20 results for “knowledge of deep learning and parallel computing”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Megan Frisella, Shubham Tiwari, Andy Ruan, Yi Pan +4 more
Piper is a user-controllable distributed training system that decouples the strategy from the runtime implementation, allowing users to declare a comprehensive distributed training strategy with a sma…
Rania Zitouni, Nadine Bousdjira, Sarah Hasnaoui, Amel Sadoun +1 more
This paper compares and optimizes CUDA strategies for a shallow neural network, achieving a 1.41x speedup on a large dataset.
This paper compares two theoretical frameworks for hierarchical neural networks with a finite but large number of hidden units and shows that training input-to-hidden weights reduces generalization er…
This paper proposes Hierarchical Block-Local Learning (HBLL), a framework for training deep neural networks without full end-to-end backpropagation, achieving $\mathcal{O}(\log N)$ parallel time compl…
This paper investigates deep learning from a physics-informed perspective, examining its key features and surprises.
This paper establishes all-depths depth separation for ReLU networks on {0,1}^n.
Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao, Semih Yavuz +2 more
This paper presents a memory-efficient training stack for Mixture-of-Experts (MoE) models, combining and specializing parallelism techniques for maximal efficiency.
This paper explores the relationship between neural network architecture and computational ability, identifying local cycles as a key design principle.
This paper characterizes the gap between neural network performance and their neural tangent kernel limit on compositional tasks, attributing it to a mismatch between kernel smoothness bias and target…
One clear sentence describing what this paper does
This paper proposes an HPC-aware methodology for Knowledge Distillation (KD) that decouples teacher and student partitioning efficiently, achieving up to 67% higher samples-per-second than the widely…
This paper analyzes the computational complexity of verifying feedforward neural networks when their weights are restricted to finite-width arithmetic, finding that verification remains NP-complete fo…
Daifeng Li, Huiqiang Jiang, Chengruidong Zhang, Wei Wu +5 more
The paper introduces D2K-Bench, a diagnostic benchmark to measure how effectively large language model agents translate expert design guidance into efficient GPU kernels.
The paper presents a field study on deploying large inference workloads on a non-GPU AI accelerator and identifies eight categories of limitations.
This paper develops optimized algorithms and a pipeline architecture for high-throughput, memory-efficient batch processing of encrypted neural network inference, significantly improving performance o…
A new error backpropagation method called supervised counterstream learning is proposed for deep associative networks, which only requires recognition of errors during training and backpropagates corr…