17 citations · 50 across the 12 of their papers we have counts for
12 papers
Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
Zhanpeng Zeng, Cole Hawkins, Mingyi Hong +4
Transformers are central in modern natural language processing and computer vision applications. Despite recent works devoted to reducing the quadratic cost of such models (as a fu…
Online, Informative MCMC Thinning with Kernelized Stein Discrepancy
Cole Hawkins, Alec Koppel, Zheng Zhang
A fundamental challenge in Bayesian inference is efficient representation of a target distribution. Many non-parametric approaches do so by sampling a large number of points using…
Low-Rank+Sparse Tensor Compression for Neural Networks
Cole Hawkins, Haichuan Yang, Meng Li +2
Low-rank tensor compression has been proposed as a promising approach to reduce the memory and compute requirements of neural networks for their deployment on edge devices. Tensor…
Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation
Cole Hawkins, Vassilis N. Ioannidis, Soji Adeshina +1
Consistency training is a popular method to improve deep learning models in computer vision and natural language processing. Graph neural networks (GNNs) have achieved remarkable p…
3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration
Yao Chen, Cole Hawkins, Kaiqi Zhang +2
The deep neural network (DNN) based AI applications on the edge require both low-cost computing platforms and high-quality services. However, the limited memory, computing resource…
On-FPGA Training with Ultra Memory Reduction: A Low-Precision Tensor Method
Kaiqi Zhang, Cole Hawkins, Xiyuan Zhang +2
Various hardware accelerators have been developed for energy-efficient and real-time inference of neural networks on edge devices. However, most training is done on high-performanc…
Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination
Cole Hawkins, Xing Liu, Zheng Zhang
While post-training model compression can greatly reduce the inference cost of a deep neural network, uncompressed training still consumes a huge amount of hardware resources, run-…
Tensor Methods for Generating Compact Uncertainty Quantification and Deep Learning Models
Chunfeng Cui, Cole Hawkins, Zheng Zhang
Tensor methods have become a promising tool to solve high-dimensional problems in the big data era. By exploiting possible low-rank tensor factorization, many high-dimensional mode…
Bayesian Tensorized Neural Networks with Automatic Rank Selection
Cole Hawkins, Zheng Zhang
Tensor decomposition is an effective approach to compress over-parameterized neural networks and to enable their deployment on resource-constrained hardware platforms. However, dir…
Robust Factorization and Completion of Streaming Tensor Data via Variational Bayesian Inference
Cole Hawkins, Zheng Zhang
Streaming tensor factorization is a powerful tool for processing high-volume and multi-way temporal data in Internet networks, recommender systems and image/video data analysis. In…
Variational Bayesian Inference for Robust Streaming Tensor Factorization and Completion
Cole Hawkins, Zheng Zhang
Streaming tensor factorization is a powerful tool for processing high-volume and multi-way temporal data in Internet networks, recommender systems and image/video data analysis. Ex…
Rational combinations of Betti diagrams of complete intersections
Michael T. Annunziata, Courtney R. Gibbons, Cole Hawkins +1
We investigate decompositions of Betti diagrams over a polynomial ring within the framework of Boij-Söderberg theory. That is, given a Betti diagram, we determine if it is possible…