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.
A new algorithm reduces frequentist regret in multi-agent bandit problems with sparse hypergraphs.
problem Deriving a frequentist regret bound for Thompson sampling in multi-agent settings with sparse hypergraphs.
method Proposed ε-exploring Multi-Agent Thompson Sampling (ε-MATS) algorithm that combines exploration and exploitation strategies.
result Achieves a worst-case frequentist regret bound sublinear in time horizon and local arm size, optimal up to constants and logarithms for sparse hypergraphs.
The paper addresses frequentist regret of Linear Thompson Sampling in stochastic linear bandits.
problem The frequentist regret of Linear Thompson Sampling (LinTS) is worse than its Bayesian counterpart.
method The paper proves the fundamental nature of the frequentist regret bound for LinTS and proposes a data-driven version of LinTS to achieve minimax optimal frequentist regret.
result The frequentist regret bound for LinTS is O(ddT), which is the best possible under certain conditions.
We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning (RL). When the state space is large or continuous, traditional tabular approaches are unfeasible and some form of function approximation is mandatory. In this paper, we introduce an optimistically-initialized variant of the popula…
We present two algorithms for Bayesian optimization in the batch feedback setting, based on Gaussian process upper confidence bound and Thompson sampling approaches, along with frequentist regret guarantees and numerical results.
In the stochastic bandit problem, the goal is to maximize an unknown function via a sequence of noisy evaluations. Typically, the observation noise is assumed to be independent of the evaluation point and to satisfy a tail bound uniformly on the domain; a restrictive assumption for many applications. In this work, we c…
The study compares Bayesian and frequentist approaches in deep learning.
problem Comparing Bayesian and frequentist inference in deep learning.
method Conducts a comparative analysis of point and posterior estimators across various settings.
result Amortized point estimators generally outperform posterior inference, though posterior inference remains competitive in some low-dimensional problems.
We study, to the best of our knowledge, the first Bayesian algorithm for unimodal Multi-Armed Bandit (MAB) problems with graph structure. In this setting, each arm corresponds to a node of a graph and each edge provides a relationship, unknown to the learner, between two nodes in terms of expected reward. Furthermore, …
A key challenge for modern Bayesian statistics is how to perform scalable inference of posterior distributions. To address this challenge, variational Bayes (VB) methods have emerged as a popular alternative to the classical Markov chain Monte Carlo (MCMC) methods. VB methods tend to be faster while achieving comparabl…
DBPA assesses LLM perturbations using frequentist hypothesis testing.
problem Quantifying input perturbation impacts on LLM outputs.
method DBPA reformulates perturbation analysis as frequentist hypothesis testing, using Monte Carlo sampling for empirical null and alternative distributions.
result DBPA provides interpretable p-values and scalar effect sizes for LLM perturbations.
We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs). We propose two near-optimal and oracle-efficient algorithms for FMDPs. Assuming oracle access to an FMDP planner, they enjoy a Bayesian and a frequentist regret bound respectively, both of which reduce to the near-optimal bound …
We exhibit a strong link between frequentist PAC-Bayesian risk bounds and the Bayesian marginal likelihood. That is, for the negative log-likelihood loss function, we show that the minimization of PAC-Bayesian generalization risk bounds maximizes the Bayesian marginal likelihood. This provides an alternative explanatio…
We have recently proposed a new information-based approach to model selection, the Frequentist Information Criterion (FIC), that reconciles information-based and frequentist inference. The purpose of this current paper is to provide a simple example of the application of this criterion and a demonstration of the natura…
Gaussian process (GP) regression is a powerful interpolation technique due to its flexibility in capturing non-linearity. In this paper, we provide a general framework for understanding the frequentist coverage of point-wise and simultaneous Bayesian credible sets in GP regression. As an intermediate result, we develop…
Safe Bayesian Optimization algorithms are improved to ensure safety in real-world applications.
problem Ensuring safety in Bayesian Optimization algorithms for real-world applications.
method Investigated and improved three safety-related issues of SafeOpt-type algorithms: frequentist uncertainty bounds, RKHS norm assumptions, and discrete search spaces.
result Introduced Real-{eta}-SafeOpt, Lipschitz-only Safe Bayesian Optimization (LoSBO), and Lipschitz-only GP-UCB (LoS-GP-UCB) algorithms that retain safety guarantees and superior performance.
Stochastic Rank-One Bandits (Katarya et al, (2017a,b)) are a simple framework for regret minimization problems over rank-one matrices of arms. The initially proposed algorithms are proved to have logarithmic regret, but do not match the existing lower bound for this problem. We close this gap by first proving that rank…
In this work, we investigate black-box optimization from the perspective of frequentist kernel methods. We propose a novel batch optimization algorithm, which jointly maximizes the acquisition function and select points from a whole batch in a holistic way. Theoretically, we derive regret bounds for both the noise-free…