Zobrazeno 1 - 10
of 17 402
pro vyhledávání: '"A Talwar"'
As content generated by Large Language Model (LLM) has grown exponentially, the ability to accurately identify and fingerprint such text has become increasingly crucial. In this work, we introduce a novel black-box approach for fingerprinting LLMs, a
Externí odkaz:
http://arxiv.org/abs/2408.02871
Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein distance is an appropriate error metric for density estimation. For example, when estimating population densitie
Externí odkaz:
http://arxiv.org/abs/2406.19566
Autor:
Asi, Hilal, Boemer, Fabian, Genise, Nicholas, Mughees, Muhammad Haris, Ogilvie, Tabitha, Rishi, Rehan, Rothblum, Guy N., Talwar, Kunal, Tarbe, Karl, Zhu, Ruiyu, Zuliani, Marco
This paper presents Wally, a private search system that supports efficient semantic and keyword search queries against large databases. When sufficient clients are making the queries, Wally performance is significantly better than previous systems. I
Externí odkaz:
http://arxiv.org/abs/2406.06761
We study the problem of private online learning, specifically, online prediction from experts (OPE) and online convex optimization (OCO). We propose a new transformation that transforms lazy online learning algorithms into private algorithms. We appl
Externí odkaz:
http://arxiv.org/abs/2406.03620
We study the problem of private vector mean estimation in the shuffle model of privacy where $n$ users each have a unit vector $v^{(i)} \in\mathbb{R}^d$. We propose a new multi-message protocol that achieves the optimal error using $\tilde{\mathcal{O
Externí odkaz:
http://arxiv.org/abs/2404.10201
Ultra-reliable low-latency communication (URLLC) is the cornerstone for a broad range of emerging services in next-generation wireless networks. URLLC fundamentally relies on the network's ability to proactively determine whether sufficient resources
Externí odkaz:
http://arxiv.org/abs/2401.03059
Autor:
Suragan, Durvudkhan, Talwar, Bharat
A simple explanation is provided to explain why weighted blow up is observed for weak solutions of certain semilinear heat equations with Hardy potential. The problem we study has a power non-linearity and a forcing term which depends only upon the s
Externí odkaz:
http://arxiv.org/abs/2311.11008
Secure aggregation of high-dimensional vectors is a fundamental primitive in federated statistics and learning. A two-server system such as PRIO allows for scalable aggregation of secret-shared vectors. Adversarial clients might try to manipulate the
Externí odkaz:
http://arxiv.org/abs/2311.10237
Autor:
Pelikan, Martin, Azam, Sheikh Shams, Feldman, Vitaly, Silovsky, Jan "Honza", Talwar, Kunal, Likhomanenko, Tatiana
While federated learning (FL) has recently emerged as a promising approach to train machine learning models, it is limited to only preliminary explorations in the domain of automatic speech recognition (ASR). Moreover, FL does not inherently guarante
Externí odkaz:
http://arxiv.org/abs/2310.00098
A key challenge in many modern data analysis tasks is that user data are heterogeneous. Different users may possess vastly different numbers of data points. More importantly, it cannot be assumed that all users sample from the same underlying distrib
Externí odkaz:
http://arxiv.org/abs/2307.15835