Results 1 to 10 of about 17,304 (236)
Sublinear regret for learning POMDPs [PDF]
Production and Operations Management, 2021 We study the model‐based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs). The oracle we consider is the optimal policy of the POMDP with a known environment in terms of the average reward over an infinite ...
Yi Xiong +3 more
semanticscholar +3 more sources
Scaling of cardiovascular risk factors in 230 Latin American cities [PDF]
Scientific ReportsUrbanization results in increased numbers of people living in cities and poses challenges and opportunities to public health policies. Studies of urban scaling have unveiled how cities’ socio-economic and infrastructural attributes vary systematically ...
Aureliano S. S. Paiva +15 more
doaj +2 more sources
Demonstration that sublinear dendrites enable linearly non-separable computations [PDF]
Scientific ReportsTheory predicts that nonlinear summation of synaptic potentials within dendrites allows neurons to perform linearly non-separable computations (LNSCs). Using Boolean analysis approaches, we predicted that both supralinear and sublinear synaptic summation
Romain D. Cazé +3 more
doaj +2 more sources
Scalable Private Decision Tree Evaluation with Sublinear Communication [PDF]
ACM Asia Conference on Computer and Communications Security, 2022 Private decision tree evaluation (PDTE) allows a decision tree holder to run a secure protocol with a feature provider. By running the protocol, the feature provider will learn a classification result. Nothing more is revealed to either party.
Jianli Bai +4 more
semanticscholar +1 more source
Sublinear Time Algorithms and Complexity of Approximate Maximum Matching [PDF]
Symposium on the Theory of Computing, 2022 Sublinear time algorithms for approximating maximum matching size have long been studied. Much of the progress over the last two decades on this problem has been on the algorithmic side.
Soheil Behnezhad +2 more
semanticscholar +1 more source
Sublinear Algorithms for (1.5+𝜖)-Approximate Matching
Symposium on the Theory of Computing, 2023 We study sublinear time algorithms for estimating the size of maximum matching. After a long line of research, the problem was finally settled by Behnezhad [FOCS’22], in the regime where one is willing to pay an approximation factor of 2.
Sayan Bhattacharya +2 more
semanticscholar +1 more source
Training Overparametrized Neural Networks in Sublinear Time [PDF]
arXiv.org, 2022 The success of deep learning comes at a tremendous computational and energy cost, and the scalability of training massively overparametrized neural networks is becoming a real barrier to the progress of artificial intelligence (AI).
Han Hu +3 more
semanticscholar +1 more source
A Sublinear Adversarial Training Algorithm [PDF]
International Conference on Learning Representations, 2022 Adversarial training is a widely used strategy for making neural networks resistant to adversarial perturbations. For a neural network of width $m$, $n$ input training data in $d$ dimension, it takes $\Omega(mnd)$ time cost per training iteration for the
Yeqi Gao +3 more
semanticscholar +1 more source
Sublinear scaling of the cellular proteome with ploidy
Nature Communications, 2022 Ploidy changes are frequent in nature and contribute to evolution, functional specialization and tumorigenesis. Analysis of model organisms of different ploidies revealed that increased ploidy leads to an increase in cell and nuclear volume, reduced ...
G. Yahya +11 more
semanticscholar +1 more source
Configurable sublinear circuits for quantum state preparation [PDF]
Quantum Information Processing, 2021 The theory of quantum algorithms promises unprecedented benefits of harnessing the laws of quantum mechanics for solving certain computational problems.
Israel F. Araujo +5 more
semanticscholar +1 more source