paper-with-me

Papers

Testing RadiX-Nets: Advances in Viable Sparse Topologies

2023-11-06 · Kevin Kwak, Zack West, Hayden Jananthan, Jeremy Kepner

The exponential growth of data has sparked computational demands on ML research and industry use. Sparsification of hyper-parametrized deep neural networks (DNNs) creates simpler representations of complex data. Past research has shown that some sparse networks achieve similar performance as dense ones, reducing runtime and storage. RadiX-Nets, a subgroup of sparse DNNs, maintain uniformity which counteracts their lack of neural connections. Generation, independent of a dense network, yields faster asymptotic training and removes the need for costly pruning. However, little work has been done on RadiX-Nets, making testing challenging. This paper presents a testing suite for RadiX-Nets in TensorFlow. We test RadiX-Net performance to streamline processing in scalable models, revealing relationships between network topology, initialization, and training behavior. We also encounter "strange models" that train inconsistently and to lower accuracy while models of similar sparsity train well.

📄 PDF Abstract BibTeX arXiv:2311.03609

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RadiX-Net: Structured Sparse Matrices for Deep Neural Networks

2019-04-30 · Ryan A. Robinett, Jeremy Kepner

The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after…

Training Behavior of Sparse Neural Network Topologies

2018-09-30 · Simon Alford, Ryan Robinett, Lauren Milechin, Jeremy Kepner

Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network …

Remaining Useful Life Estimation Under Uncertainty with Causal GraphNets

2020-11-23 · Charilaos Mylonas, Eleni Chatzi

In this work, a novel approach for the construction and training of time series models is presented that deals with the problem of learning on large time series with non-equispaced observations, which at the same time ma…

Time SeriesTime Series Analysis

Radix-2 Self-Recursive Sparse Factorizations of Delay Vandermonde Matrices for Wideband Multi-Beam Antenna Arrays

2022-06-01 · S. M. Perera, A. Madanayake, R. J. Cintra

This paper presents a self-contained factorization for the Vandermonde matrices associated with true-time delay based wideband analog multi-beam beamforming using antenna arrays. The proposed factorization contains spars…

RadixMLP -- Intra-batch Deduplication for Causal Transformers

2026-01-21 · Michael Feil, Julius Lipp arxiv

Batch inference workloads for causal transformer models frequently process sequences that share common prefixes, such as system prompts, few-shot examples, or shared queries. Standard inference engines treat each sequenc…