Detects changes in body-worn video data for police interactions.
problem Large-scale body-worn video data requires efficient change-point detection methods.
method Two-stage framework: scene classification using machine learning, change-point detection algorithms.
result Achieved over 90% recall and nearly 70% precision in detecting vehicle exits and entrances.
New method detects conflicts in police body-worn audio.
problem Poor metrics for conflict detection in police interactions.
method Adaptive noise removal, non-speech filtering, and new phrase-based measures.
result Demonstrated effectiveness on LAPD body-worn audio data.
Runaway feedback loops in predictive policing cause crime rate disparities.
problem Runaway feedback loops in predictive policing systems exacerbate crime rate disparities.
method Developed a mathematical model to explain and demonstrate interventions to prevent runaway feedback loops.
result Interventions can prevent runaway feedback loops and allow true crime rates to be learned.
Develops a method to quantify racial bias in law enforcement systems.
problem Quantify racial bias in law enforcement systems considering criminality and multi-stage interactions.
method Multi-stage causal framework incorporating criminality.
result Identifies three canonical scenarios of racial bias in law enforcement.
Predictive policing models can be biased by differential crime reporting rates.
problem Bias in predictive policing models due to differential crime reporting.
method Simulation based on Bogotá, Colombia's victimization and crime reporting data.
result Differential crime reporting rates can lead to misallocation of police patrols.
New model for multivariate discrete event data with flexible interactions.
problem Modeling multivariate discrete event data with categorical interactions.
method Developed a new modeling approach with convex constraints, two estimation procedures (LS and ML).
result Proposed model can capture arbitrary shapes of historical event influence.
Faster method detects bias in lending, hiring, and policing decisions.
problem Detecting bias in lending, hiring, and policing decisions.
method Developed a faster method for fitting threshold tests using discriminant distributions.
result Reduced computation time from hours to minutes.
Algorithm learns fair allocations in unknown group frequencies.
problem Fairness in resource allocation problems.
method Efficient learning algorithm in a censored feedback model.
result Algorithm converges to optimal fair allocation.
POLICE enforces linear constraints on deep neural networks efficiently.
problem Enforcing constraints on deep neural networks without affecting optimization.
method Provably optimal affine constraint enforcement method that minimally modifies DNNs.
result POLICE ensures DNNs fulfill affine constraints during training and testing.
Paper introduces CageBO for optimizing complex public policy problems.
problem Complex decision-making and implicit constraints in public policy.
method CageBO framework using conditional variational autoencoder.
result CageBO outperforms baselines in optimizing large-scale police redistricting.
Machine learning improves risk assessment for gender-based violence victims.
problem Accurately predicting recidivism risk in gender-based crime victims.
method Applied machine learning techniques to create models predicting recidivism risk.
result Proposed ML method outperforms classical statistical methods.
Paper tackles activity recognition from body-worn video footage.
problem Classifying frames of body-worn video footage according to the wearer's activity.
method Extract motion features and semi-supervised classification.
result Method achieves comparable results to supervised and deep learning methods using less training data.
Deep learning improves crime prediction accuracy.
problem Improving crime prediction accuracy using deep learning.
method Comparative study of 10 deep learning methods on crime data.
result Deep learning methods outperform existing methods in crime prediction.
Model-Based Offline Planning (MBOP) learns models from offline data to control systems directly.
problem Training RL policies from offline data without direct system interaction.
method Generates models from offline data and uses planning to control the system.
result Near-optimal policies found for simulated systems with minimal real-time interaction.
New model detects crime linkages from text, time, and space.
problem Detecting crime linkages from limited information.
method Spatio-temporal-textual Hawkes processes with text embeddings.
result Joint modeling of space, time, and text enhances crime linkage detection.
Framework for optimizing search engine rankings using observational data.
problem Optimizing ranking policies for search engines using limited observational data.
method Formulated expected reward optimization problem, estimated context value distribution, trained ranking policy via Bayesian inference.
result Demonstrated trade-offs in ranking policies trained on empirical reward estimates.
Machine learning predicts homicide clearance rates with SHAP explaining key features.
problem Predicting and explaining homicide clearance rates in the US.
method Nine algorithmic approaches compared; XGBoost selected. SHAP used for feature importance.
result XGBoost best predicts national homicide clearance rates; SHAP reveals key features.
New framework models time-uncertain point processes for better event prediction.
problem Uncertainty in event times in point processes.
method Formulated and discretized continuous-time Hawkes processes with time grid, enabling optimization methods for inference.
result Parameter recovery with O(1/k) convergence rate using gradient descent and VI. Study disrupts Sicilian Mafia networks using data analysis.
problem Challenges in disrupting resilient criminal networks.
method Social Network Analysis methods applied to real-world datasets.
result Neutralizing only 5% of affiliates can disrupt network connectivity by 70%.
This thesis explores how opportunity and information flow through weak ties in the labor market.
problem The impact of unemployment on individual and national well-being.
method Leveraging computational social science, network science, and data-driven theories to measure opportunity/information flow.
result Opportunity/information flow through weak ties is a key determinant of unemployment length.
Study on adversarial attacks on deep reinforcement learning policies.
problem Adversarial attacks on deep reinforcement learning policies.
method Novel method for reducing adversarial example injection frequency using value function.
result Reinforcement learning policies are vulnerable to adversarial attacks.
Bayesian model assesses criminal threat escalation.
problem Evaluate threats posed by potential violent criminals.
method Customised three-level Bayesian hierarchical model.
result Model calibrates to expert judgments and updates in real time.
In this paper, we assume an insure is allowed to purchase proportional reinsurance and can invest his or her wealth into the financial market where a savings account, stocks and bonds are available. Different from classical optimal investment and reinsurance problem, this paper studies the insurer's long-term investmen…
Detects crime series using RBM embeddings from crime narratives.
problem Detecting related crime series from crime records.
method Unsupervised learning of latent feature embeddings using Gaussian-Bernoulli RBM.
result Related cases are closer in feature space, unrelated cases are far apart.
New method debiases word embeddings for multiclass settings like race and religion.
problem Word embeddings in online texts perpetuate human stereotypes, including race and religion.
method Proposes a novel methodology to debias word embeddings in multiclass settings.
result Demonstrates robust multiclass debiasing that maintains NLP task efficacy.
This work ensures policy gradient methods converge to global optima for certain control problems.
problem Non-convex optimization challenges in policy gradient methods for complex control problems.
method Identifies structural properties ensuring non-convex objective functions have no suboptimal stationary points.
result Policy gradient methods converge to global optima under certain conditions, satisfying a Polyak-Lojasiewicz condition.
The paper develops a framework for fair machine learning predictions.
problem Fairness in machine learning models for legal and ethical decisions.
method Uses causal inference to model fairness, defining counterfactual fairness.
result Demonstrates the framework on predicting success in law school.
Machine learning predicts criminal networks' missing partnerships and future behavior.
problem Predicting and understanding criminal networks' properties and future behavior.
method Combining graph representation learning and machine learning methods.
result Outstanding accuracy in predicting missing criminal partnerships and future behavior.
Model traffic congestion events using multi-modal data and attention-based neural networks.
problem Capture non-homogeneous temporal and directional spatial dependencies in traffic congestion events.
method Attention-based neural networks for point processes, adapted tail-up model for spatial statistics.
result Superior performance compared to state-of-the-art methods on synthetic and real data.
Distill-and-Compare audits black-box models by training transparent models to mimic them.
problem Auditing proprietary, opaque black-box risk scoring models.
method Model distillation and comparison of transparent student models to black-box models.
result Identifies missing features in black-box models, improving transparency.
Survey and compare PAC-Bayes bounds for bandit problems.
problem Designing and evaluating bandit algorithms with strong performance guarantees.
method PAC-Bayes bounds applied to bandit problems.
result PAC-Bayes bounds useful for offline bandit algorithms, but loose for online algorithms.
Classi-Fly uses machine learning to infer aircraft categories from open data.
problem Lack of metadata for aircraft in open data sources.
method Machine learning approach based on aircraft movement patterns.
result Correct aircraft category inference with over 88% accuracy.
This work examines the legal requirement for AI systems to provide explanations.
problem The need for accountability in AI systems that can have significant impacts on individuals.
method Review of legal contexts requiring explanation from AI systems and technical considerations for providing such explanations.
result Technical challenges in providing explanations that align with legal requirements for AI systems.
New method recovers diverse policies from expert data using state-action pair weighting.
problem Recovering diverse policies from expert trajectories.
method Pointwise mutual information weighted behavioral cloning.
result Effective in focusing on state-action pairs most representative of the style.
Framework uses human annotations to make models robust to spurious correlations.
problem Machine learning models fail when unmeasured variables change test distributions.
method Human annotations to augment training examples, UV-DRO objective for robustness.
result Improvements of 5-10% on digit recognition task and 1.5-5% on NYPD Police Stops analysis.
VIREL uses variational inference for RL, improving policy learning and performance.
problem Challenges in learning optimal policies in reinforcement learning.
method VIREL proposes a novel probabilistic inference framework that uses a parametrised action-value function to capture future dynamics.
result VIREL enables learning deterministic optimal policies naturally and optimises value functions and policies separately.
New strategies for identifying the best arm in bandits with decreasing variances.
problem Best arm identification in bandits with time-varying variances.
method Two policies: initial wait followed by continuous sampling, and periodic sampling with weighted average.
result Analytical guarantees and simulations show improved performance over existing methods.
This work bridges offline RL and DRL to address distributional shift.
problem Distributional shift in offline RL due to difference in state-action visitation distributions.
method Proposes offline RL algorithms using DRL framework, characterizes sample complexity under single policy concentrability.
result Demonstrates superior performance of proposed algorithms through simulations.
Decision tree predicts DV recidivism with interpretable models.
problem Predicting DV re-offending to aid risk assessment and victim protection.
method Employed decision tree induction to balance accuracy and interpretability, addressing class imbalance and feature selection.
result Achieved comparable accuracy with 3 features and understandable 4-node trees.
Study evaluates fairness metrics in biased datasets.
problem Detecting bias in machine learning models trained on biased data.
method Causal inference with observational data, investigating six fairness metrics.
result Best practice guidelines for selecting fairness metrics.
New AI governance framework tackles risks in finance.
problem Risks from evolving AI models in finance.
method Agent-based framework with modular governance architecture.
result Controls quarantine harmful behavior in real time.
IFM improves recommender systems by learning flexible feature interactions.
problem Dealing with feature interactions in recommender systems can degrade performance.
method Introduces Interaction-Aware Mechanism (IAM) to learn feature and field interactions.
result Improves performance on two well-known datasets compared to state-of-the-art methods.
Surrogate-based analysis of interactions via local effect smooths
problem Detecting and characterizing feature interactions in machine learning models
method Surrogate-based analysis using generalized additive models
result Empirical validation of effectiveness for pairwise interactions
Framework integrates mental disorder measurements for personalized treatment.
problem Optimizing treatment for mental disorders with latent mental states and heterogeneity.
method Measurement theory and multi-layer neural network for complex treatment effects.
result Learned treatment policies outperform alternatives on heterogeneous treatment effects.
The paper improves decision accuracy and fairness by optimizing expert assignments.
problem Improving the accuracy and fairness of human decision making.
method Sequential decision making and weighted bipartite matchings with approximation guarantees.
result The algorithms can significantly improve both accuracy and fairness of decisions.
A new method detects interactions in neural networks using topological analysis.
problem Detecting interactions between input features in neural networks.
method Topological analysis of neural network connectivity to quantify interaction strength.
result The PID algorithm outperforms state-of-the-art baselines in interaction detection tasks.
Interactive learning framework for various settings.
problem Various interactive learning settings.
method Adapted active learning algorithm for interactive structure discovery.
result Noise-tolerant algorithm with favorable query complexity.
A new method for identifying interactions in high dimensions.
problem Challenges in identifying interactions with many covariates.
method Interaction pursuit (IP) procedure: feature screening and selection.
result The method screens interactions separately from main effects, improving effectiveness.