329 papers
The paper introduces AuToMATo, a novel persistence-based clustering algorithm that combines ToMATo with bootstrapping to provide robust, out-of-the-box performance without parameter tuning, making it particularly effective for topological data analysis applications like Mapper.
The paper proposes LoCo-RLHF, a framework that leverages low-rank contextual modeling and a pessimistic reduced-subspace policy to effectively align large language models with heterogeneous human feedback while ensuring computational efficiency and robustness to distributional shifts.
The paper proposes DCENWCNet, a novel deep CNN ensemble model that integrates three uniquely configured architectures to achieve state-of-the-art accuracy and robustness in white blood cell classification on the Rabbin-WBC dataset, while employing LIME to enhance model interpretability and trust in automated diagnosis.
This paper proposes a scalable physics-informed deep generative model (sPI-GeM) that overcomes the limitations of existing methods by effectively solving forward and inverse stochastic differential equations in high-dimensional stochastic and spatial spaces through a combination of physics-informed basis networks and a deep generative model.
This paper establishes a tighter information-theoretic lower bound and proposes a modified Track-and-Stop algorithm with a tie-aware stopping rule that achieves asymptotic instance-optimality for best-arm identification in stochastic multi-armed bandits when the number of optimal arms is known.
This paper analyzes the convergence and escape dynamics of Stochastic Gradient Descent in one-dimensional landscapes, establishing that while SGD reliably converges to local minima, it may linger near local maxima depending on noise variance and geometry, with specific results provided for the probability of escaping sharp maxima to neighboring minima.
This paper proposes a computationally efficient supervised filter based on a Gumbel-copula implied upper-tail concordance score to identify features that are simultaneously extreme with the positive class, demonstrating its effectiveness in ranking clinically relevant predictors for diabetes risk across large-scale and clinical datasets while outperforming standard filters and matching strong baselines.
This paper introduces Supervised Calibration (SC), a loss-minimization framework that enhances In-Context Learning in Large Language Models by learning optimal per-class affine transformations to correct systematic biases and alter decision boundary orientations, thereby achieving state-of-the-art performance across multiple models and datasets.
This paper challenges the default use of honest estimation in causal forests, demonstrating through extensive benchmarking that while it prevents overfitting, it often increases underfitting and reduces the accuracy of individual-level treatment effect estimates, suggesting its application should be guided by specific goals and empirical evaluation rather than reflexive adoption.
This paper proposes a novel Bayesian framework that generalizes federated ADMM by leveraging variational inference duality, yielding both a theoretical unification of ADMM with Gaussian assumptions and practical, high-performance variants like Newton-like and Adam-like updates for diverse distribution families.
This paper establishes Gaussian approximation bounds for the finite-dimensional distributions of deep neural networks with randomly initialized weights and Lipschitz activations, proving convergence to a Gaussian limit as layer widths grow and deriving specific convergence rates that depend on the network depth.
This paper analyzes the asymptotic performance of best-of- LLM ensembling via majority voting as , proposing an adaptive generation scheme to efficiently allocate inference budgets and an optimal weighted ensemble method formulated as a mixed-integer linear program to outperform individual models.
This paper introduces the Online Learning in the Replay Setting to model systems training on self-annotated data, establishing the Extended Threshold dimension as the exact measure of learnability and proving that while proper learners may fail catastrophically, specific improper algorithms can achieve optimal mistake bounds against replay adversaries.
This paper introduces MAYA, a sequential imitation learning model based on multi-armed bandits that effectively reproduces and predicts individual bees' foraging decisions by accounting for their limited memory through an optimal temporal window, outperforming existing baselines while offering interpretability for ecological applications.
This paper demonstrates that the implicit bias of per-sample Adam on separable data can deviate from the full-batch -max-margin behavior, potentially converging to the -max-margin classifier or a data-adaptive Mahalanobis-norm margin depending on the dataset, whereas Signum consistently converges to the -max-margin regardless of batch size.
This paper characterizes the second-order implicit bias of the Jordan-Kinderlehrer-Otto (JKO) scheme as a Wasserstein gradient flow on a modified energy functional that subtracts a term proportional to the squared metric curvature of the original energy, thereby explaining the scheme's unique stability and dissipation properties through its deceleration in directions of rapidly changing curvature.
This paper introduces an intrinsic drift budget based on Fisher-Rao distance to quantify cumulative distributional motion in closed-loop learning, establishing tight prequential reproducibility bounds that reveal an irreducible accuracy floor proportional to the average drift rate.
This paper establishes a unified statistical framework demonstrating that synthetic augmentation in imbalanced learning is not universally beneficial, revealing that its efficacy and optimal quantity depend on local data symmetry and generator alignment, and proposing a Validation-Tuned Synthetic Size (VTSS) strategy to empirically determine the best augmentation level.
This paper establishes a homology theory for ample groupoids using compactly supported Moore complexes, proving functoriality and Kakutani invariance, deriving Mayer-Vietoris sequences, and demonstrating that a universal coefficient theorem holds for discrete coefficients while identifying specific obstructions for non-discrete ones.
This paper proposes a sample-efficient tensor factorization model that combines cheap automated ratings with a small set of human labels to enable fine-grained, accurate, and confidence-interval-backed evaluation of generative models at the prompt level.