The unprecedented demand for collaborative machine learning in a privacy-preserving manner gives rise to a novel machine learning paradigm called federated learning (FL). Given a sufficient level of privacy guarantees, the practicality of an FL syste
m mainly depends on its time-to-accuracy performance during the training process. Despite bearing some resemblance with traditional distributed training, FL has four distinct challenges that complicate the optimization towards shorter time-to-accuracy: information deficiency, coupling for contrasting factors, client heterogeneity, and huge configuration space. Motivated by the need for inspiring related research, in this paper we survey highly relevant attempts in the FL literature and organize them by the related training phases in the standard workflow: selection, configuration, and reporting. We also review exploratory work including measurement studies and benchmarking tools to friendly support FL developers. Although a few survey articles on FL already exist, our work differs from them in terms of the focus, classification, and implications.
Homomorphic encryption (HE) is a promising privacy-preserving technique for cross-silo federated learning (FL), where organizations perform collaborative model training on decentralized data. Despite the strong privacy guarantee, general HE schemes r
esult in significant computation and communication overhead. Prior works employ batch encryption to address this problem, but it is still suboptimal in mitigating communication overhead and is incompatible with sparsification techniques. In this paper, we propose FLASHE, an HE scheme tailored for cross-silo FL. To capture the minimum requirements of security and functionality, FLASHE drops the asymmetric-key design and only involves modular addition operations with random numbers. Depending on whether to accommodate sparsification techniques, FLASHE is optimized in computation efficiency with different approaches. We have implemented FLASHE as a pluggable module atop FATE, an industrial platform for cross-silo FL. Compared to plaintext training, FLASHE slightly increases the training time by $leq6%$, with no communication overhead.
Creating virtual humans with embodied, human-like perceptual and actuation constraints has the promise to provide an integrated simulation platform for many scientific and engineering applications. We present Dynamic and Autonomous Simulated Human (D
ASH), an embodied virtual human that, given natural language commands, performs grasp-and-stack tasks in a physically-simulated cluttered environment solely using its own visual perception, proprioception, and touch, without requiring human motion data. By factoring the DASH system into a vision module, a language module, and manipulation modules of two skill categories, we can mix and match analytical and machine learning techniques for different modules so that DASH is able to not only perform randomly arranged tasks with a high success rate, but also do so under anthropomorphic constraints and with fluid and diverse motions. The modular design also favors analysis and extensibility to more complex manipulation skills.
Hotellings T-squared test is a classical tool to test if the normal mean of a multivariate normal distribution is a specified one or the means of two multivariate normal means are equal. When the population dimension is higher than the sample size, t
he test is no longer applicable. Under this situation, in this paper we revisit the tests proposed by Srivastava and Du (2008), who revise the Hotellings statistics by replacing Wishart matrices with their diagonal matrices. They show the revised statistics are asymptotically normal. We use the random matrix theory to examine their statistics again and find that their discovery is just part of the big picture. In fact, we prove that their statistics, decided by the Euclidean norm of the population correlation matrix, can go to normal, mixing chi-squared distributions and a convolution of both. Examples are provided to show the phase transition phenomenon between the normal and mixing chi-squared distributions. The second contribution of ours is a rigorous derivation of an asymptotic ratio-unbiased-estimator of the squared Euclidean norm of the correlation matrix.
High-resolution magnetic resonance images can provide fine-grained anatomical information, but acquiring such data requires a long scanning time. In this paper, a framework called the Fused Attentive Generative Adversarial Networks(FA-GAN) is propose
d to generate the super-resolution MR image from low-resolution magnetic resonance images, which can reduce the scanning time effectively but with high resolution MR images. In the framework of the FA-GAN, the local fusion feature block, consisting of different three-pass networks by using different convolution kernels, is proposed to extract image features at different scales. And the global feature fusion module, including the channel attention module, the self-attention module, and the fusion operation, is designed to enhance the important features of the MR image. Moreover, the spectral normalization process is introduced to make the discriminator network stable. 40 sets of 3D magnetic resonance images (each set of images contains 256 slices) are used to train the network, and 10 sets of images are used to test the proposed method. The experimental results show that the PSNR and SSIM values of the super-resolution magnetic resonance image generated by the proposed FA-GAN method are higher than the state-of-the-art reconstruction methods.
Astrophysical black holes are thought to be the Kerr black holes predicted by general relativity, but macroscopic deviations from the Kerr solution can be expected from a number of scenarios involving new physics. In Paper I, we studied the reflectio
n features in NuSTAR and XMM-Newton spectra of the supermassive black hole at the center of the galaxy MCG-06-30-15 and we constrained a set of deformation parameters proposed by Konoplya, Rezzolla & Zhidenko (Phys. Rev. D93, 064015, 2016). In the present work, we analyze the X-ray data of a stellar-mass black hole within the same theoretical framework in order to probe a different curvature regime. We consider a NuSTAR observation of the X-ray binary EXO 1846-031 during its outburst in 2019. As in the case of Paper I, all our fits are consistent with the Kerr black hole hypothesis, but some deformation parameters cannot be constrained well.
Inertial measurement units (IMUs) increasingly function as a basic component of wearable sensor network (WSN)systems. IMU-based joint angle estimation (JAE) is a relatively typical usage of IMUs, with extensive applications. However, the issue that I
MUs move with respect to their original placement during JAE is still a research gap, and limits the robustness of deploying the technique in real-world application scenarios. In this study, we propose to detect and correct the IMU movement online in a relatively computationally lightweight manner. Particularly, we first experimentally investigate the influence of IMU movements. Second, we design the metrics for detecting IMU movements by mathematically formulating how the IMU movement affects the IMU measurements. Third, we determine the optimal thresholds of metrics by synthetic IMU data from a significantly amended simulation model. Finally, a correction method is proposed to correct the effects of IMU movements. We demonstrate our method on both synthetic data and real-user data. The results demonstrate our method is a promising solution to detecting and correcting IMU movements during JAE.
Robustness is a key concern for Rust library development because Rust promises no risks of undefined behaviors if developers use safe APIs only. Fuzzing is a practical approach for examining the robustness of programs. However, existing fuzzing tools
are not directly applicable to library APIs due to the absence of fuzz targets. It mainly relies on human efforts to design fuzz targets case by case which is labor-intensive. To address this problem, this paper proposes a novel automated fuzz target generation approach for fuzzing Rust libraries via API dependency graph traversal. We identify several essential requirements for library fuzzing, including validity and effectiveness of fuzz targets, high API coverage, and efficiency. To meet these requirements, we first employ breadth-first search with pruning to find API sequences under a length threshold, then we backward search longer sequences for uncovered APIs, and finally we optimize the sequence set as a set covering problem. We implement our fuzz target generator and conduct fuzzing experiments with AFL++ on several real-world popular Rust projects. Our tool finally generates 7 to 118 fuzz targets for each library with API coverage up to 0.92. We exercise each target with a threshold of 24 hours and finally find 30 previously-unknown bugs from seven libraries.
We generalize the Bogomolov-Gieseker inequality for semistable coherent sheaves on smooth projective surfaces to smooth Deligne-Mumford surfaces. We work over positive characteristic $p>0$ and generalize Langers method to smooth Deligne-Mumford stack
s. As applications we obtain the Bogomolov inequality for semistable coherent sheaves on a Deligne-Mumford surface in characteristic zero, and the Bogomolov inequality for semistable sheaves on a root stack over a smooth surface which is equivalent to the Bogomolov inequality for the rational parabolic sheaves on a smooth surface $S$. In a joint appendix with Hao Max Sun, we generalize the Bogomolov inequality formula to Simpson Higgs sheaves on tame Deligne-Mumford stacks.
We study correlation functions of D-branes and a supergravity mode in AdS, which are dual to structure constants of two sub-determinant operators with large charge and a BPS single-trace operator. Our approach is inspired by the large charge expansio
n of CFT and resolves puzzles and confusions in the literature on the holographic computation of correlation functions of heavy operators. In particular, we point out two important effects which are often missed in the literature; the first one is an average over classical configurations of the heavy state, which physically amounts to projecting the state to an eigenstate of quantum numbers. The second one is the contribution from wave functions of the heavy state. To demonstrate the power of the method, we first analyze the three-point functions in $mathcal{N}=4$ super Yang-Mills and reproduce the results in field theory from holography, including the cases for which the previous holographic computation gives incorrect answers. We then apply it to ABJM theory and make solid predictions at strong coupling. Finally we comment on possible applications to states dual to black holes and fuzzballs.
