Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Asadi, A. R."'
Autor:
Aminian, Gholamali, Asadi, Amir R., Li, Tian, Beirami, Ahmad, Reinert, Gesine, Cohen, Samuel N.
The generalization error (risk) of a supervised statistical learning algorithm quantifies its prediction ability on previously unseen data. Inspired by exponential tilting, Li et al. (2021) proposed the tilted empirical risk as a non-linear risk metr
Externí odkaz:
http://arxiv.org/abs/2409.19431
Autor:
Asadi, Vahid R., Kuroiwa, Kohdai, Leung, Debbie, May, Alex, Pasterski, Sabrina, Waddell, Chris
The conditional disclosure of secrets (CDS) primitive is among the simplest cryptographic settings in which to study the relationship between communication, randomness, and security. CDS involves two parties, Alice and Bob, who do not communicate but
Externí odkaz:
http://arxiv.org/abs/2404.14491
A non-local quantum computation (NLQC) replaces an interaction between two quantum systems with a single simultaneous round of communication and shared entanglement. We study two classes of NLQC, $f$-routing and $f$-BB84, which are of relevance to cl
Externí odkaz:
http://arxiv.org/abs/2402.18647
We study simple binary hypothesis testing under both local differential privacy (LDP) and communication constraints. We qualify our results as either minimax optimal or instance optimal: the former hold for the set of distribution pairs with prescrib
Externí odkaz:
http://arxiv.org/abs/2301.03566
Autor:
Asadi, Amir R.
Machine learning is the dominant approach to artificial intelligence, through which computers learn from data and experience. In the framework of supervised learning, a necessity for a computer to learn from data accurately and efficiently is to be p
Externí odkaz:
http://arxiv.org/abs/2212.14681
We study the problem of designing worst-case to average-case reductions for quantum algorithms. For all linear problems, we provide an explicit and efficient transformation of quantum algorithms that are only correct on a small (even sub-constant) fr
Externí odkaz:
http://arxiv.org/abs/2212.03348
We present a new framework for designing worst-case to average-case reductions. For a large class of problems, it provides an explicit transformation of algorithms running in time $T$ that are only correct on a small (subconstant) fraction of their i
Externí odkaz:
http://arxiv.org/abs/2202.08996
Autor:
Asadi, Vahid R., Carmosino, Marco L., Jahanara, Mohammadmahdi, Rafiey, Akbar, Salamatian, Bahar
Protecting the privacy of people whose data is used by machine learning algorithms is important. Differential Privacy is the appropriate mathematical framework for formal guarantees of privacy, and boosted decision trees are a popular machine learnin
Externí odkaz:
http://arxiv.org/abs/2201.12648
Autor:
Asadi, Vahid R., Shinkar, Igor
Locally decodable codes (LDCs) are error-correcting codes $C : \Sigma^k \to \Sigma^n$ that admit a local decoding algorithm that recovers each individual bit of the message by querying only a few bits from a noisy codeword. An important question in t
Externí odkaz:
http://arxiv.org/abs/2009.07311
Autor:
Asadi, Amir R., Abbe, Emmanuel
A well-known result across information theory, machine learning, and statistical physics shows that the maximum entropy distribution under a mean constraint has an exponential form called the Gibbs-Boltzmann distribution. This is used for instance in
Externí odkaz:
http://arxiv.org/abs/2006.14614