paper-with-me

홈 › Papers

Noisy Computing of the $\mathsf{OR}$ and $\mathsf{MAX}$ Functions

2023-09-07 · Banghua Zhu, Ziao Wang, Nadim Ghaddar, Jiantao Jiao, Lele Wang

We consider the problem of computing a function of $n$ variables using noisy queries, where each query is incorrect with some fixed and known probability $p \in (0,1/2)$. Specifically, we consider the computation of the $\mathsf{OR}$ function of $n$ bits (where queries correspond to noisy readings of the bits) and the $\mathsf{MAX}$ function of $n$ real numbers (where queries correspond to noisy pairwise comparisons). We show that an expected number of queries of \[ (1 \pm o(1)) \frac{n\log \frac{1}{\delta}}{D_{\mathsf{KL}}(p \| 1-p)} \] is both sufficient and necessary to compute both functions with a vanishing error probability $\delta = o(1)$, where $D_{\mathsf{KL}}(p \| 1-p)$ denotes the Kullback-Leibler divergence between $\mathsf{Bern}(p)$ and $\mathsf{Bern}(1-p)$ distributions. Compared to previous work, our results tighten the dependence on $p$ in both the upper and lower bounds for the two functions.

📄 PDF Abstract BibTeX arXiv:2309.03986

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries

2024-07-08 · Nirmit Joshi, Theodor Misiakiewicz, Nathan Srebro

The goal of this paper is to investigate the complexity of gradient algorithms when learning sparse functions (juntas). We introduce a type of Statistical Queries ($\mathsf{SQ}$), which we call Differentiable Learning Qu…

Online Low Rank Matrix Completion

2022-09-08 · Prateek Jain, Soumyabrata Pal

We study the problem of {\em online} low-rank matrix completion with $\mathsf{M}$ users, $\mathsf{N}$ items and $\mathsf{T}$ rounds. In each round, the algorithm recommends one item per user, for which it gets a (noisy) …

ClusteringCollaborative FilteringLow-Rank Matrix CompletionMatrix Completion

Families of costs with zero and nonnegative MTW tensor in optimal transport

2024-01-01 · Du Nguyen

We compute explicitly the MTW tensor (or cross curvature) for the optimal transport problem on $\mathbb{R}^n$ with a cost function of form $\mathsf{c}(x, y) = \mathsf{u}(x^{\mathfrak{t}}y)$, where $\mathsf{u}$ is a scala…

Form

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

2023-09-21 · NeurIPS 2023 11

Large Language Models (LLMs), despite their recent impressive accomplishments, are notably cost-prohibitive to deploy, particularly for applications involving long-content generation, such as dialogue systems and story w…

On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results

2021-04-16 · Marcelo Arenas, Pablo Barceló, Leopoldo Bertossi, Mikaël Monet

In Machine Learning, the $\mathsf{SHAP}$-score is a version of the Shapley value that is used to explain the result of a learned model on a specific entity by assigning a score to every feature. While in general computin…