Results 11 to 20 of about 1,414,908 (321)
Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning [PDF]
IEEE Symposium on Security and Privacy, 2021 Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a dataset D, or a ...
Milad Nasr +4 more
semanticscholar +1 more source
Information-theoretic bounds on quantum advantage in machine learning [PDF]
Physical Review Letters, 2021 We study the performance of classical and quantum machine learning (ML) models in predicting outcomes of physical experiments. The experiments depend on an input parameter x and involve execution of a (possibly unknown) quantum process E.
Hsin-Yuan Huang, R. Kueng, J. Preskill
semanticscholar +1 more source
Encoding-dependent generalization bounds for parametrized quantum circuits [PDF]
Quantum, 2021 A large body of recent work has begun to explore the potential of parametrized quantum circuits (PQCs) as machine learning models, within the framework of hybrid quantum-classical optimization.
Matthias C. Caro +4 more
semanticscholar +1 more source
BOUNDED AND FULLY BOUNDED MODULES [PDF]
Bulletin of the Australian Mathematical Society, 2011 AbstractGeneralizing the concept of right bounded rings, a module MR is called bounded if annR(M/N)≤eRR for all N≤eMR. The module MR is called fully bounded if (M/P) is bounded as a module over R/annR(M/P) for any ℒ2-prime submodule P◃MR. Boundedness and right boundedness are Morita invariant properties.
Haghany, A., Mazrooei, M., Vedadi, M. R.
openaire +2 more sources
Error bounds for approximations with deep ReLU networks [PDF]
Neural Networks, 2016 We study expressive power of shallow and deep neural networks with piece-wise linear activation functions. We establish new rigorous upper and lower bounds for the network complexity in the setting of approximations in Sobolev spaces.
D. Yarotsky
semanticscholar +1 more source
Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting [PDF]
IEEE Transactions on Information Theory, 2009 Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multiarmed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low norm in a ...
Niranjan Srinivas +3 more
semanticscholar +1 more source
New positivity bounds from full crossing symmetry [PDF]
Journal of High Energy Physics, 2020 Positivity bounds are powerful tools to constrain effective field theories. Utilizing the partial wave expansion in the dispersion relation and the full crossing symmetry of the scattering amplitude, we derive several sets of generically nonlinear ...
A. Tolley, Zi-yue Wang, Shuang-Yong Zhou
semanticscholar +1 more source
Lipschitz Bounds and Nonautonomous Integrals [PDF]
Archive for Rational Mechanics and Analysis, 2020 We provide a general approach to Lipschitz regularity of solutions for a large class of vector-valued, nonautonomous variational problems exhibiting nonuniform ellipticity.
Cristiana De Filippis, G. Mingione
semanticscholar +1 more source
Simple yet sharp sensitivity analysis for unmeasured confounding
Journal of Causal Inference, 2022 We present a method for assessing the sensitivity of the true causal effect to unmeasured confounding. The method requires the analyst to set two intuitive parameters. Otherwise, the method is assumption free. The method returns an interval that contains
Peña Jose M.
doaj +1 more source
Frontiers in Veterinary Science, 2021 Case-based learning is a valuable tool to impart various problem-solving skills in veterinary education and stimulate active learning. Students can solve imaginary cases without the need for contact with real patients.
Jasmin Nessler +2 more
doaj +1 more source