293 papers
This paper proposes a robust transfer learning framework that leverages side information to construct estimate-centered uncertainty sets, thereby reducing the conservatism of standard distributionally robust optimization and improving policy performance under environmental shifts with limited target data.
The paper introduces ReGEN-TAD, an interpretable generative framework that combines a convolutional-transformer architecture with econometric diagnostics to detect anomalies in high-dimensional financial time series by aggregating multiple signals into a unified, label-free score that enables economically coherent factor-level attribution.
This paper proposes a full-data, privacy-preserving conformal prediction framework that leverages differential privacy-induced stability to avoid the sample size reduction inherent in data-splitting methods, achieving sharper prediction sets and asymptotic recovery of nominal coverage levels.
This monograph offers a rigorous theoretical and methodological overview of probabilistic inference and learning with Stein's method, detailing the construction and properties of Stein discrepancies, their connection to Stein variational gradient descent, and providing precise definitions and proofs.
The paper introduces DistGP, a distributed sparse Gaussian process model that enables multi-robot collaborative mapping through local computation and Gaussian belief propagation, achieving performance comparable to centralized training while outperforming distributed neural network optimizers in accuracy, robustness, and continual learning capabilities.
This paper introduces Variational Flow Maps (VFMs), a framework that enables high-quality, single-step conditional generation and inverse problem solving by learning a noise adapter to align the initial noise distribution with observations, thereby bypassing the need for iterative sampling trajectories required by traditional diffusion models.
This paper proposes a deep learning-based framework using deep conditional transformation models and cross-fitting to estimate conditional rank-rank regression for measuring within-group intergenerational mobility, offering improved accuracy and interpretability over traditional methods for both continuous and discrete outcomes while providing rigorous asymptotic theory and empirical evidence of significant mobility patterns in the U.S. and India.
This paper introduces deep spatiotemporal engression methods that leverage lightweight generative architectures with pre-additive noise to provide accurate, reliable, and explainable probabilistic forecasts for epidemic incidences, demonstrating superior performance over existing benchmarks across multiple datasets.
This paper demonstrates that optimizing for objectives like profit or crime reduction while maintaining a zero Average Treatment Effect (ATE) can mask significant unfairness driven by confounding, thereby arguing that fairness regulations must shift from evaluating aggregate decision-level outcomes to scrutinizing model-level causal mechanisms.
This paper establishes that while policy gradient methods can achieve near-optimal performance in post-training autoregressive models when staying within the base model's support, they face an exponential query barrier to generalize beyond it unless process rewards are utilized to leverage token-level likelihood quantiles.
This paper establishes that while enforcing fairness in attribute-aware machine learning systems consistently improves outcomes for disadvantaged groups, fairness constraints in attribute-blind settings can lead to "leveling down" where both groups suffer, depending on the underlying data distribution and the presence of masked candidates.
This paper establishes the exact minimax regret rate for contextual bilateral trade under heavy-tailed valuations with infinite variance by extending self-bounding properties to real-valued settings and combining them with truncated-mean estimation to derive an epoch-based algorithm that interpolates between classical nonparametric and trivial linear rates.
The paper introduces CREDO, a method that combines interpretable credal envelopes with conformal calibration to generate distribution-free prediction intervals that explicitly account for epistemic uncertainty while maintaining rigorous coverage guarantees.
This paper establishes theoretical bounds on the approximation error of Laplacian-based state representations in reinforcement learning, demonstrating how the error scales with the algebraic connectivity of the state graph and providing a comprehensive error decomposition that accounts for both representation learning and eigenvector estimation under general non-uniform policies.
This paper addresses the intrinsic gradient bias in concave multi-objective reinforcement learning caused by nonlinear scalarization, demonstrating that existing methods suffer suboptimal sample complexity while proposing a Natural Policy Gradient algorithm with multi-level Monte Carlo estimation (or vanilla NPG under second-order smoothness) to achieve the optimal sample complexity.
This paper introduces "decalibration," an efficient method that generates credal sets as probability intervals for complex foundation models without requiring computationally expensive retraining, thereby enabling robust uncertainty representation in safety-critical applications.
This paper introduces a novel optimization algorithm based on Fractional Weyl Integrals that replaces instantaneous gradients with a memory-weighted historical sequence to effectively mitigate overfitting and significantly improve performance on imbalanced datasets, such as those in financial fraud detection and medical diagnostics.
This paper introduces a gradient-based optimization method for generating time series counterfactual explanations that ensures plausibility by integrating soft-DTW alignment with k-nearest neighbors, resulting in valid and temporally realistic outputs that outperform existing approaches in distributional alignment.
This paper critiques the current metric-centric evaluation paradigm in long-term time series forecasting, arguing that an overreliance on aggregate error metrics like MSE and MAE misaligns with real-world objectives, and proposes a multi-dimensional framework prioritizing structural coherence and decision-level relevance to advance meaningful forecasting progress.
This paper presents a novel explainable condition monitoring methodology that utilizes probabilistic anomaly detection on healthy data alone, incorporating Bayesian uncertainty quantification and interpretability tools to effectively detect and anticipate faults in safety-critical systems like helicopter transmissions.