This paper surveys fairness notions in ML and recommends the most suitable one for real-world scenarios.
problem Ensuring ML systems do not discriminate against specific individuals or sub-populations.
method Identifying fairness-related characteristics of real-world scenarios and analyzing the behavior of fairness notions.
result A decision diagram to recommend the most suitable fairness notion for specific setups.
Validates economic scenarios using statistical tests on stochastic processes.
problem Ensuring the accuracy of real-world economic scenario models.
method Applies Chevyrev and Oberhauser's (2022) signature and maximum mean distance test to various stochastic processes.
result Demonstrates the test's effectiveness across different path properties relevant to financial modeling.
Enhances portfolio optimization under uncertainty using robust multi-objective methods.
problem Uncertainties in real-world portfolio optimization scenarios.
method Robust multi-objective optimization with benchmark comparisons.
result More reliable and adaptable portfolio strategies for market uncertainties.
Survey on modeling event sequences through temporal processes.
problem Modeling phenomena with sequences of events over continuous time.
method Probabilistic models based on point processes, categorized into simple, marked, and spatio-temporal.
result Analysis of existing approaches and their applicability to prediction and modeling.
This research integrates human interaction into reinforcement learning to improve sample efficiency and real-time learning.
problem Current reinforcement learning requires thousands of samples to converge, and is prone to catastrophic failures.
method Integrates human interaction modalities (demonstrations, interventions, evaluations) into the reinforcement learning loop.
result Human interaction accelerates learning and improves sample efficiency.
Differentiable causal discovery methods perform robustly under model violations.
problem Causal discovery algorithms struggle with real-world data due to unverifiable causal assumptions.
method Benchmarked differentiable causal discovery methods under eight model assumption violations.
result Differentiable causal discovery methods exhibit robust performance under Structural Hamming Distance and Structural Intervention Distance metrics.
GRAM enhances deep RL for reliable real-world deployment.
problem Generalizing deep RL across in-distribution and out-of-distribution scenarios.
method Introduces a robust adaptation module and a joint training pipeline.
result GRAM achieves strong generalization performance in simulations and hardware.
New method detects changes online with bounds on delay.
problem Detecting changes in data streams efficiently.
method Maximizes discrepancy between pre-change and post-change distributions.
result Non-asymptotic bounds on average running length and detection delay.
Evaluates transfer learning methods in dynamic data availability scenarios.
problem Real-world data availability varies over time, leading to unrealistic TL method evaluations.
method Proposes a data manipulation framework to simulate varying data availability and domain transformations.
result Demonstrates the usefulness of the framework on proprietary and publicly available datasets.
For autonomous agents to successfully operate in the real world, anticipation of future events and states of their environment is a key competence. This problem has been formalized as a sequence extrapolation problem, where a number of observations are used to predict the sequence into the future. Real-world scenarios …
Generates multimodal safety-critical scenarios for robustness evaluation of decision-making algorithms.
problem Lack of comprehensive evaluation of neural network robustness under real-world scenarios.
method Proposes a flow-based multimodal scenario generator using weighted likelihood maximization and gradient-based sampling.
result Demonstrates improved testing efficiency and multimodal modeling capability compared to traditional methods.
Improved AST method finds more useful failure scenarios for autonomous vehicles.
problem Finding useful failure scenarios for autonomous vehicle validation is challenging.
method Adaptive Stress Testing with reward augmentation, modified to encode domain information.
result The modified AST method discovers a larger and more expressive subset of failure scenarios.
Anomaly detection method tackles hidden adversary actions in real-world scenarios.
problem Detecting hidden adversary actions in real-world scenarios where the defender cannot perfectly observe the attacker's actions.
method Extends existing anomaly detection models to handle continuous action spaces and game-theoretic framework. Proposes two algorithms: direct extension and learning-based approach.
result Learning-based approach produces less exploitable strategies and is scalable to higher dimensions.
RL faces nine challenges to apply to real-world problems.
problem Applying RL to real-world problems is difficult due to assumptions rarely met.
method Identified nine challenges, provided definitions, literature approaches, and evaluation metrics.
result Addressing all nine challenges would make RL applicable to many real-world problems.
Scenario-based testing for the safety validation of highly automated vehicles is a promising approach that is being examined in research and industry. This approach heavily relies on data from real-world scenarios to derive the necessary scenario information for testing. Measurement data should be collected at a reason…
Framework for transitioning financial models from risk-neutral to real-world measure.
problem Transitioning financial models from risk-neutral to real-world measure to better reflect market dynamics and investor preferences.
method Leveraging probability theory, specifically Girsanov's theorem, to incorporate real-world dynamics into financial models.
result Validation of the robustness and practical relevance of the methodology through case studies involving financial forecasts and stress tests.
Novel Bayesian meta-reinforcement learning framework improves traffic signal control robustness.
problem Lack of robustness and stability in adaptation for traffic signal control.
method Value-based Bayesian meta-reinforcement learning framework BM-DQN with fast-adaptation variation and DQN fast-update advantage.
result Framework adapts more quickly and robustly to new scenarios than previous methods.
CPRA efficiently finds diverse solutions in CO problems using UL and parallelization.
problem Finding optimal solutions often requires diverse outcomes in real-world applications.
method CPRA, an UL-based framework, discovers shared representations to generate diverse solutions.
result CPRA outperforms existing UL-based solvers in generating diverse solutions.
Retail company uses Prophet algorithm for accurate sales forecasting.
problem Accurate sales forecasting in the retail industry.
method Facebook's Prophet algorithm and backtesting strategy.
result Framework demonstrates real-world use case capabilities.
This work addresses missing data imputation for MNAR scenarios with identifiable deep generative models.
problem Missing data with complex missingness mechanisms (MNAR) leading to biased imputation results.
method Systematic analysis and proposal of an identifiable deep generative model.
result Proposed model provides identifiability guarantees under mild assumptions for various MNAR mechanisms.
LC-FL uses generative models to reduce communication costs in federated learning.
problem High communication costs and strict model homogeneity in federated learning.
method LC-FL employs generative models to transmit data and aggregate models.
result LC-FL reduces communication costs and supports heterogeneous models.
Paper proposes a multi-modal probabilistic prediction model for interactive behavior.
problem Predicting future motions of interacting entities in real-world scenarios.
method Generative model for joint prediction of sequential motions of interacting agents.
result Interpretable model capable of handling prediction uncertainties and multi-modal distributions.
New method improves domain adaptation by aligning sub-domains.
problem Real-world domain adaptation with shifted class distributions.
method Rebalanced sub-domain alignment and novel generalization bound.
result Improves performance in shifted class distribution scenarios.
IDAS approach for autonomous vehicles to make decisions under merging scenarios.
problem Decision making for autonomous vehicles in merging scenarios with varying driver cooperativeness.
method IDAS approach using multi-agent reinforcement learning (MARL) with curriculum learning and masking mechanism.
result IDAS approach can handle uncertainties in real-world scenarios and make strategic decisions.
A2MT learns agents to select which modalities to acquire at test time.
problem Learning agents to select modalities for multimodal temporal data acquisition.
method Perceiver IO architecture for active acquisition of multimodal temporal data.
result Agents successfully learn cost-reactive acquisition behavior on real-world datasets.
Proposes novel method for detecting novel scenarios in autonomous systems.
problem Detecting when a machine learning model makes a trustworthy prediction in dynamic, real-world situations.
method Leverages trained model's learned information and a new image similarity metric.
result Demonstrates the method's efficacy on real-world driving and indoor racing datasets.
Study compares Interval Regression models and their performance.
problem Regression models struggle with interval target values.
method Comprehensive review and comparative analysis of existing Interval Regression models.
result No single model is universally optimal for all scenarios.
Paper proposes a method for weather-informed probabilistic forecasting and scenario generation in power systems.
problem Challenges of integrating renewable energy sources into power grids due to their stochasticity and uncertainty.
method Combines probabilistic forecasting and Gaussian copula for day-ahead prediction and scenario generation of load, wind, and solar power.
result Demonstrates superior performance of the proposed weather-informed Temporal Fusion Transformer (WI-TFT) model.
SCARY dataset generates complex causal scenarios for causality research.
problem Lack of complexity in existing causal datasets.
method Synthetic dataset with 40 scenarios, three seeds, and two data generation mechanisms.
result Provides a valuable resource for realistic causal discovery.
New method handles indirect mediators in CMA for complex scenarios.
problem Handling indirect and multi-dimensional mediators in causal mediation analysis.
method Identifiable Variational Autoencoder (iVAE) architecture for multi-dimensional, indirectly observed mediators.
result Accurate estimation of direct and mediated effects in synthetic and semi-synthetic experiments.
The paper proposes a new method to estimate interest rates consistently under both risk-neutral and real-world measures.
problem Consistent estimation of interest rates under both risk-neutral and real-world measures.
method Proposes a framework using progressive and square-integrable functions to specify the change of measure, and introduces two time-dependent candidates: step and linear functions.
result The proposed methods produce more stable and realistic long-term interest rate forecasts compared to using a constant function.
FLBench automates federated learning benchmarking.
problem Manual dataset partitioning fails to simulate real-world isolated data islands.
method Develops a federated learning benchmark suite with three domains.
result Automates evaluation of federated learning systems and algorithms.
Uplift modeling aims to directly model the incremental impact of a treatment on an individual response. In this work, we address the problem from a new angle and reformulate it as a Markov Decision Process (MDP). We conducted extensive experiments on both a synthetic dataset and real-world scenarios, and showed that ou…
PIP-Net predicts pedestrian crossing intentions with up to 4-second lead.
problem Accurate pedestrian intention prediction for autonomous vehicles in real-world scenarios.
method Recurrent and temporal attention-based model using kinematic and spatial features.
result PIP-Net predicts pedestrian crossing intentions up to 4 seconds in advance.
This paper uses SLT to ensure learning guarantees in CD detection.
problem Lack of learning guarantees in CD detection algorithms.
method Adapting SLT assumptions to CD scenarios to ensure learning guarantees.
result Ensured learning guarantees in CD detection algorithms.
Survey of Monte Carlo methods for noisy, costly densities in reinforcement learning and ABC.
problem Dealing with intractable, costly, and noisy densities in real-world scenarios.
method Classification and description of Monte Carlo methodologies using surrogate models.
result Unified scheme and numerical comparisons of different methodologies.
Modeling complex systems with multi-resolution data and causal dependencies.
problem Accurate prediction of complex systems with varying causal dependencies and multi-resolution data.
method Score-based Variational Graphical Diffusion Model (Temporal-SVGDM) that constructs individual SDEs for each variable at its native resolution and couples them through a causal score mechanism.
result Improved prediction accuracy and causal understanding compared to existing methods, especially in temporal scenarios.
New algorithms improve federated learning accuracy and stability with real-world data.
problem Real-world data diversity and imbalance challenge federated learning.
method Developed new algorithms (FedVC, FedIR) to resample and reweight data.
result Significant improvements in accuracy and stability of federated learning.
Proposes a context-aware approach to deep autoencoder novelty detection.
problem Challenges of static distribution in novelty detection.
method Semi-supervised network architecture with auxiliary labels for contextual information.
result Single model achieves performance of individually trained models on various contexts.
Paper introduces a real-world image dataset for federated learning.
problem Lack of high-quality real-world data for federated learning.
method Created a dataset from 26 street cameras and 7 categories, implemented YOLO and Faster R-CNN.
result Benchmarked model performance, efficiency, and communication in federated learning.
This work tackles autonomous learning of interrelated tasks in robots.
problem Learning interrelated tasks in robots, especially in complex environments.
method Using a multi-task reinforcement learning approach within an MDP framework.
result Demonstrates how to autonomously learn interrelated tasks in robots.
Model handles missing data in partial blackouts for multivariate time series.
problem Missing values in multivariate time series data.
method Two-stage imputation process using self-attention and diffusion processes.
result Model effectively handles missing data during training and outperforms state-of-the-art.
Accurately predicting the possible behaviors of traffic participants is an essential capability for future autonomous vehicles. The majority of current researches fix the number of driving intentions by considering only a specific scenario. However, distinct driving environments usually contain various possible driving…
As machine learning transitions increasingly towards real world applications controlling the test-time cost of algorithms becomes more and more crucial. Recent work, such as the Greedy Miser and Speedboost, incorporate test-time budget constraints into the training procedure and learn classifiers that provably stay wit…
New framework tests AVs as a black box, prioritizing rare failure modes.
problem Lack of rigorous and scalable testing methods for AVs.
method Developed a simulation testing framework that learns to identify and rank failure scenarios via adaptive importance-sampling methods.
result First independent evaluation of a full-stack commercial AV system (Comma AI's OpenPilot).
This work tackles real-world robotic reinforcement learning challenges.
problem Limited success of reinforcement learning in real-world robotics.
method Proposes a system for autonomous real-world learning without instrumentation.
result Demonstrates a complete system that learns without human intervention.
DA-GNN improves robustness of GNNs by modeling noise dependencies.
problem Real-world graph node features often contain noise, leading to performance degradation in GNNs.
method DA-GNN captures noise dependencies using variational inference and new benchmark datasets.
result DA-GNN consistently outperforms existing baselines across various noise scenarios.
FavMac maximizes value while controlling cost in multi-label prediction.
problem Value-maximizing predictions with strict cost control in multi-label scenarios.
method FavMac pipeline combining any multi-label classifier with online update mechanism.
result FavMac achieves higher value with strict cost control compared to baselines.