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…
On-device research index
arXiv research
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.
168,738 papers · 148 categories
Trend · papers per month
48 results for “exploration-exploitation tradeoff”
In this paper, we propose and study opportunistic bandits - a new variant of bandits where the regret of pulling a suboptimal arm varies under different environmental conditions, such as network load or produce price. When the load/price is low, so is the cost/regret of pulling a suboptimal arm (e.g., trying a suboptim…
Monte Carlo Tree Search (MCTS) algorithms have achieved great success on many challenging benchmarks (e.g., Computer Go). However, they generally require a large number of rollouts, making their applications costly. Furthermore, it is also extremely challenging to parallelize MCTS due to its inherent sequential nature:…
Study explores strategies for randomized allocation in delayed rewards bandits.
problem Understanding the exploration-exploitation tradeoff in randomized strategies with delayed rewards.
method Examines two strategies: updating exploration sequence at every time point vs. updating only when a new reward is observed.
result The strategy updating only when a new reward is observed leads to strong consistency in allocation for a wider scope of situations.
Algorithm balances online and offline data for linear bandits.
problem Online learning with an offline dataset in linear bandits.
method Proposes a linear bandit algorithm that uses offline data early and increasingly favors exploration as the horizon grows.
result Establishes regret bounds showing competitive performance with both purely online and offline solutions.
Efficient algorithm for CMDPs reduces to offline density estimation.
problem Offline learning for CMDPs with horizon H.
method Reduction to offline density estimation, layerwise exploration-exploitation tradeoff.
result First efficient and near-optimal reduction from CMDPs to offline density estimation.
We study the explore-exploit tradeoff in distributed cooperative decision-making using the context of the multiarmed bandit (MAB) problem. For the distributed cooperative MAB problem, we design the cooperative UCB algorithm that comprises two interleaved distributed processes: (i) running consensus algorithms for estim…
Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorithms for such learning is the multi-armed bandit setting. Randomized probability matching, based upon …
This paper extends the MAB problem to consider risk-reward tradeoffs.
problem Maximizing reward while accounting for risk in multi-armed bandit problems.
method Introduced the Risk Aware Lower Confidence Bound (RALCB) algorithm to solve the mean-variance MAB problem.
result The RALCB algorithm performs better than the algorithm in Sani et al. (2012) in both independent and dependent scenarios.
The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to resolve the tradeoff by using a fixed exploration mechanism, such as -greedy ex…
ERTS uses Thompson sampling for Gaussian entropic risk bandits, achieving regret bounds.
problem Risk in decision making complicates reward maximization in MAB problems.
method ERTS (Entropic Risk Thompson Sampling) using Thompson sampling with an entropic risk measure.
result Regret bounds for ERTS under entropic risk measure provided.
We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling. By making a connection between information-theoretic quantities and confidence bounds, we obtain results that relate the per-period performance of the agent with its information gain about the enviro…
LaMBO optimizes biological sequences using autoencoders and Bayesian optimization.
problem Bayesian optimization for drug design is limited by discrete, high-dimensional decision variables.
method Jointly trains denoising autoencoder with a Gaussian process head for gradient-based optimization in latent space.
result LaMBO outperforms genetic optimizers and requires no large pretraining corpus.
An online labor platform faces an online learning problem in matching workers with jobs and using the performance on these jobs to create better future matches. This learning problem is complicated by the rise of complex tasks on these platforms, such as web development and product design, that require a team of worker…
We study a budgeted hyper-parameter tuning problem, where we optimize the tuning result under a hard resource constraint. We propose to solve it as a sequential decision making problem, such that we can use the partial training progress of configurations to dynamically allocate the remaining budget. Our algorithm combi…
We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating the neighborhood of users in a context-dependent manner. CAB makes sharp departures from the state of the art by incorporating collaborative effects into …
Task offloading is an emerging technology in fog-enabled networks. It allows users to transmit tasks to neighbor fog nodes so as to utilize the computing resources of the networks. In this paper, we investigate a stochastic task offloading model and propose a multi-armed bandit framework to formulate this model. We con…
The purpose of this paper is to provide further understanding into the structure of the sequential allocation ("stochastic multi-armed bandit", or MAB) problem by establishing probability one finite horizon bounds and convergence rates for the sample (or "pseudo") regret associated with two simple classes of allocation…
The enactive approach to cognition is typically proposed as a viable alternative to traditional cognitive science. Enactive cognition displaces the explanatory focus from the internal representations of the agent to the direct sensorimotor interaction with its environment. In this paper, we investigate enactive learnin…
Improved UCB method for stochastic bandits using distance tuning.
problem Improving performance in stochastic bandit problems.
method Tuning confidence bounds based on bandit distance.
result Empirically shows increased performance compared to existing methods.
Paper solves nonparametric contextual bandit with unbounded contexts.
problem Sequential decision making with unbounded context distributions.
method Two nearest neighbor methods combined with UCB exploration.
result Achieves minimax optimal regret under weak margin condition and light-tailed distributions.
Paper proposes CVaR-TS for risk-constrained MAB problems.
problem Risk in decision-making complicates reward maximization in MAB problems.
method Risk measure CVaR is used, and Thompson Sampling is adapted for CVaR.
result CVaR-TS outperforms other L/UCB-based algorithms in risk-constrained MAB settings.
We consider the exploration-exploitation tradeoff in linear quadratic (LQ) control problems, where the state dynamics is linear and the cost function is quadratic in states and controls. We analyze the regret of Thompson sampling (TS) (a.k.a. posterior-sampling for reinforcement learning) in the frequentist setting, i.…
Batched Neural Bandits reduces policy updates in sequential decision-making.
problem Sequential decision-making with batched policy changes.
method BatchNeuralUCB algorithm combining neural networks and optimism.
result Achieves similar regret as fully sequential version with fewer policy updates.
Two-stage mechanism designs reduce regret in recommender systems with stochastic covariates.
problem Designing effective recommender systems with user covariates sampled online.
method Two-stage algorithm integrating incentivized exploration with offline learning methods.
result Achieves sublinear regret while maintaining incentive compatibility.
Develops Thompson Sampling algorithms for mean-variance bandits.
problem Risk in online decision making systems.
method Thompson Sampling algorithms for mean-variance MAB with comprehensive regret analyses.
result Achieves best known regret bounds for mean-variance MABs and information-theoretic bounds in some regimes.
We investigate how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks in a black-box setting. We formalize the problem setting and systematically evaluate what benefits the adversary can gain by using substitute models. We show that there is an exploration-exploita…
Improved analysis of UCRL2 with empirical Bernstein inequality reduces exploration-exploitation regret.
problem Exploration-exploitation in communicating Markov Decision Processes.
method Analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B).
result Regret bound of for UCRL2B.
Cellular network configuration plays a critical role in network performance. In current practice, network configuration depends heavily on field experience of engineers and often remains static for a long period of time. This practice is far from optimal. To address this limitation, online-learning-based approaches hav…
On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spacescs.LG
New RL algorithm tackles large state spaces using optimistic function approximation.
problem Challenges in reinforcement learning with large state spaces and modern function approximators.
method Optimistic modification of least-squares value iteration algorithm for kernel functions or overparameterized neural networks.
result Polynomial runtime and sample complexity, independent of the number of states, with regret.
New AIM algorithm optimizes exploration-exploitation in bandits.
problem Balancing exploration and exploitation in decision-making.
method Approximate Information Maximization (AIM) algorithm.
result AIM outperforms Infomax and Thompson sampling with enhanced speed and tractability.
Batch Thompson Sampling reduces exploration-exploitation trade-off in online decision making.
problem Balancing exploration and exploitation in online decision making.
method Introducing a batch Thompson Sampling framework for stochastic multi-arm bandit and linear contextual bandit problems.
result Achieves asymptotic regret bound with batch queries, significantly reducing interactions.
Paper develops a dynamic Bayesian approach for active learning that optimizes exploration-exploitation balance.
problem Balancing exploration and exploitation in active learning for unknown functions.
method Develops BHEEM, a Bayesian hierarchical approach with approximate Bayesian computation for sampling trade-off parameters.
result BHEEM achieves at least 21% and 11% improvement over pure exploration and exploitation strategies respectively.
Nearly Dimension-Independent Sparse Linear Bandit over Small Action Spaces via Best Subset Selectionstat.ML
A new method for sparse linear bandits reduces exploration-exploitation tradeoff.
problem Sparse linear bandits in high-dimensional settings with finite actions.
method Best subset selection for parameter estimation and doubly growing epochs for regret minimization.
result Achieves nearly dimension-independent regret of with high probability.
Paper finds wide minima are better for generalization and proposes a new learning rate schedule.
problem The challenge of finding optimal learning rates for model training.
method The paper introduces a new hypothesis about the density of wide minima and designs an explore-exploit learning rate schedule.
result The explore-exploit learning rate schedule improves model performance and reduces training time.
We develop a coherent framework for integrative simultaneous analysis of the exploration-exploitation and model order selection trade-offs. We improve over our preceding results on the same subject (Seldin et al., 2011) by combining PAC-Bayesian analysis with Bernstein-type inequality for martingales. Such a combinatio…
ICEE learns new RL tasks in less time with a Transformer model.
problem Efficient in-context policy learning for reinforcement learning.
method In-context Exploration-Exploitation (ICEE) algorithm that optimizes efficiency without explicit Bayesian inference.
result ICEE solves Bayesian optimization problems as efficiently as Gaussian process biased methods but in significantly less time.
Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of function approximation raises a fundamental set of challenges involving computational …
New algorithms improve estimation of treatment effects.
problem Estimating Average Treatment Effect (ATE) in adaptive settings.
method Optimistic algorithms for adaptive estimation using AIPW estimator.
result Significant theoretical and empirical gains over prior methods.
The contextual bandit literature has traditionally focused on algorithms that address the exploration-exploitation tradeoff. In particular, greedy algorithms that exploit current estimates without any exploration may be sub-optimal in general. However, exploration-free greedy algorithms are desirable in practical setti…
New strategies improve multi-agent decision-making on irregular networks.
problem Maximizing group reward in multi-agent settings with heterogeneous strategies.
method Design and analysis of heterogeneous explore-exploit strategies for multi-star networks.
result Group performance improves under heterogeneous strategies compared to homogeneous strategies.
New algorithm reduces regret in sequential decision-making problems.
problem Balancing exploration and exploitation in online sequential decision problems.
method Variational Bayesian optimistic sampling (VBOS) for optimizing policies.
result VBOS achieves Bayesian regret for stochastic multi-armed bandits.
Interactive user interfaces need to continuously evolve based on the interactions that a user has (or does not have) with the system. This may require constant exploration of various options that the system may have for the user and obtaining signals of user preferences on those. However, such an exploration, especiall…
Consequential decisions are increasingly informed by sophisticated data-driven predictive models. However, to consistently learn accurate predictive models, one needs access to ground truth labels. Unfortunately, in practice, labels may only exist conditional on certain decisions---if a loan is denied, there is not eve…
We introduce the bilinear bandit problem with low-rank structure in which an action takes the form of a pair of arms from two different entity types, and the reward is a bilinear function of the known feature vectors of the arms. The unknown in the problem is a by matrix that defines the reward…
Lecture notes on reinforcement learning using statistical methods.
problem Addressing the exploration-exploitation dilemma in decision making.
method Frequentist and Bayesian approaches, function approximation, neural networks.
result Unified framework for decision making and estimation.
The main goal of this thesis is to point out that the bias-variance tradeoff is not always true (e.g. in neural networks). We advocate for this lack of universality to be acknowledged in textbooks and taught in introductory courses that cover the tradeoff. We first review the history of the bias-variance tradeoff, its …
Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learningcs.LG
Algorithm optimizes constrained reinforcement learning with dual variables.
problem Minimizing convex functional subject to convex constraint in large state spaces.
method VPDPO algorithm using Lagrangian and Fenchel duality.
result Achieves sublinear regret and constraint violation, globally optimal policy.