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

The paper develops a quantitative framework to analyze and improve flow distillation in diffusion models, providing stability guarantees and suggesting non-uniform time scheduling to reduce approximat…

The paper proposes a kernel-based, polynomial approximation of the ReLU activation function to enable the use of non-linear deep learning models, such as LLMs, within the constraints of Homomorphic En…

ShaplEIG introduces a Bayesian experimental design framework to efficiently and adaptively estimate Shapley values by minimizing the number of required costly function evaluations.

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 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…

The paper introduces a novel threat model, approximate obfuscation, and proposes a framework to detect IP piracy in approximate circuits by comparing their statistical error profiles.

The paper proposes FOAM, an adaptive damping method that stabilizes the Shampoo optimization algorithm by dynamically controlling damping and eigendecomposition frequency, thereby reducing staleness-i…

This paper proves several properties about Extended Frege proof systems and circuit equivalence.

This paper settles the complexity of three sketching problems in graphs and distributions.

This paper introduces a new variant of the Traveling Salesman Problem where the goal is to find two paths connecting a set of sites while minimizing the Fréchet distance between the two paths.

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…

The paper introduces novel, efficient differentially private algorithms for estimating monotone statistics, significantly improving sample complexity compared to existing methods.

This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…

The paper introduces a method to efficiently detect 'essential' constraints in Boolean MinCSPs, significantly reducing the search space for solving these problems and providing a dichotomy theorem for…

The paper establishes tight upper and lower bounds on the statistical cost of approximate machine unlearning for smooth strongly convex losses, showing that the optimal unlearning rate depends critica…

This paper improves the theoretical bounds for estimating discrete probability distributions using the $\ell_\infty$ norm, resolving several open questions in the field.

The paper introduces PostRI, a novel method that allows for computing a Randomization Interval (RI) for differentially private median queries after the median has already been estimated, significantly…

The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight res…

The paper proposes a novel method using random walks and equitable partitions to derive an inequality for the total variation distance of codes, generalizing existing bounds for finite abelian groups.