activity
20182023
most citedFP8 Quantization: The Power of the Exponent

13 citations · 14 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2023★ 1 cited

QBitOpt: Fast and Accurate Bitwidth Reallocation during Training

Jorn Peters, Marios Fournarakis, Markus Nagel +2

Quantizing neural networks is one of the most effective methods for achieving efficient inference on mobile and embedded devices. In particular, mixed precision quantized (MPQ) net…

cs.LG2022★ 13 cited

FP8 Quantization: The Power of the Exponent

Andrey Kuzmin, Mart Van Baalen, Yuwei Ren +3

When quantizing neural networks for efficient inference, low-bit integers are the go-to format for efficiency. However, low-bit floating point numbers have an extra degree of freed…

cs.LG2020

Self Normalizing Flows

T. Anderson Keller, Jorn W. T. Peters, Priyank Jaini +3

Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework. Most propo…

cs.LG2019

Integer Discrete Flows and Lossless Compression

Emiel Hoogeboom, Jorn W. T. Peters, Rianne van den Berg +1

Lossless compression methods shorten the expected representation size of data without loss of information, using a statistical model. Flow-based models are attractive in this setti…

cs.LG2018

Probabilistic Binary Neural Networks

Jorn W. T. Peters, Max Welling

Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a pr…

cs.LG2018

HexaConv

Emiel Hoogeboom, Jorn W. T. Peters, Taco S. Cohen +1

The effectiveness of Convolutional Neural Networks stems in large part from their ability to exploit the translation invariance that is inherent in many learning problems. Recently…