21 papers · ranked by Valyu relevance
Song, Heekang, Choi, Wan
In this paper, we propose an optimally structured gradient coding scheme to mitigate the straggler problem in distributed learning. Conventional gradient coding methods often assume homogeneous straggler models or rely on excessive data replication, limiting performance in real-world heterogeneous systems. To address…
Yuxin Jiang, Wenqin Zhang, Lele Wang
Gradient coding is a distributed computing technique aiming to provide robustness against slow or non-responsive computing nodes, known as stragglers, while balancing the computational load for responsive computing nodes. Among existing gradient codes, a construction based on combinatorial designs, called BIBD gradient…
Heekang Song, Wan Choi
We propose a communication-efficient optimally structured gradient coding scheme to jointly address straggler resilience and communication efficiency in heterogeneous distributed learning. By establishing a unified framework that simultaneously optimizes gradient coding and quantization, we formulate an optimization…
Xian Su, Jun Li
In large-scale machine learning, distributed training commonly involves multiple workers evaluating the gradients of the model on different dataset partitions. A common challenge is the presence of straggling workers, which may significantly slow down training. Traditional gradient coding (GC) addresses this by…
Xudong You, Kai Wan, Xiang Zhang, Wenbo Huang + 2 more
This paper considers a new secure gradient coding problem with uncoded groupwise keys, formalized as a (K, N, N_r, M, S) secure gradient coding model, where a user aims to compute the sum of the gradients from K datasets with the assistance of N distributed servers. We consider arbitrary heterogeneous data assignment…
Kuzma Strelnikov
Activity gradients measured with neuroimaging play a fundamental role in brain function, yet their relationship to the brain's internal predictive models during rest remains poorly understood. Clarifying this relationship can reveal how the brain processes information efficiently and adapts to a changing environment.…
MOHAMED HASSAN, ALEKSANDAR VAKANSKI, BOYU ZHANG, MIN XIAN
The generalization performance of deep neural networks (DNNs) is a critical factor in achieving robust model behavior on unseen data. Recent studies have highlighted the importance of sharpness-based measures in promoting generalization by encouraging convergence to flatter minima. Among these approaches…
Authors not listed
Pharmacophores are widely used to describe protein-ligand interactions, and the Grids of Pharmacophore Interaction Fields (GRAIL) method extends this concept by representing binding pockets as interpretable sets of interaction type-specific pharmacophoric maps. In this work, we propose a hybrid framework for binding…
Jiamin Sun, Zhongjie Zhu, Renwei Tu, Zhibo Xie + 1 more
In Versatile Video Coding (VVC), the partition patterns for coding units (CUs) have significant impact on the encoding efficiency. Determining the optimal CU partition is particularly time-consuming due to the calculation and comparison of rate-distortion costs for all possible partition patterns, especially during the…
Davide Noè, Hideaki Yamamoto, Yuichi Katori, Shigeo Sato
The predictive coding framework offers a compelling model for temporal signal processing in the cortex. Recent studies explored its implementation in spiking architectures using Hebbian plasticity rules or offline learning; however, a biologically inspired model that enables gradient-based minimization of prediction…
Kyle Bojanek, Olivier Marre, Stephanie E. Palmer
Populations of sensory neurons are thought to be shaped by selective pressures for optimal information transmission, yet real neural circuits display substantial variability across stimulus repeats, across time, and between individuals. Reconciling this variability with normative theories requires understanding not…
Kungjui Hou, Kunlun Wu, Yongcheng Zhou
Background Spiking Neural Networks (SNNs) have emerged as a promising paradigm in artificial intelligence due to their energy efficiency. However, training SNNs remains a formidable challenge because the nondifferentiable nature of spike activation functions prevents the direct application of conventional…
Authors not listed
Physics-based coarse-grained (CG) models are widely used in (bio)molecular simulations, yet their parameterization remains challenging and labor-intensive. In this work, we demonstrate how recently developed gradient-based optimization methods can substantially accelerate the refinement of CG force field (FF)…
Authors not listed
This work provides a rigorous theoretical investigation of selective error correction strategies for variational quantum algorithms, with focus on understanding the interplay between error suppression, circuit trainability, and computational resource requirements. We develop a mathematical framework that characterizes…
Runguang Zhou, Douglas Zhou, Songting Li, Xiaoyu Chen + 1 more
Under the Marr-Ito-Albus framework, the cerebellum performs supervised learning in Purkinje cells upon the unsupervised sparse representations generated within granule cells, contributing fundamentally to associative learning in motor control. However, the specific mechanisms through which cerebellar circuitry and…
Yuhang Wang, Weihua Chen, Linjing Song, Zhiping Xu + 6 more
With the rapid growth of data volume in sensor networks, lossy source coding systems achieve high-efficiency data compression with low distortion under limited transmission bandwidth. However, conventional compression algorithms rely on a two-stage framework with high computational complexity and frequently struggle to…
Authors not listed
Phase equilibrium calculations are crucial in chemical engineering design and optimization processes. The PC-SAFT equation of state (EoS) can precisely calculate phase equilibrium, but is relatively complex and computationally intensive. Surrogate models are mathematically simple models that map or regress the…
Hyunmin Cho, Jaejun Yoo, Kyong Hwan Jin
We study sinusoidal recurrence as an iterative mechanism for harmonic spectral enrichment in implicit neural representations (INRs). Our analysis reveals that sinusoidal activations induce a harmonic line spectrum, providing a spectral account of how recurrent unrolling enriches the effective spectral support. We…
Yibo Yang, Stephan Mandt
—Popularized by their strong image generation performance, diffusion and related methods for generative modeling have found widespread success in visual media applications. In particular, diffusion methods have enabled new approaches to data compression, where realistic reconstructions can be generated at extremely low…
Authors not listed
The GENERIC framework provides a robust structure for nonequilibrium dynamics but lacks a principled method to select reversible ($L$) and irreversible ($M$) brackets. Similarly, finite-time optimizations minimizing path-averaged reciprocal temperature exist but remain isolated. Here, we introduce the \textbf{Entropy…
Lorenzo Tiberi, Haim Sompolinsky
In everyday vision, animals routinely extract from the same visual stimulus both object identity and continuous identity-independent variables such as position and size. It has been shown that linear decoding performance of both kinds of information increases along the ventral stream, suggesting that inferior temporal…