Search Results for author:
Found 20 papers, 3 papers with code
Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
Trustworthy ML systems should not only return accurate predictions, but also a reliable representation of their uncertainty.
A Survey of Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function.
Second-Order Uncertainty Quantification: A Distance-Based Approach
In the past couple of years, various approaches to representing and quantifying different types of predictive uncertainty in machine learning, notably in the setting of classification, have been proposed on the basis of second-order probability distributions, i. e., predictions in the form of distributions on probability distributions.
Identifying Copeland Winners in Dueling Bandits with Indifferences
We consider the task of identifying the Copeland winner(s) in a dueling bandits problem with ternary feedback.
Iterative Deepening Hyperband
Hyperparameter optimization (HPO) is concerned with the automated search for the most appropriate hyperparameter configuration (HPC) of a parameterized machine learning algorithm.
Approximating the Shapley Value without Marginal Contributions
The Shapley value, which is arguably the most popular approach for assigning a meaningful contribution value to players in a cooperative game, has recently been used intensively in explainable artificial intelligence.
On Second-Order Scoring Rules for Epistemic Uncertainty Quantification
In this paper, we generalise these findings and prove a more fundamental result: There seems to be no loss function that provides an incentive for a second-order learner to faithfully represent its epistemic uncertainty in the same manner as proper scoring rules do for standard (first-order) learners.
AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration
We study the algorithm configuration (AC) problem, in which one seeks to find an optimal parameter configuration of a given target algorithm in an automated way.
On the Calibration of Probabilistic Classifier Sets
In this paper, we extend the notion of calibration, which is commonly used to evaluate the validity of the aleatoric uncertainty representation of a single probabilistic classifier, to assess the validity of an epistemic uncertainty representation obtained by sets of probabilistic classifiers.
Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation
Uncertainty quantification has received increasing attention in machine learning in the recent past.
Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget
We consider the combinatorial bandits problem with semi-bandit feedback under finite sampling budget constraints, in which the learner can carry out its action only for a limited number of times specified by an overall budget.
Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models
In every round of the sequential decision problem, the learner makes a context-dependent selection of two choice alternatives (arms) to be compared with each other and receives feedback in the form of noisy preference information.
A Survey of Methods for Automated Algorithm Configuration
We review existing AC literature within the lens of our taxonomies, outline relevant design choices of configuration approaches, contrast methods and problem variants against each other, and describe the state of AC in industry.
Non-Stationary Dueling Bandits
We propose the $\mathrm{Beat\, the\, Winner\, Reset}$ algorithm and prove a bound on its expected binary weak regret in the stationary case, which tightens the bound of current state-of-art algorithms.
Identification of the Generalized Condorcet Winner in Multi-dueling Bandits
The reliable identification of the “best” arm while keeping the sample complexity as low as possible is a common task in the field of multi-armed bandits.
Machine Learning for Online Algorithm Selection under Censored Feedback
In online algorithm selection (OAS), instances of an algorithmic problem class are presented to an agent one after another, and the agent has to quickly select a presumably best algorithm from a fixed set of candidate algorithms.
Multi-Armed Bandits with Censored Consumption of Resources
We consider a resource-aware variant of the classical multi-armed bandit problem: In each round, the learner selects an arm and determines a resource limit.
Online Preselection with Context Information under the Plackett-Luce Model
We consider an extension of the contextual multi-armed bandit problem, in which, instead of selecting a single alternative (arm), a learner is supposed to make a preselection in the form of a subset of alternatives.
Preselection Bandits
To formalize this goal, we introduce a reasonable notion of regret and derive lower bounds on the expected regret.
Preference-based Online Learning with Dueling Bandits: A Survey
The aim of this paper is to provide a survey of the state of the art in this field, referred to as preference-based multi-armed bandits or dueling bandits.
