LES reduces over-exploration in LSO, improving solution quality.
problem Over-exploration in LSO leads to unrealistic solutions.
method LES uses a decoder's approximation of the data distribution to mitigate over-exploration.
result LES enhances solution quality while maintaining high objective values.
The paper extends physics-based information maximization to complex bandit problems.
problem Designing efficient decision-making policies for complex bandit problems.
method Information and free-energy maximization principles adapted to three distinct bandit types.
result Information maximization leads to strong performance in complex bandit problems.
Bayesian optimization (BO) is a global optimization strategy designed to find the minimum of an expensive black-box function, typically defined on a compact subset of Rd, by using a Gaussian process (GP) as a surrogate model for the objective. Although currently available acquisition functions address this…
We address the challenge of effective exploration while maintaining good performance in policy gradient methods. As a solution, we propose diverse exploration (DE) via conjugate policies. DE learns and deploys a set of conjugate policies which can be conveniently generated as a byproduct of conjugate gradient descent. …
We study the effects of approximate inference on the performance of Thompson sampling in the k-armed bandit problems. Thompson sampling is a successful algorithm for online decision-making but requires posterior inference, which often must be approximated in practice. We show that even small constant inference error …
This paper solves the best arm identification problem with both quick commitment and reward maximization.
problem Simultaneously identifying the best arm and minimizing regret in a stochastic Multi-Armed Bandit problem.
method Introduces Regret Optimal Best Arm Identification (ROBAI) and presents algorithms EOCP and its variants.
result Achieves asymptotic optimal regret and quick commitment to the optimal arm in both pre-determined and adaptive stopping times.
Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration inequalities, which thus lead to over-exploration. In this paper, we propose a n…
In this paper, we consider the distributed stochastic multi-armed bandit problem, where a global arm set can be accessed by multiple players independently. The players are allowed to exchange their history of observations with each other at specific points in time. We study the relationship between regret and communica…
Standard acquisition functions are sufficient for asynchronous Bayesian optimization.
problem Redundant and repeated queries in asynchronous Bayesian optimization.
method Conceptual analysis and theoretical guarantees of standard acquisitions.
result Standard acquisition functions achieve theoretical guarantees equivalent to Thompson sampling in asynchronous settings.
Local search improves GFlowNets' ability to generate high-reward samples.
problem GFlowNets struggle with over-exploration in high-reward space.
method Local search focusing on high-reward samples via backtracking and reconstruction.
result Significant performance improvement in biochemical tasks.
Enhances BO in high dimensions with Newton methods.
problem Challenges in scaling BO to high-dimensional spaces.
method Construct multiple local quadratic models using gradients and Hessians from a global GP, and select new sample points by solving bound-constrained quadratic programs.
result Outperforms existing high-dimensional BO techniques on synthetic and real-world applications.
Boundary effects inflate variance in Gaussian processes, leading to acquisition bias.
problem Boundary-induced acquisition bias in Gaussian processes.
method Traced root cause to geometric mechanism of kernel truncation at domain boundaries.
result Boundary effects create distortion that worsens with dimensionality, affecting acquisition behavior.
The paper improves experimental design by weighting diversity metrics with quality, leading to more diverse and effective discoveries.
problem Existing experimental design techniques favor exploitation over exploration, leading to local optima and insufficient diversity.
method The paper extends Vendi scores to account for quality and applies them to various experimental design problems.
result Quality-weighted Vendi scores allow for better balance between quality and diversity, resulting in 70%-170% more effective discoveries.
This paper improves Bayesian optimization methods with tighter regret bounds and practical solutions.
problem Improving Bayesian optimization methods with tighter regret bounds and practical solutions.
method The paper analyzes and compares different acquisition functions (GP-UCB, TS, PIMS) to achieve tighter Bayesian cumulative regret bounds and address practical issues.
result PIMS achieves the tighter BCR bound and avoids hyperparameter tuning, unlike GP-UCB and TS.
Although exploration in reinforcement learning is well understood from a theoretical point of view, provably correct methods remain impractical. In this paper we study the interplay between exploration and approximation, what we call approximate exploration. Our main goal is to further our theoretical understanding of …
End-to-end learnable Gaussian mixture priors improve diffusion models' exploration and expressiveness.
problem Challenges in diffusion models when priors differ from target distributions.
method End-to-end learnable Gaussian mixture priors (GMPs) with iterative refinement.
result Significant performance improvements across various benchmark problems.
Bayesian optimization and Lipschitz optimization have developed alternative techniques for optimizing black-box functions. They each exploit a different form of prior about the function. In this work, we explore strategies to combine these techniques for better global optimization. In particular, we propose ways to use…
Study on utility maximization with Tsallis entropy in reinforcement learning.
problem Exploring utility maximization with Tsallis entropy in reinforcement learning.
method Introducing Tsallis entropy regularizer to induce exploration, investigating specific examples, characterizing well-posedness, designing reinforcement learning algorithm.
result Characterized well-posedness and provided semi-closed-form solutions for specific examples, found distinct optimal strategies.
Tr-LinUCB reduces regret in stochastic linear bandits by truncating exploration.
problem Over-exploration in LinUCB leads to suboptimal cumulative regret.
method Proposes Tr-LinUCB, a truncated version of LinUCB.
result Achieves O(dlog(T)) regret with S=Cdlog(T), matching lower bound. New algorithm reduces regret by focusing on near-optimal actions.
problem Regret minimization in multi-armed bandits leads to over-exploitation.
method Proposes a lenient regret criterion and a new algorithm, ε-TS.
result ε-TS achieves asymptotic optimality in lenient regret.
Bayesian optimisation improves with fully-Bayesian treatment of hyperparameters.
problem Overconfident model predictions in BO due to ignoring hyperparameter uncertainty.
method Investigate FBBO using three approximate inference schemes compared to maximum likelihood approach.
result FBBO using EI with an ARD kernel leads to best performance in noise-free setting.
New algorithm reduces regret bounds for Bayesian optimization with unknown hyperparameters.
problem Optimizing black-box functions with unknown hyperparameters, especially length scale.
method Length Scale Balancing (LB) - aggregating multiple surrogate models with varying length scales.
result LB achieves a regret bound only logaritically away from the oracle algorithm.