Search Results for author:
Found 19 papers, 2 papers with code
Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspective
We theoretically analyze the potential over-informativeness and under-informativeness of existing Shapley value attribution methods.
Reward Modeling for Mitigating Toxicity in Transformer-based Language Models
Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks.
Multi-resource allocation for federated settings: A non-homogeneous Markov chain model
In a federated setting, agents coordinate with a central agent or a server to solve an optimization problem in which agents do not share their information with each other.
Bias-Corrected Peaks-Over-Threshold Estimation of the CVaR
To mitigate this problem, the CVaR can be estimated by extrapolating above a lower threshold than the VaR using a generalized Pareto distribution (GPD), which is often referred to as the peaks-over-threshold (POT) approach.
Generating Embroidery Patterns Using Image-to-Image Translation
Our goal is to generate a preview image which looks similar to an embroidered image, from a user-uploaded image.
Risk-Averse Action Selection Using Extreme Value Theory Estimates of the CVaR
To mitigate this problem, extreme value theory can be used to derive an estimator for the CVaR that uses extrapolation beyond available samples.
A Scheme for Dynamic Risk-Sensitive Sequential Decision Making
For a given risk-sensitive problem, in which the objective and constraints are, or can be estimated by, functions of the mean and variance of return, we generate a synthetic dataset as training data.
Variance-Based Risk Estimations in Markov Processes via Transformation with State Lumping
In the numerical experiment, we illustrate state lumping in the SAT, errors from a naive reward simplification, and the validity of the SAT for the two risk estimations.
Efficient Single-Shot Multibox Detector for Construction Site Monitoring
Asset monitoring in construction sites is an intricate, manually intensive task, that can highly benefit from automated solutions engineered using deep neural networks.
Ensemble-based Adaptive Single-shot Multi-box Detector
This uses data to reduce the uncertainty in the selection of best aspect ratios for the default boxes and improves performance of SSD for datasets containing small and complex objects (e. g., equipments at construction sites).
State-Augmentation Transformations for Risk-Sensitive Reinforcement Learning
In the framework of MDP, although the general reward function takes three arguments-current state, action, and successor state; it is often simplified to a function of two arguments-current state and action.
Transition-based versus State-based Reward Functions for MDPs with Value-at-Risk
Thirdly, since the estimation method is for a Markov reward process with the reward function on current state only, we present a transformation algorithm for the Markov reward process with the reward function on current and next states, in order to estimate the VaR function with an intact total reward distribution.
Pricing Vehicle Sharing with Proximity Information
For vehicle sharing schemes, where drop-off positions are not fixed, we propose a pricing scheme, where the price depends in part on the distance between where a vehicle is being dropped off and where the closest shared vehicle is parked.
Two Phase $Q-$learning for Bidding-based Vehicle Sharing
We consider one-way vehicle sharing systems where customers can rent a car at one station and drop it off at another.
Functional Bandits
We introduce the functional bandit problem, where the objective is to find an arm that optimises a known functional of the unknown arm-reward distributions.
r-Extreme Signalling for Congestion Control
A central authority has up-to-date knowledge of the congestion across all resources and uses randomisation to provide a scalar or an interval for each resource at each time.
Data-driven Distributionally Robust Polynomial Optimization
We consider robust optimization for polynomial optimization problems where the uncertainty set is a set of candidate probability density functions.
Adaptive and optimal online linear regression on $\ell^1$-balls
We first present regret bounds with optimal dependencies on $d$, $T$, and on the sizes $U$, $X$ and $Y$ of the $\ell^1$-ball, the input data and the observations.
