions.
result Evolved programs outperform top chess programs with fewer parameters.
ε-shotgun optimizes expensive function evaluations in parallel.
problem Optimizing expensive black-box functions efficiently.
method ε-greedy batch Bayesian optimisation.
result ε-shotgun outperforms state-of-the-art batch methods.
ECP optimizes expensive functions without knowing Lipschitz constant.
problem Optimizing expensive, non-convex functions with unknown Lipschitz constants.
method ECP minimizes evaluations by focusing on potentially optimal regions, eliminating Lipschitz constant estimation.
result Guaranteed no-regret performance and minimax-optimal regret bounds.
New method for off-policy evaluation in POMDPs using future-dependent value functions.
problem Curse of horizon in off-policy evaluation for POMDPs.
method Develops future-dependent value functions and minimax learning method.
result PAC result and Bellman completeness for the proposed OPE estimator.
A new algorithm optimizes time-varying functions with non-constant evaluation times.
problem Optimizing functions that change over time with varying evaluation times.
method Proposes a novel time-varying Bayesian optimization algorithm.
result Establishes a regret bound for the proposed algorithm.
Paper evaluates squared-exponential covariance function for Gaussian processes with integral observations.
problem Evaluating double line integrals of the squared exponential covariance function in Gaussian processes.
method Proposes a new approach to reduce double integrals to a single integral using the error function and efficiently computed with numerical techniques.
result Shows superior numerical robustness and accuracy compared to existing methods.
New method for evaluating policies in complex decision-making models with hidden variables.
problem Evaluating policies in partially observable Markov decision processes with hidden confounders.
method Introduces novel identification methods and minimax estimation techniques for linking target policy's value and observed data distribution.
result Proposes three estimators for off-policy evaluation in POMDPs with latent confounders, demonstrating their effectiveness through nonasymptotic and asymptotic analysis.
Cost-aware BO minimizes function evaluations with varying costs.
problem Optimization with varying evaluation costs in expensive functions.
method Cost Apportioned Bayesian Optimization (CArBO) combining initial and cost-cooled phases.
result CArBO finds better hyperparameter configurations with the same cost budget.
We present an information-theoretic framework for solving global black-box optimization problems that also have black-box constraints. Of particular interest to us is to efficiently solve problems with decoupled constraints, in which subsets of the objective and constraint functions may be evaluated independently. For …
Novel CE-method variants reduce local minima convergence with fewer function evaluations.
problem Local minima and expensive function evaluations in optimization.
method Surrogate model-based CE-method variants to reduce local minima convergence.
result Surrogate model-based approach reduces local minima convergence using fewer function evaluations.
Study evaluates policies in partially observable environments without full model specification.
problem Evaluating policies in partially observable environments without full model specification.
method Developed non-parametric identification and recursive fitted-Q-evaluation algorithm.
result Established finite-sample error bounds for policy value estimation.
New RL method learns value function for many policies using few key states.
problem Evaluate and improve policies in continuous control problems.
method Combines actor-critic architecture and policy embedding to learn a single value function for many policies.
result Value function minimizes prediction error by learning a small set of 'probing states' and their impact on policies' returns.
FunBO uses LLMs to discover effective acquisition functions for Bayesian optimization.
problem Designing optimal acquisition functions for Bayesian optimization across diverse problems.
method FunBO leverages FunSearch, an LLM, to learn and evaluate new acquisition functions.
result FunBO discovers acquisition functions that generalize well and outperform existing methods.
Adaptive replication improves stochastic function optimization.
problem Challenges in accurately estimating functions with high variance.
method Trust-region-based Bayesian optimization with adaptive replication.
result Adaptive replication substantially improves solution accuracy and efficiency.
A tutorial on optimizing complex functions with partial knowledge.
problem Optimizing functions with limited or partial information.
method Grey-box Bayesian optimization, blending black-box and white-box approaches.
result Improves optimization performance by leveraging internal information.
Paper develops a method to highlight influential transitions for off-policy evaluation.
problem Validating off-policy evaluation in high-stakes settings.
method Highlight influential transitions, develop influence functions for Q-evaluation.
result Method can identify limitations and make evaluation more robust.
Bayesian optimization for expensive integrands achieves optimal performance.
problem Optimizing functions with expensive integrands in noisy conditions.
method Bayesian optimization with discretization-free value of information optimization.
result Achieves optimal performance in noisy and smooth conditions.
We introduce a fully coherent spin network amplitude whose expansion generates all SU(2) spin networks associated with a given graph. We then give an explicit evaluation of this amplitude for an arbitrary graph. We show how this coherent amplitude can be obtained from the specialization of a generating functional obtai…
Greedy algorithms which use only function evaluations are applied to convex optimization in a general Banach space X. Along with algorithms that use exact evaluations, algorithms with approximate evaluations are treated. A priori upper bounds for the convergence rate of the proposed algorithms are given. These bounds…
BOOST automates kernel and acquisition function selection in Bayesian optimization.
problem Inappropriate kernel and acquisition function combinations lead to poor performance in Bayesian optimization.
method BOOST uses offline evaluation to predict and select the best kernel-acquisition function pair.
result BOOST consistently improves over fixed-hyperparameter BO and is competitive with state-of-the-art adaptive methods.
Novel kernelized LSTD method improves Q-function approximation in RL.
problem Improving policy evaluation in reinforcement learning.
method Manifold regularization applied to kernelized LSTD.
result Superior performance in Q-function approximation compared to existing methods.
Study calculates mass of special polyhedra in hyperbolic space.
problem Evaluating mass in hyperbolic geometry.
method Used upper half space model and special polyhedra.
result Evaluated mass functional on polyhedra.
New method uses noisy function evaluations for sampling Langevin diffusions.
problem Difficulty in obtaining gradient evaluations for Langevin diffusions.
method Stochastic zeroth-order discretizations of Langevin diffusions using Gaussian Stein's identities.
result Comprehensive sample complexity analysis for both overdamped and underdamped Langevin diffusions.
A new estimator for evaluating policies in unknown environments.
problem Evaluating policies when both logging policy and value function are unknown.
method Doubly-Robust (DR) off-policy evaluation (OPE) estimator, DRUnknown, that estimates both the logging policy and value function.
result DRUnknown achieves the smallest asymptotic variance and is optimal when both models are correctly specified.
Reconstructing polytopes with fixed facet directions from support function evaluations.
problem Reconstructing polytopes with known facet directions from limited data.
method Least-squares estimate via convex quadratic program, combinatorial characterization for uniqueness, algorithm convergence.
result The least-squares estimate for a fixed simplicial normal fan is a convex quadratic program, and the solution is unique under certain conditions.
New methods for off-policy evaluation in reinforcement learning.
problem Improving off-policy evaluation in reinforcement learning.
method Developed MWL and MQL estimators for importance weights and value functions.
result MWL and MQL provide a unified view of algorithms in reinforcement learning.
AIS method improves estimation of RBM partition function with reduced computational cost.
problem Efficiently estimating partition function of RBMs for large systems.
method Annealed Importance Sampling (AIS) with optimized initialization.
result Good estimation of partition function Z with reduced computational cost.
We present PESMO, a Bayesian method for identifying the Pareto set of multi-objective optimization problems, when the functions are expensive to evaluate. The central idea of PESMO is to choose evaluation points so as to maximally reduce the entropy of the posterior distribution over the Pareto set. Critically, the PES…
The paper analyzes the sample complexities for policy evaluation with linear function approximation.
problem Policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
method Investigates sample complexities for two policy evaluation algorithms: TD and TDC.
result Establishes high-probability sample complexity bounds for policy evaluation algorithms.
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…
BOSH optimizes functions with stochastic evaluations more efficiently and precisely.
problem Optimizing functions with noisy evaluations can lead to suboptimal solutions.
method BOSH uses a hierarchical Gaussian process to generate a growing pool of realizations.
result BOSH provides more efficient and higher-precision optimization than standard BO.
This paper proposes automatic tuning of Bayesian Optimization's acquisition function.
problem Optimizing black-box functions with noisy, expensive evaluations and hyperparameter tuning.
method Exploring heuristics to automatically tune acquisition functions in Bayesian Optimization.
result Demonstrates effectiveness of heuristics in automatic Bayesian Optimization.