Research
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.

168,695 papers · 148 categories

Trend · papers per month

79158236315 · Jun 202019922001200920172026
48 results for PAC Combinatorial Pure Exploration

New algorithm finds high-reward combinatorial sets with fewest pulls.

problem Finding high-reward combinatorial sets with unknown individual arm rewards.
method Successive acceptance and elimination based on combinatorial structure.
result Algorithm requires minimal combinatorial oracle calls, making it practical for large problems.

This paper tackles combinatorial pure exploration for dueling bandits, aiming to find the best candidate-position match.

problem Finding the best candidate-position match in a dueling bandit setting.
method The paper adapts combinatorial pure exploration for multi-armed bandits to dueling bandits, considering both Borda winner and Condorcet winner cases. It designs PAC and exact algorithms for Borda winner and a fully polynomial time approximation scheme (FPTAS) for Condorcet winner.
result The paper introduces the first algorithm with polynomial running time per round for identifying the Condorcet winner in CPE-DB.

This paper explores how boolean formulas can be learned by deep neural networks.

problem Understanding the learnability of boolean formulas by deep neural networks.
method Analysis of boolean formulas associated with model-sampling benchmarks, combinatorial optimization problems, and random 3-CNFs.
result Neural networks outperform rule-based systems and pure symbolic approaches in learning boolean formulas.

This paper tackles combinatorial optimization under uncertainty with limited feedback.

problem Tackling combinatorial optimization problems with uncertain or unknown parameters.
method Review of techniques for combinatorial pure exploration with limited bandit feedback.
result Introduction of methods for combinatorial optimization under uncertainty with limited observation.

In this paper, we analyze PAC learnability from labels produced by crowdsourcing. In our setting, unlabeled examples are drawn from a distribution and labels are crowdsourced from workers who operate under classification noise, each with their own noise parameter. We develop an end-to-end crowdsourced PAC learning algo…

2019-02-12abs ↗pdf ↗

Given a huge set of applicants, how should a firm allocate sequential resume screenings, phone interviews, and in-person site visits? In a tiered interview process, later stages (e.g., in-person visits) are more informative, but also more expensive than earlier stages (e.g., resume screenings). Using accepted hiring mo…

2019-06-23abs ↗pdf ↗

The paper tackles combinatorial pure exploration with various feedback structures and proposes efficient algorithms.

problem Identifying the optimal action in a combinatorial space with limited feedback and nonlinear rewards.
method Designs polynomial-time adaptive algorithms for CPE-BL and CPE-PL, providing sample complexity analyses.
result The proposed algorithms achieve sample complexity close to lower bounds and outperform existing methods.

Optimal algorithm for selecting high-quality arms from infinite bandit arms.

problem Efficiently choosing the best arm from an infinite set of options.
method Developed algorithms for both fixed confidence and fixed budget settings, achieving optimal or near-optimal sample complexities.
result Optimal sample complexity results for both fixed confidence and fixed budget settings, resolving open questions in the field.

Algorithm identifies best arm in combinatorial bandits with semi-bandit feedback.

problem Identifying the best arm in combinatorial bandits with semi-bandit feedback.
method Interpreted as a sequential zero-sum game, developed a CombGame meta-algorithm with finite time guarantees.
result First computationally efficient algorithm that is asymptotically optimal and has competitive empirical performance.

We study a specific \textit{combinatorial pure exploration stochastic bandit problem} where the learner aims at finding the set of arms whose means are above a given threshold, up to a given precision, and \textit{for a fixed time horizon}. We propose a parameter-free algorithm based on an original heuristic, and prove…

2016-05-27abs ↗pdf ↗

We study the combinatorial pure exploration problem Best-Set in stochastic multi-armed bandits. In a Best-Set instance, we are given nn arms with unknown reward distributions, as well as a family F\mathcal{F} of feasible subsets over the arms. Our goal is to identify the feasible subset in F\mathcal{F} with the maxi…

2017-06-04abs ↗pdf ↗

Characterizes statistical complexity of realizable regression in PAC and online learning.

problem Understanding the statistical complexity of realizable regression in both PAC and online learning settings.
method Introduces minimax instance optimal learners, novel and combinatorial dimensions to characterize learnability.
result Characterizes which classes of real-valued predictors are learnable and provides necessary conditions for learnability.

Sharp sample complexity for multiclass PAC learning with bandit feedback.

problem Multiclass PAC learning with bandit feedback.
method Characterization of optimal sample complexity using a new combinatorial dimension (bandit DS dimension) and a learning algorithm (ListCascade).
result Sharp sample complexity characterization for every concept class up to logarithmic factors.

The cold posterior effect is explored through PAC-Bayes bounds for small sample sizes.

problem The cold posterior effect in approximate Bayesian inference for small datasets.
method Investigation through PAC-Bayes generalization bounds, focusing on temperature parameter λ.
result The temperature parameter λ in PAC-Bayes bounds captures the cold posterior effect.

We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead. We propose a model-free RL method that modifies Delayed Q-learning and utilizes the long-term exploration bonu…

2018-08-31abs ↗pdf ↗

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…

2011-05-23abs ↗pdf ↗

Goussarov, Polyak, and Viro proved that finite type invariants of knots are ``finitely multi-local'', meaning that on a knot diagram, sums of quantities, defined by local information, determine the value of the knot invariant. The result implies the existence of Gauss diagram combinatorial formulas for finite type inva…

2007-11-26abs ↗pdf ↗

The paper tackles pure exploration in multi-armed bandits with low rank structure using oblivious sampling.

problem Pure exploration in multi-armed bandits with low rank reward sequences.
method The approach involves separating the exploration strategy from feedback, using oblivious sampling, and incorporating kernel information of reward vectors.
result Efficient algorithms with regret bound O(d(lnN)/n)O(d\sqrt{(\ln N)/n}) for both time-varying and fixed cases, with a lower bound gap of O(lnN)O(\sqrt{\ln N}).

Paper bounds PAC RL sample complexity in deterministic MDPs.

problem Identify ε-optimal policy with high probability.
method Proposes nearly matching upper and lower bounds on sample complexity, introduces deterministic return gap, uses graph-theoretical concepts and maximum-coverage exploration.
result First nearly matching upper and lower bounds on sample complexity for PAC RL in deterministic MDPs.

We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Previous approaches to this problem, such as those of Chow ([1]), and Ho gen ([7]) have shown that this class is PAC-learnable by reducing it to …

2012-07-11abs ↗pdf ↗

This work introduces CAET, an algorithm for cost-aware pairwise pure exploration.

problem Identifying optimal arm pairs with varying costs in multi-armed bandits.
method Introduces a framework for pairwise pure exploration with arm-specific costs, derives a lower bound, and proposes CAET algorithm.
result CAET optimizes cumulative cost and approaches the lower bound asymptotically.