This paper establishes a large deviation principle for the generalization error of interpolating classifiers in the overparametrized regime.

The paper introduces the $\alpha$-Wasserstein mechanism to achieve Rényi Pufferfish Privacy using Laplace and Gaussian noise, demonstrating that it generalizes existing privacy frameworks and reduces…

The paper improves Banaszczyk's inequality, providing a significantly better tail estimate for the discrete Gaussian measure on a lattice, which has applications in analyzing dual attacks against the…

The paper analyzes the phase transitions of the noisy transformer model on the unit sphere, proving a sharp global-minimizer dichotomy that depends on the dimension and coupling strength.

The paper refutes Steurer's conjecture regarding the existence of large constant-separated sets within families of unit-norm vectors with low average correlation, using high-dimensional expanders to s…

This paper analyzes the conditions under which Bitcoin's security might fail due to miners deviating from honest mining when block rewards decline to zero, concluding that protocol mechanisms can miti…

This paper develops a novel, computationally efficient method to quantify the uncertainty in wide neural network predictions by characterizing the limiting random fluctuations using stochastic evoluti…

The paper introduces the Generalized Thresholding Mechanism (GTM) to solve the generalized private testing problem in differential privacy, achieving near-optimal accuracy and sample complexity guaran…

This paper introduces a novel framework for differentially private sampling by using the Wasserstein distance as the utility measure, proposing the Wasserstein Projection Mechanism (WPM) to address li…

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 extends the privacy subsidy concept from the single-period Kyle model to continuous time, deriving a closed-form expression for the cumulative expected transfer (privacy subsidy) in a conti…

This paper develops a perturbation theory for spherical Hellinger-Kantorovich (SHK) gradient flows, providing explicit, time-dependent bounds on divergence metrics to guarantee differential privacy fo…

This paper demonstrates that the classical discrete Laplace mechanism can be post-processed to create versatile, unbiased estimators for various subexponential functions, making it a preferred choice…

This paper develops improved Gaussian mechanisms for Rényi Pufferfish Privacy (RPP) by incorporating Gaussian and Gaussian-mixture priors, significantly reducing the required noise and improving the p…

The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distributio…

The paper provides a tight, transparent, and closed-form analysis of the trade-off function for Differentially Private SGD using random shuffling, significantly improving upon previous methods and est…

This paper shows that standard optimal control in Markov Decision Processes (MDPs) with an absorbing catastrophic state naturally generates behavioral signatures mimicking prospect theory, even withou…

The paper addresses the failure of fixed-price inference in resource-constrained pricing controllers by developing a target-aware controller that tracks local densities and provides certified, shrinki…

The paper proves that standard runtime enforcement mechanisms cannot detect systematic behavioral drift in autonomous agents, proposing a new Invariant Measurement Layer (IML) that restores observabil…

The paper introduces the Kerimov-Alekberli model, an information-geometric framework that uses non-equilibrium thermodynamics and stochastic control to provide a physically grounded method for detecti…