Search Results for author:
Found 34 papers, 4 papers with code
Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization
Portfolio optimization involves determining the optimal allocation of portfolio assets in order to maximize a given investment objective.
REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values
In this paper, we introduce the problem of feature \emph{reselection}, so that features can be selected with respect to secondary model performance characteristics efficiently even after a feature selection process has been done with respect to a primary objective.
Privacy-Preserving Algorithmic Recourse
We observe that PrivRecourse can provide paths that are private and realistic.
Fair Coresets via Optimal Transport
In this work, we present fair Wasserstein coresets (FWC), a novel coreset approach which generates fair synthetic representative samples along with sample-level weights to be used in downstream learning tasks.
Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates
Discrete optimization belongs to the set of $\mathcal{NP}$-hard problems, spanning fields such as mixed-integer programming and combinatorial optimization.
On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
Explainable Artificial Intelligence (XAI) has received widespread interest in recent years, and two of the most popular types of explanations are feature attributions, and counterfactual explanations.
SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features
While any method to compute SHAP values with uncertainty estimates (such as KernelSHAP and SamplingSHAP) can be trivially adapted to solve TkIP, doing so is highly sample inefficient.
GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations
Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods prominent in fairness, recourse and model understanding.
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
There is an emerging interest in generating robust counterfactual explanations that would remain valid if the model is updated or changed even slightly.
Bayesian Hierarchical Models for Counterfactual Estimation
Counterfactual explanations utilize feature perturbations to analyze the outcome of an original decision and recommend an actionable recourse.
Learn to explain yourself, when you can: Equipping Concept Bottleneck Models with the ability to abstain on their concept predictions
The Concept Bottleneck Models (CBMs) of Koh et al. [2020] provide a means to ensure that a neural network based classifier bases its predictions solely on human understandable concepts.
Rethinking Log Odds: Linear Probability Modelling and Expert Advice in Interpretable Machine Learning
We introduce a family of interpretable machine learning models, with two broad additions: Linearised Additive Models (LAMs) which replace the ubiquitous logistic link function in General Additive Models (GAMs); and SubscaleHedge, an expert advice algorithm for combining base models trained on subsets of features called subscales.
Towards learning to explain with concept bottleneck models: mitigating information leakage
Concept bottleneck models perform classification by first predicting which of a list of human provided concepts are true about a datapoint.
Feature Importance for Time Series Data: Improving KernelSHAP
Feature importance techniques have enjoyed widespread attention in the explainable AI literature as a means of determining how trained machine learning models make their predictions.
Robust Counterfactual Explanations for Tree-Based Ensembles
In this work, we propose a novel strategy -- that we call RobX -- to generate robust counterfactuals for tree-based ensembles, e. g., XGBoost.
Global Counterfactual Explanations: Investigations, Implementations and Improvements
Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding.
Asynchronous Collaborative Learning Across Data Silos
Our proposed approach enhances conventional federated learning techniques to make them suitable for this asynchronous training in this intra-organisation, cross-silo setting.
Explaining Preference-driven Schedules: the EXPRES Framework
The EXPRES framework consists of: (i) an explanation generator that, based on a Mixed-Integer Linear Programming model, finds the best set of reasons that can explain an unsatisfied preference; and (ii) an explanation parser, which translates the generated explanations into human interpretable ones.
Optimal Admission Control for Multiclass Queues with Time-Varying Arrival Rates via State Abstraction
To improve the scalability of our approach to a greater number of task classes, we present an approximation based on state abstraction.
A Survey on the Robustness of Feature Importance and Counterfactual Explanations
There exist several methods that aim to address the crucial task of understanding the behaviour of AI/ML models.
Counterfactual Shapley Additive Explanations
Feature attributions are a common paradigm for model explanations due to their simplicity in assigning a single numeric score for each input feature to a model.
How Robust are Limit Order Book Representations under Data Perturbation?
The success of machine learning models in the financial domain is highly reliant on the quality of the data representation.
Towards Robust Representation of Limit Orders Books for Deep Learning Models
The success of deep learning-based limit order book forecasting models is highly dependent on the quality and the robustness of the input data representation.
Graph Reasoning with Context-Aware Linearization for Interpretable Fact Extraction and Verification
This paper presents an end-to-end system for fact extraction and verification using textual and tabular evidence, the performance of which we demonstrate on the FEVEROUS dataset.
Counterfactual Explanations for Arbitrary Regression Models
We present a new method for counterfactual explanations (CFEs) based on Bayesian optimisation that applies to both classification and regression models.
Contrastive Explanations of Plans Through Model Restrictions
We formally define model-based compilations in PDDL2. 1 of each constraint derived from a user question in the taxonomy, and empirically evaluate the compilations in terms of computational complexity.
Towards Efficient Anytime Computation and Execution of Decoupled Robustness Envelopes for Temporal Plans
One of the major limitations for the employment of model-based planning and scheduling in practical applications is the need of costly re-planning when an incongruence between the observed reality and the formal model is encountered during execution.
Towards Explainable AI Planning as a Service
Explainable AI is an important area of research within which Explainable Planning is an emerging topic.
Towards Providing Explanations for AI Planner Decisions
In order to engender trust in AI, humans must understand what an AI system is trying to achieve, and why.
Explainable Security
The Defense Advanced Research Projects Agency (DARPA) recently launched the Explainable Artificial Intelligence (XAI) program that aims to create a suite of new AI techniques that enable end users to understand, appropriately trust, and effectively manage the emerging generation of AI systems.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Explainable Planning
As AI is increasingly being adopted into application solutions, the challenge of supporting interaction with humans is becoming more apparent.
CASP Solutions for Planning in Hybrid Domains
CASP is an extension of ASP that allows for numerical constraints to be added in the rules.
PDDL+ Planning via Constraint Answer Set Programming
PDDL+ is an extension of PDDL that enables modelling planning domains with mixed discrete-continuous dynamics.
Plan-based Policies for Efficient Multiple Battery Load Management
Application of the approach leads to construction of policies that, in simulation, significantly outperform those that are currently in use and the best published solutions to the battery management problem.
