This paper investigates limitations of learning tanh neural networks under finite-precision computations and Lp accuracy guarantees.

The paper proposes a novel exponential mechanism using quadratic approximations to fine-tune machine learning models on sensitive data while providing strong differential privacy guarantees.

The paper proposes using pseudo-sensitivities, derived from adjoint sensitivity fields, as an optimal conditioning signal in a Bernoulli flow-matching framework to significantly improve the out-of-dis…

This paper introduces approximation-preserving coresets, which provide weaker guarantees than strong coresets but stronger guarantees than weak coresets for preserving the costs of good solutions in b…

This paper investigates the necessity of interaction for order-optimal 1-bit mean estimation in nonparametric finite-moment classes.

This paper analyzes the finite-time behavior of nonlinear two-time-scale stochastic approximation and identifies a sharp boundary for decoupling the $k^{-1}$ rate.

This paper proves conditions for efficiently approximating expectations of certain functions with respect to standard Gaussian or symmetric exponential probability measures.

This paper establishes a connection between neural network approximation of score functions and approximation of probability distributions generated by reverse diffusion models.

The paper presents an adaptive scaling algorithm with a competitive ratio of 1.373 for incremental submodular maximization under increasing cardinality constraint, improving upon the previous best res…

This paper proves the conjecture that Local SGD outperforms Mini-batch SGD under bounded second-order heterogeneity for general convex objectives, improving the convergence guarantee and lower bounds.

This paper introduces Polynomial-Sensitivity-Aware Pruning (PSAP), a reliability-aware structured pruning method for neural networks under homomorphic encryption, reducing catastrophic layer vulnerabi…