Novel decision lists with rules in one direction improve model interpretability and efficiency.
problem Improving model interpretability and efficiency in decision lists.
method Introducing a novel family of decision lists with rules oriented in the same direction, and demonstrating their effectiveness on simulated and real-world data.
result The proposed model family is easier to train than general decision lists and can be applied to practical problems like manufacturing process symptom identification.
New algorithms for privately learning decision lists and halfspaces.
problem Private learning of decision lists and halfspaces.
method Differentially private algorithms for PAC and online models.
result Private algorithms match or surpass non-private guarantees.
Automates cost-effective treatment recommendations using decision lists.
problem Making cost-effective treatment decisions for patients.
method Formulated as a Markov Decision Process (MDP) and used UCT strategy for decision list construction.
result Demonstrated effectiveness on real-world data for bail decisions and asthma treatment.
Automates treatment recommendation decisions by learning cost-effective and interpretable rules.
problem Making optimal treatment decisions for patients based on diagnostic test results.
method Formulated as a decision list problem, optimized using a Markov Decision Process and UCT strategy.
result Demonstrated effectiveness in real-world asthma patient data.
A new method explains RNNs by decision lists over skipgrams, improving explanation fidelity and interpretability.
problem Lack of understanding how input segments combine to form patterns in neural network outputs.
method Proposes a pipeline to explain RNNs using decision lists over skipgrams, creating synthetic and real-world datasets for evaluation.
result Persistently achieves high explanation fidelity and interpretable rules.
The paper calculates how much data is needed to learn decision lists in the presence of evasion attacks.
problem Quantifying sample complexity for robust learning of decision lists against evasion attacks.
method PAC learning framework, Lipschitz condition on distributions, lower and upper bounds on sample complexity.
result Upper and lower bounds on sample complexity for robust learning of decision lists, showing exponential vs polynomial dependence on adversary's budget.
New model predicts stroke risk with high accuracy and interpretability.
problem Developing accurate and understandable models for stroke risk prediction.
method Bayesian Rule Lists: a generative model that produces interpretable decision lists.
result Bayesian Rule Lists achieves predictive accuracy comparable to top machine learning algorithms and is more accurate than existing models.
Improved conversion prediction for B2B products using collective online activity trails.
problem Limited information from single user activity trails for B2B ad targeting.
method Introduced relevant users concept and used distributed activity representations to build seed lists.
result Improved conversion prediction AUC by 8.8% using collective activity trails.
Optimal rule lists for categorical data are created with guaranteed accuracy.
problem Creating interpretable yet accurate models for categorical data.
method Custom discrete optimization technique producing rule lists with optimal training performance.
result Optimal rule lists are constructed in seconds with guaranteed accuracy.
Classy learns interpretable probabilistic rule lists for multiclass classification.
problem Creating interpretable multiclass classifiers that are both accurate and understandable.
method Probabilistic rule lists and minimum description length (MDL) principle for model selection.
result Classy selects small probabilistic rule lists that outperform state-of-the-art classifiers in terms of predictive performance and interpretability.
A new recommender system learns from user interactions to improve recommendations.
problem Mitigating information overload by personalizing item suggestions.
method Modeling interactions as MDP, using RL to learn optimal strategies, incorporating list-wise recommendations.
result The proposed framework LIRD improves recommendation effectiveness.
Proposes FairCORELS for fair, interpretable rule lists.
problem Fairness in interpretable models for high-stakes decisions.
method Multi-objective variant of CORELS, supporting fairness measures.
result Outperforms state-of-the-art fair classification techniques.
NeuRules learns interpretable rule lists from data without pre-discretization.
problem Interpretable rule lists for high-stakes decisions in machine learning.
method Neuro-symbolic continuous optimization with temperature annealing.
result NeuRules outperforms existing methods in learning interpretable rule lists.
New statistical models for predicting ranked preferences from partial orders.
problem Statistical models overlook information in list length.
method Composite and augmented ranking models for joint modeling of partial orders and list lengths.
result Augmented ranking models best predict both length and preferences.
Young investors, especially students, dominate Indonesian stock exchanges.
problem Investment behavior of young and rookie investors in the stock market.
method Qualitative approach with descriptive analysis and interviews.
result Perception of behavioral control influences investment decisions.
Fairwashing occurs when machine learning models are made to appear fair through rationalization.
problem Rationalizing unfair black-box models to appear fair.
method LaundryML uses a regularized rule list enumeration algorithm to find fair rule lists approximating an unfair model.
result It is possible to systematically rationalize decisions from unfair black-box models using model and outcome explanations.
Optimized decision trees for reinforcement learning, improving sample complexity and interpretability.
problem Updating decision trees online in reinforcement learning.
method Gradient update over differentiable decision trees, including theoretical justification and empirical validation.
result Our approach outperforms neural networks in sample complexity and achieves higher rewards online.
Proposes Deep Scenes for interaction-aware scene understanding in reinforcement learning for autonomous driving.
problem Leveraging deep reinforcement learning for high-level decision making in autonomous driving requires handling variable-length sequences of different object types and interactions.
method Introduces Deep Scenes architecture, an extension of Deep Sets or Graph Convolutional Networks, to learn complex interaction-aware scene representations.
result Graph-Q and DeepScene-Q algorithms outperform state-of-the-art methods in evaluations with SUMO.
Decision trees improve performance in various fields.
problem Improving performance in machine learning and data mining.
method Introduce tree-based models and training techniques.
result Highlight probabilistic characteristics and practical benefits.
Study shows long-term debt impacts financial growth of non-financial firms listed at Nairobi Securities Exchange.
problem Declining financial performance and reluctance to lend to non-financial firms listed at Nairobi Securities Exchange.
method Descriptive and panel data analysis of 45 non-financial firms over 10 years.
result Long-term debt positively and significantly influences financial growth measured by earnings per share and market capitalization.
Proposes a new method to explain model predictions for consumer recourse.
problem Current explanation methods fail to provide meaningful recourse to decision subjects.
method Develops feature responsiveness scores to highlight actionable features.
result Standard practices can undermine decision subjects by highlighting unresponsive features.
This paper optimizes slate decision systems for large action spaces.
problem Optimizing large-scale decision systems with arbitrary reward functions.
method A policy optimization framework with a novel relaxation of decision functions.
result Demonstrates the effectiveness of the proposed method on large action spaces.
Machine learning outperforms crowd investors in predicting loan defaults and investment returns.
problem Determining if machine learning can outperform human decision-making in crowd lending.
method Using data from Prosper.com, a sophisticated ML algorithm was trained to predict loan defaults and investment returns.
result The ML algorithm outperforms crowd investors in predicting loan defaults and investment returns, especially for risky loans.
In this paper we propose an algorithm that builds sparse decision DAGs (directed acyclic graphs) from a list of base classifiers provided by an external learning method such as AdaBoost. The basic idea is to cast the DAG design task as a Markov decision process. Each instance can decide to use or to skip each base clas…
Study assesses short-term debt's impact on non-financial firms' financial growth.
problem Declining financial performance and reluctance to lend to non-financial firms listed at Nairobi Securities Exchange.
method Explanatory research design, descriptive statistics, and panel data analysis.
result Short-term debt positively and significantly influences financial growth.
New model improves website ranking by considering user choices as a whole.
problem Optimizing content ordering for user clicks in website design.
method Introduced multinomial logit (MNL) choice model to LTR framework, proposing UCB algorithms.
result Proved theoretical bounds on regret for UCB algorithms in both known and unknown position parameter settings.
Unified method for local GBDT feature contributions.
problem Need for local model interpretation for GBDT.
method Unified computation mechanism for instance-level feature contributions.
result Unified computation mechanism for GBDT feature contributions.
Research connects machine learning and robust statistics under weakly structured data.
problem Understanding decision theory in machine learning and robust statistics with incomplete information.
method Collects and connects previous research on machine learning and robust statistics.
result Provides a comprehensive overview of the field, highlighting future research directions.
Simplifies complex RL policies by ranking important decisions.
problem Complexity in RL policies makes them hard to analyze and interpret.
method Statistical fault localisation to rank states and prune unimportant decisions.
result Pruned policies can perform similarly to original policies, improving interpretability.
This article reviews forecasting theory and practice.
problem Forecasting uncertainty and challenges in decision making.
method Overview of forecasting models, principles, and applications.
result Encyclopedic presentation of forecasting theory and practice.
Machine learning algorithms can inherit human biases, requiring fairness audits.
problem Machine learning algorithms can inherit or perpetuate human biases in decision making.
method Fairness constraints must be specific to the domain and include transparency for audits.
result Fairness in algorithms is complex and context-dependent.
Surveying risk measures for handling uncertainty in various fields.
problem Handling uncertainty in engineering and data-driven problems.
method Review of risk measures and their applications.
result Rapid development and widespread use of risk measures.
Characterizes the sample complexity of list regression tasks.
problem Understanding the sample complexity of list learning tasks in regression.
method Introducing two combinatorial dimensions: k-OIG dimension and k-fat-shattering dimension.
result These dimensions characterize realizable and agnostic k-list regression.
The paper proposes a method to evaluate ML models for subjective inference, focusing on sentence toxicity.
problem Bias in ML models for subjective inference, especially in real-life applications.
method Proposes a list of specifications to evaluate ML models for subjective inference, illustrated with a sentence toxicity example.
result Demonstrates the importance of considering subjectivity and bias in evaluating ML models.
This study assesses how share capital affects financial growth of non-financial firms listed at NSE.
problem Non-financial firms listed at NSE struggle with financial growth due to declining performance and lack of investor interest.
method Descriptive and panel data analysis of 45 non-financial firms over 10 years.
result Share capital positively and significantly influences financial growth, explaining 32.73% and 11.62% of variations in earnings per share and market capitalization growth, respectively.
The outcome of a functional genomics pipeline is usually a partial list of genomic features, ranked by their relevance in modelling biological phenotype in terms of a classification or regression model. Due to resampling protocols or just within a meta-analysis comparison, instead of one list it is often the case that …
S-SIRUS explains RF for spatial data, improving accuracy and interpretability.
problem Non-interpretable nature of Random Forest in spatially dependent data.
method Proposes S-SIRUS, a spatial extension of SIRUS for extracting interpretable rules.
result S-SIRUS outperforms SIRUS in spatially dependent data, offering higher predictive accuracy and shorter rule lists.
Paper tackles high-accuracy list-decodable learning for mean estimation.
problem Estimate the mean of a distribution with a small fraction coming from a nice distribution.
method Developed a novel proof of identifiability and a new algorithmic approach.
result Achieved high-accuracy guarantees for list-decodable mean estimation.
The study compares A and N shares returns of Chinese firms cross-listed in U.S. markets.
problem Analyzing the impact of cross-listing on Chinese stock returns.
method Used CAPM for expected returns, GARCH model for volatility, and event study method.
result Cross-listing significantly affected N shares negatively, with increased volatility for some companies.
This work characterizes when a hypothesis class can be k-list learned.
problem Characterizing when a hypothesis class can be k-list learned.
method Introducing the k-DS dimension and proving the equivalence of k-list learnability and the finiteness of the k-DS dimension.
result A hypothesis class is k-list learnable if and only if the k-DS dimension is finite.
Investigates principles of generalization in list learning, refutes sample compression conjecture.
problem Determining applicability of classical principles in list PAC learning.
method Examines uniform convergence and sample compression in list PAC learning.
result Sample compression fails in list PAC learning, refutes conjecture.
New method combines score lists using joint CDFs, improving computation.
problem Combining non-comparable score lists over a common index set.
method New algorithm for computing joint CDF values, linear runtime.
result Improved computation of joint CDF values for N-dimensional order statistics.
Introduction. Case Based Reasoning (CBR) is an emerg- ing decision making paradigm in medical research where new cases are solved relying on previously solved similar cases. Usually, a database of solved cases is provided, and every case is described through a set of attributes (inputs) and a label (output). Extracting…
TopRank algorithm improves online ranking with better performance and insights.
problem Sequential decision-making in online learning to rank with user feedback.
method Generalized click model and topological sort-based algorithm.
result TopRank outperforms existing algorithms in terms of performance and proof insight.
Study on list learning with noisy data, showing limits and some learnable cases.
problem Learning from noisy data in a list learning context.
method Inspired by coding theory, extends list learning model to study sparse conjunctions and parities/majors.
result Sparse conjunctions can be efficiently list learned under certain conditions, but parities and majors cannot be efficiently learned.
Deep Sets improve reinforcement learning for autonomous driving with variable inputs.
problem Optimal decision making in autonomous driving with varying number of objects.
method Employed Deep Sets for high-level decision making in reinforcement learning.
result Deep Sets outperform other approaches in performance and generalization.
New RL algorithm ensures stable, replicable policies.
problem Stability and replicability issues in RL algorithms.
method Introduced weak and strong forms of list replicability, developed a novel planning strategy, and tested state reachability.
result Proved efficient tabular RL algorithm with polynomial list complexity.
Deep RL learns driving decisions from compact scene descriptions.
problem Learning consistent driving behavior from varying environments.
method Compact semantic state representation for reinforcement learning.
result Agent adapts behavior online without re-training.