~ similar to 2606.00412· 19 results
The paper formalizes the problem of representation identifiability in supervised learning, showing that a representation property is identifiable if and only if it is constant across all possible fact…
This paper introduces a local information-operator framework to analyze spatial identifiability in inverse problems where spatially varying fields are inferred from heterogeneous observations.
The paper proposes a novel method to identify parsimonious explicit piece-wise polynomial relationships, demonstrating its effectiveness in modeling the inverse kinematics of industrial manipulator ro…
The paper introduces and explores Truly Linear FPT (TLFPT), a complexity class defined by $O(n) + f(k)$, demonstrating that it is a strict subset of standard Linear FPT and providing new algorithms fo…
This paper analyzes the computational complexity of verifying feedforward neural networks when their weights are restricted to finite-width arithmetic, finding that verification remains NP-complete fo…
Haoyang Liu, Jie Wang, Boxuan Niu, Xiongwei Han +7 more
The paper introduces Opt-Verifier, a novel LLM-based framework that significantly improves the accuracy of automated optimization model generation by implementing dual-side verification from both stru…
The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…
Amirpasha Hedayat, Ali Mohaghegh, Laura Balzano, Cheng Huang +1 more
The paper introduces a history-aware adaptive Reduced-Order Model (ROM) framework using incremental Singular Value Decomposition (iSVD) that maintains accuracy for online dynamics far beyond the initi…
The paper analyzes the structured CVP distance on the log-unit lattice of cyclotomic fields, significantly reducing the conjectured CDPR factor for the ML-KEM cryptosystem from exponential to sub-poly…
This paper analyzes the computational complexity of evaluating recurrent functions, showing that the complexity depends heavily on how the input offsets are encoded and the structure of the recurrence…
AdaKoop introduces an efficient streaming algorithm that models complex nonlinear dynamics from nonstationary data streams by leveraging the Koopman operator theory, achieving state-of-the-art accurac…
The paper systematically investigates the conditions under which linear layers in AES-like ciphers avoid related-differential structures, proving that the MDS property is necessary and identifying spe…
The paper introduces a Variational Encrypted Model Predictive Control (VEMPC) protocol that enables online MPC execution using only encrypted polynomial operations, eliminating the need for intermedia…
The paper introduces Multifidelity Proper Orthogonal Decomposition (MFPOD), a method that significantly reduces the computational cost of dimension reduction by intelligently combining data from cheap…
Weijun Li, Arnaud Grivet Sébert, Qiongkai Xu, Annabelle McIver +1 more
The paper proposes an empirical calibration method, TeDA, to provide a more comparable and interpretable assessment of privacy loss for text rewriting mechanisms under Local Differential Privacy (LDP)…
The paper develops a formal theory to analyze how throughput changes in AI-enhanced cybersecurity pipelines when stage capacities are perturbed by multipliers.
The paper introduces a non-intrusive variant of index-aware learning for solving differential-algebraic equations (DAEs), ensuring that learned solutions maintain physical consistency like Kirchhoff's…
Wanying Ren, Xin Song, Futing Wang, Guoxiu He +1 more
The paper theoretically analyzes the limitations of parameter-based knowledge editing and empirically demonstrates that these methods consistently damage core LLM capabilities compared to retrieval-ba…
The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…