arXiv research

Boosted GFlowNets improve exploration by sequentially training GFlowNets with residual rewards.

Proposes a method to accelerate safe sequential learning using offline data.

VCSMC improves efficiency in Bayesian phylogenetic inference.

An agent explores indefinitely in an environment with unlimited rewards.

Proposes EVE for efficient exploration in reinforcement learning.

Improved batched SH algorithm maintains original performance.

Parallelized bandit algorithms speed up decision-making.

REN addresses uncertainty in user feedbacks for better recommendation systems.

Enhances SMC² with Hessian info for more efficient posterior approximation.

This work optimizes identifying good arms in nonparametric multi-armed bandits.

Study new bounds on TC of spaces with subgroup inclusions.

This review examines bandit problems in AI using statistical methods.

PEAK tests means of multiple data streams with sequential betting.

Can one parallelize complex exploration exploitation tradeoffs? As an example, consider the problem of optimal high-throughput experimental design, where we wish to sequentially design batches of experiments in order to simultaneously learn a surrogate function mapping stimulus to response and identify the maximum of t…

Efficient exploration improves large language model performance with fewer queries.

OMLE combines optimism and MLE for efficient sequential decision making.

We introduce Parameterized Exploration (PE), a simple family of methods for model-based tuning of the exploration schedule in sequential decision problems. Unlike common heuristics for exploration, our method accounts for the time horizon of the decision problem as well as the agent's current state of knowledge of the …

We study the multi-armed bandit problem with subgaussian rewards. The explore-then-commit (ETC) strategy, which consists of an exploration phase followed by an exploitation phase, is one of the most widely used algorithms in a variety of online decision applications. Nevertheless, it has been shown in Garivier et al. (…

New algorithm achieves near optimal sample complexity for 1-identification problem.

Current state-of-the-art nonparametric Bayesian text clustering methods model documents through multinomial distribution on bags of words. Although these methods can effectively utilize the word burstiness representation of documents and achieve decent performance, they do not explore the sequential information of text…

We explore a general framework in Markov chain Monte Carlo (MCMC) sampling where sequential proposals are tried as a candidate for the next state of the Markov chain. This sequential-proposal framework can be applied to various existing MCMC methods, including Metropolis-Hastings algorithms using random proposals and m…

Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning, and sequential optimization has become a popular solution. Typical examples include data summarization, sample mining for predictive modeling and hyper-parameter optimization. Existing solutions attempt to adaptiv…

This study improves audit sampling by using sequential procedures with statistical guarantees.

The article applies Lusternik-Schnirelmann theory to establish lower bounds on critical points using sequential and parametrized topological complexity.

The classification procedure of streaming data usually requires various ad hoc methods or particular heuristic models. We explore a novel non-parametric and systematic approach to analysis of heterogeneous sequential data. We demonstrate an application of this method to classification of the delays in responding to the…

NAS-X improves inference and model learning for SLVMs.

Proposes LDIDPs for efficient sequential data generation from latent dynamical models.

In this paper, we consider the challenge of maximizing an unknown function f for which evaluations are noisy and are acquired with high cost. An iterative procedure uses the previous measures to actively select the next estimation of f which is predicted to be the most useful. We focus on the case where the function ca…

We extend CS divergence to conditional distributions and show its advantages in time series data and sequential decision making.

New reinforcement learning bound improves generalization for sequential data.

The paper addresses estimating long-term treatment effects with monotone missing data.

Algorithm identifies optimal stable matching in uncertain two-sided markets.

Safe actions learned in finite trials, without infinite exploration.

Optimal timing strategy for mean-reverting price spreads.

Bayesian reflex models AI learning like the autonomic nervous system.

A new method converts neural networks to function space for scalable sequential learning.

New algorithm reduces regret in sequential decision-making problems.

We consider the best-arm identification problem in multi-armed bandits, which focuses purely on exploration. A player is given a fixed budget to explore a finite set of arms, and the rewards of each arm are drawn independently from a fixed, unknown distribution. The player aims to identify the arm with the largest expe…

Paper proposes a new method for efficient hyperparameter optimization.

A single policy suffices for near-optimal parallel exploration in RL.

One way to solve lasso problems when the dictionary does not fit into available memory is to first screen the dictionary to remove unneeded features. Prior research has shown that sequential screening methods offer the greatest promise in this endeavor. Most existing work on sequential screening targets the context of …

A framework for generating 3D shapes by sequentially assembling primitives.

In point-based sensing systems such as coordinate measuring machines (CMM) and laser ultrasonics where complete sensing is impractical due to the high sensing time and cost, adaptive sensing through a systematic exploration is vital for online inspection and anomaly quantification. Most of the existing sequential sampl…

Optimal online data collection for semiparametric inference reduces regret.

Batched Neural Bandits reduces policy updates in sequential decision-making.

Survey explores how transfer learning improves deep reinforcement learning.

In this paper, we consider the pricing of derivative products that involve dynamic hedging strategies and payments within the planning horizon. Equity-indexed annuities (EIAs), Guaranteed investment certificate (GIC), American and Barrier options are typical examples of these products. Our exploration involves evaluati…

New method optimizes decision-making in uncertain environments.