A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Optimizes function networks by selectively evaluating parts of the network, reducing costs.
Real-world optimization problems often have expensive objective functions in terms of cost and time. It is desirable to find near-optimal solutions with very few function evaluations. Surrogate-assisted optimizers tend to reduce the required number of function evaluations by replacing the real function with an efficien…
Accelerates Bayesian optimization of function networks with partial evaluations.
Grading function evaluates Bach-style chorales, outperforming human experts.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
Counterfactual evaluation of novel treatment assignment functions (e.g., advertising algorithms and recommender systems) is one of the most crucial causal inference problems for practitioners. Traditionally, randomized controlled trials (A/B tests) are performed to evaluate treatment assignment functions. However, such…
Neural programming involves training neural networks to learn programs, mathematics, or logic from data. Previous works have failed to achieve good generalization performance, especially on problems and programs with high complexity or on large domains. This is because they mostly rely either on black-box function eval…
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…
In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate mentor, we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Computer Chess …
ECP optimizes expensive functions without knowing Lipschitz constant.
New method for off-policy evaluation in POMDPs using future-dependent value functions.
A new algorithm optimizes time-varying functions with non-constant evaluation times.
New method for evaluating policies in complex decision-making models with hidden variables.
Cost-aware BO minimizes function evaluations with varying costs.
The notion of expense in Bayesian optimisation generally refers to the uniformly expensive cost of function evaluations over the whole search space. However, in some scenarios, the cost of evaluation for black-box objective functions is non-uniform since different inputs from search space may incur different costs for …
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.
We propose a Bayesian optimization algorithm for objective functions that are sums or integrals of expensive-to-evaluate functions, allowing noisy evaluations. These objective functions arise in multi-task Bayesian optimization for tuning machine learning hyperparameters, optimization via simulation, and sequential des…
Study evaluates policies in partially observable environments without full model specification.
New RL method learns value function for many policies using few key states.
FunBO uses LLMs to discover effective acquisition functions for Bayesian optimization.
Adaptive replication improves stochastic function optimization.
A tutorial on optimizing complex functions with partial knowledge.
Bayesian optimization is an approach to optimizing objective functions that take a long time (minutes or hours) to evaluate. It is best-suited for optimization over continuous domains of less than 20 dimensions, and tolerates stochastic noise in function evaluations. It builds a surrogate for the objective and quantifi…
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…
Study calculates mass of special polyhedra in hyperbolic space.
Greedy algorithms which use only function evaluations are applied to convex optimization in a general Banach space . 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.
A new estimator for evaluating policies in unknown environments.
Reconstructing polytopes with fixed facet directions from support function evaluations.
Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications. This alone presents a challenge in many areas of artificial intelligence. In this …
Bayesian optimization (BO) is a class of sample-efficient global optimization methods, where a probabilistic model conditioned on previous observations is used to determine future evaluations via the optimization of an acquisition function. Most acquisition functions are myopic, meaning that they only consider the impa…
AIS method improves estimation of RBM partition function 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.
In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to directly optimize the evaluation metric. We propose a sample efficient reinforceme…
BOSH optimizes functions with stochastic evaluations more efficiently and precisely.
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…
This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history generated by unknown behavioral policies. We study a regression-based fitted Q iter…
This paper proposes automatic tuning of Bayesian Optimization's acquisition function.
The paper tackles noisy multi-armed bandit problems with improved regret guarantees.
Bayesian optimization (BO) and its batch extensions are successful for optimizing expensive black-box functions. However, these traditional BO approaches are not yet ideal for optimizing less expensive functions when the computational cost of BO can dominate the cost of evaluating the blackbox function. Examples of the…
EPIC quantifies reward differences without policy optimization.
The paper proposes a technique to speed up evolutionary algorithms by using lower-cost approximations of the objective function.
Q-MMR evaluates policies using reweighted rewards and moment matching.
VA-OPE improves OPE by incorporating variance information, achieving tighter error bounds.
Certified algorithms optimize functions with varying costs, providing error bounds.
New bounds using samplewise evaluated CMI for deep neural networks.