paper-with-me

Papers

Learning compositional functions via multiplicative weight updates

2020-06-25 · NeurIPS 2020 12 · Jeremy Bernstein, Jia-Wei Zhao, Markus Meister, Ming-Yu Liu, Anima Anandkumar, Yisong Yue

Compositionality is a basic structural feature of both biological and artificial neural networks. Learning compositional functions via gradient descent incurs well known problems like vanishing and exploding gradients, making careful learning rate tuning essential for real-world applications. This paper proves that multiplicative weight updates satisfy a descent lemma tailored to compositional functions. Based on this lemma, we derive Madam -- a multiplicative version of the Adam optimiser -- and show that it can train state of the art neural network architectures without learning rate tuning. We further show that Madam is easily adapted to train natively compressed neural networks by representing their weights in a logarithmic number system. We conclude by drawing connections between multiplicative weight updates and recent findings about synapses in biology.

📄 PDF Abstract BibTeX arXiv:2006.14560

Code (1)

jxbz/madam 공식 구현 pytorch

Tasks

LEMMA

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Multiplicative Learning

2025-03-13 · Han Kim, Hyungjoon Soh, Vipul Periwal, Junghyo Jo

Efficient training of artificial neural networks remains a key challenge in deep learning. Backpropagation (BP), the standard learning algorithm, relies on gradient descent and typically requires numerous iterations for …

image-classificationImage Classification

M+Adam: Low-Precision Training via Additive-Multiplicative Optimization

2026-07-12 · Xiaoyuan Liang, Sebastian Loeschcke, Mads Toftrup, Anima Anandkumar arxiv

Training with quantized weights can reduce costs but often results in degraded accuracy, especially when optimization is carried out in low precision, without storing high-precision copies. We identify a key failure mode…

Implicit Bias in Deep Linear Discriminant Analysis

2026-03-03 · Jiawen Li arxiv

While the Implicit Bias(or Implicit Regularization) of standard loss functions has been studied, the optimization geometry induced by discriminative metric-learning objectives remains largely unexplored.To the best of ou…

Multiplicative Filter Networks

2021-01-01 · ICLR 2021 1 · Rizal Fathony, Anit Kumar Sahu, Devin Willmott, J Zico Kolter

Although deep networks are typically used to approximate functions over high dimensional inputs, recent work has increased interest in neural networks as function approximators for low-dimensional-but-complex functions, …

Modeling Compositionality with Multiplicative Recurrent Neural Networks

2014-12-20 · Ozan İrsoy, Claire Cardie

We present the multiplicative recurrent neural network as a general model for compositional meaning in language, and evaluate it on the task of fine-grained sentiment analysis. We establish a connection to the previously…

Sentiment Analysis