289 papers
This paper introduces ULFS-KDPE, a novel kernel-based estimator that achieves semiparametric efficiency for pathwise differentiable parameters in nonparametric models by constructing a data-adaptive debiasing flow via a universal least favorable submodel, thereby eliminating the need for explicit efficient influence function derivation while ensuring rigorous theoretical guarantees and computational tractability.
The paper presents Midicoth, a lossless compression system that enhances online probability estimation by applying a lightweight, multi-stage micro-diffusion denoising layer to correct systematic biases in adaptive statistical models through a data-efficient, binary-tree decomposition of byte predictions.
This paper establishes a fundamental trilemma in AI safety, proving that no verification procedure can simultaneously guarantee soundness, generality, and tractability, thereby demonstrating that formal alignment certification is impossible without relaxing at least one of these critical properties.
This paper presents a physics-informed neural network (PINN) framework that robustly reconstructs hidden state variables and estimates biophysical parameters in multiscale neuronal models using only partial, noisy voltage observations, effectively overcoming the convergence failures and sensitivity issues common in traditional numerical methods.
This paper introduces a family of mean-normalized matrix operator norms to derive width-independent smoothness bounds for deep neural networks, leading to the development of MOGA, a row/column-normalized optimizer that enables stable hyperparameter transfer across model widths and outperforms Muon in speed while maintaining competitive performance.
This paper proposes a novel hierarchical multi-task multi-fidelity (H-MT-MF) framework for Gaussian process-based surrogate modeling that unifies inter-task information sharing and fidelity-dependent uncertainty handling to significantly improve prediction accuracy and data efficiency in manufacturing systems with heterogeneous data sources.
This paper derives upper PAC generalization bounds for neural oscillators based on second-order ODEs and MLPs, demonstrating that their estimation errors grow polynomially with model size and time while showing that constraining MLP Lipschitz constants via regularization enhances generalization performance in modeling nonlinear structural systems.
This paper presents a unified framework for traditional and convex Non-negative Matrix Factorization (NMF) under Negative Binomial and Tweedie distributions, deriving novel multiplicative update rules via Majorize-Minimization and demonstrating through empirical evaluation that appropriate noise model selection and convex formulations significantly improve feature recovery in overdispersed data.
This paper establishes a non-asymptotic Gaussian comparison theorem based on Gordon's theorem to rigorously validate dynamic mean-field expressions and derive refined iterative approximations for the training dynamics of machine learning models, such as perceptrons, under Gaussian mixture data.
This paper introduces efficient, representation-based transductive generalization bounds for graph node classification using optimal transport and Wasserstein distances, which not only correlate strongly with empirical performance but also explain the non-monotonic relationship between GNN depth and generalization error through the analysis of distributional transformations.
This paper presents an improved distributed protocol for the distributed experts problem that achieves a specific regret bound while significantly reducing communication costs compared to previous work.
This paper introduces the Temporal Markov Transition Field (TMTF), a novel time series representation that overcomes the limitations of the global Markov Transition Field by partitioning data into temporal chunks to preserve regime-specific dynamics, thereby creating a structured image suitable for convolutional neural networks.
This paper introduces Bayesian Generative Modeling (BGM), a unified framework that leverages a stochastic iterative Bayesian updating algorithm to learn a single generative model capable of performing arbitrary conditional inference with principled uncertainty quantification, without requiring retraining for different conditioning structures.
This paper critiques the prevalent reliance on fixed-threshold metrics in machine learning evaluation by advocating for a consequentialist framework that prioritizes proper scoring rules like the Brier score, supported by a new decision-theoretic mapping, a practical Python package called `briertools`, and a clipped Brier score variant to bridge the gap between theoretical utility and current practices.
This paper introduces Variational Mixture-of-Experts Routing (VMoER), a scalable Bayesian framework that confines uncertainty quantification to the expert-selection stage of Mixture-of-Experts Transformers, achieving significant improvements in calibration, stability, and out-of-distribution detection with negligible computational overhead.
This paper introduces Transfer-Informed Betting (TIB), a novel method that combines betting-based confidence sequences with cross-domain transfer learning to achieve tighter, data-efficient risk guarantees for selective prediction, demonstrating significant coverage improvements over existing bounds across multiple benchmarks and applications.
This paper proposes a multi-level meta-reinforcement learning framework that systematically compresses Markov decision processes into hierarchical structures with skill-based curriculum learning to decouple sub-tasks, reduce stochasticity, and enable efficient transfer of skills across different problems and levels.
This paper introduces the Variable-Invariant Two-Dimensional State Space Model (VI 2D SSM) and its unified VI 2D Mamba architecture, which theoretically establish and implement a permutation-equivariant framework for multivariate time series that eliminates artificial variable ordering to achieve state-of-the-art performance with improved structural scalability.
This paper introduces Robust Regularized Policy Iteration (RRPI), a novel offline reinforcement learning framework that unifies policy-induced extrapolation and transition uncertainty by formulating robust policy optimization with a tractable KL-regularized surrogate, offering theoretical convergence guarantees and demonstrating superior performance and robustness on D4RL benchmarks.
This paper proposes a novel statistical learning framework for multi-item auctions that utilizes nonparametric density estimation and credible intervals to implement two cost-reducing strategies, which maintain key economic properties like incentive compatibility and fairness while outperforming alternative methods in both revenue maximization and implementation efficiency.