289 papers
This paper proposes "Shortcut Invariance," a targeted Jacobian regularization method that improves out-of-distribution generalization by injecting anisotropic noise into a disentangled latent space to flatten decision boundaries along shortcut-aligned axes, thereby eliminating the need for explicit shortcut labels or conflicting training samples.
This paper demonstrates that current graph-based tabular deep learning methods fail to accurately recover underlying feature interaction structures despite their focus on predictive accuracy, and shows that explicitly modeling the true graph structure significantly improves prediction performance.
This paper introduces Overlap-Adaptive Regularization (OAR), a novel method that enhances the performance of existing CATE meta-learners in low-overlap regions by proportionally increasing regularization based on overlap weights, while offering flexible, debiased variants that preserve Neyman-orthogonality for robust inference.
This paper introduces GDR-learners, a flexible suite of generative models (including CNFs, CGANs, CVAEs, and CDMs) that achieve quasi-oracle efficiency and double robustness for estimating potential outcome distributions, thereby outperforming existing methods in both theoretical properties and empirical performance.
This paper introduces the first provably convergent online algorithms for decision-focused learning in dynamic environments by regularizing non-differentiable objectives and employing perturbation techniques to handle non-convexity, thereby establishing static and dynamic regret bounds and demonstrating superior performance over standard benchmarks.
This paper introduces A3RL, a novel framework that integrates offline and online reinforcement learning through a confidence-aware active advantage-aligned sampling strategy to dynamically prioritize high-value data, thereby overcoming challenges like catastrophic forgetting and improving sample efficiency to outperform existing methods.
This paper derives error bounds for the excess risk of deep neural network classifiers trained on noisy labels by decomposing the risk into statistical and approximation errors, utilizing independent block construction for dependent data and refining results under the low-dimensional manifold hypothesis.
This paper introduces BNEM, a robust diffusion-based sampler that learns from energy functions via bootstrapped noised energy matching to efficiently generate independent samples from Boltzmann distributions, outperforming existing methods on complex molecular dynamics benchmarks.
This paper proposes a novel Variational Learning framework for Gaussian Process Latent Variable Models that utilizes Stochastic Gradient Annealed Importance Sampling to overcome proposal distribution challenges in high-dimensional spaces, achieving tighter variational bounds and superior performance compared to state-of-the-art methods.
The paper proposes OTAD, a novel two-step defense framework that combines optimal transport theory with convex integration to train deep neural networks that achieve both high accuracy and certified local Lipschitz robustness against adversarial attacks.
This paper establishes finite-sample guarantees for a cost-driven representation learning method that learns a latent dynamic model by predicting multi-step costs, enabling the derivation of near-optimal controllers for finite-horizon Linear Quadratic Gaussian (LQG) control problems without explicitly modeling observations or actions.
This paper introduces two online neural network-based algorithms for change-point detection in large time series that demonstrate linear computational complexity, outperform existing methods on various datasets, and are proven to converge to optimal solutions under specific conditions.
This paper introduces Structural Causal Bottleneck Models (SCBMs), a novel framework that assumes causal effects between high-dimensional variables depend only on low-dimensional summary statistics, offering a flexible and estimable approach for task-specific dimension reduction and improved effect estimation in low-sample transfer learning settings.
This paper introduces Momentum SVGD-EM, an accelerated algorithm for Maximum Marginal Likelihood Estimation that integrates Nesterov momentum into both parameter updates and probability measure optimization via Stein variational gradient descent, demonstrating consistently faster convergence across diverse low- and high-dimensional tasks.
This paper proposes Generative Adversarial Regression (GAR), a minimax framework that learns conditional risk scenarios by training generators to align their policy-induced risk with real data across a broad class of policies, thereby outperforming existing baselines in preserving downstream risk metrics like Value-at-Risk and Expected Shortfall.
This paper unifies online A/B testing and off-policy evaluation by proving that standard variance reduction methods in both domains are mathematically equivalent, specifically showing that Difference-in-Means estimators correspond to optimal Inverse Propensity Scoring and that regression adjustment techniques align with Doubly Robust estimation.
This paper establishes a tight Bayesian regret bound of for Gaussian Process Posterior Sampling Reinforcement Learning in continuous control with unbounded state spaces by proving that visited states remain within a near-constant radius and applying the chaining method to control regret.
This paper introduces ReinMax-Rao and ReinMax-CV, novel gradient estimators that apply Rao-Blackwellisation and control variate techniques to the ReinMax method, effectively reducing its high variance while maintaining low bias for training variational autoencoders with discrete latent variables.
This paper introduces Local Constrained Bayesian Optimization (LCBO), a novel framework that overcomes the curse of dimensionality in high-dimensional constrained problems by alternating between local descent and uncertainty-driven exploration, achieving polynomial convergence rates and outperforming state-of-the-art methods on benchmarks up to 100 dimensions.
This paper introduces a reinforcement learning pipeline that successfully simplifies complex knot diagrams and determines the unknotting number of the composite knot $4_1\#9_{10}$ as three, confirming a recently established upper bound.