Razvan Pascanu

Nando de Freitas

Caglar Gulcehre

2024-02-29

ArXiv (prépublication)

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

Soham De

Samuel L. Smith

Anushan Fernando

Aleksandar Botev

George Cristian-Muraru

Albert Gu

Ruba Haroun

Leonard Berrada

Yutian Chen 0001

Srivatsan Srinivasan

Guillaume Desjardins

Arnaud Doucet

David Mark Budden

Yee Whye Teh

Nando de Freitas

Caglar Gulcehre

Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to sc… (voir plus)ale. We propose Hawk, an RNN with gated linear recurrences, and Griffin, a hybrid model that mixes gated linear recurrences with local attention. Hawk exceeds the reported performance of Mamba on downstream tasks, while Griffin matches the performance of Llama-2 despite being trained on over 6 times fewer tokens. We also show that Griffin can extrapolate on sequences significantly longer than those seen during training. Our models match the hardware efficiency of Transformers during training, and during inference they have lower latency and significantly higher throughput. We scale Griffin up to 14B parameters, and explain how to shard our models for efficient distributed training.

2024-02-29

ArXiv (prépublication)

Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers.

Xiuying Wei

Skander Moalla

Caglar Gulcehre

2024-01-01

Neural Information Processing Systems (publié)

dblp.uni-trier.de

Discovering modular solutions that generalize compositionally

Simon Schug

Seijin Kobayashi

Yassir Akram

Maciej Wolczyk

Alexandra Proca

Johannes Von Oswald

João Sacramento

Angelika Steger

Many complex tasks can be decomposed into simpler, independent parts. Discovering such underlying compositional structure has the potential … (voir plus)to enable compositional generalization. Despite progress, our most powerful systems struggle to compose flexibly. It therefore seems natural to make models more modular to help capture the compositional nature of many tasks. However, it is unclear under which circumstances modular systems can discover hidden compositional structure. To shed light on this question, we study a teacher-student setting with a modular teacher where we have full control over the composition of ground truth modules. This allows us to relate the problem of compositional generalization to that of identification of the underlying modules. In particular we study modularity in hypernetworks representing a general class of multiplicative interactions. We show theoretically that identification up to linear transformation purely from demonstrations is possible without having to learn an exponential number of module combinations. We further demonstrate empirically that under the theoretically identified conditions, meta-learning from finite data can discover modular policies that generalize compositionally in a number of complex environments.

2024-01-01

International Conference on Learning Representations (publié)

Disentangling the Causes of Plasticity Loss in Neural Networks

Clare Lyle

Zeyu Zheng

Khimya Khetarpal

Hado van Hasselt

James Martens

Will Dabney

2024-01-01

CoLLAs (publié)

softmax is not enough (for sharp out-of-distribution)

Petar Veličković

Christos Perivolaropoulos

Federico Barbero

A key property of reasoning systems is the ability to make sharp decisions on their input data. For contemporary AI systems, a key carrier o… (voir plus)f sharp behaviour is the softmax function, with its capability to perform differentiable query-key lookups. It is a common belief that the predictive power of networks leveraging softmax arises from "circuits" which sharply perform certain kinds of computations consistently across many diverse inputs. However, for these circuits to be robust, they would need to generalise well to arbitrary valid inputs. In this paper, we dispel this myth: even for tasks as simple as finding the maximum key, any learned circuitry must disperse as the number of items grows at test time. We attribute this to a fundamental limitation of the softmax function to robustly approximate sharp functions, prove this phenomenon theoretically, and propose adaptive temperature as an ad-hoc technique for improving the sharpness of softmax at inference time.

2024-01-01

arXiv.org (prépublication)

Towards Compute-Optimal Transfer Learning

Massimo Caccia

Alexandre Galashov

Arthur Douillard

Amal Rannen-Triki

Dushyant Rao

Michela Paganini

Laurent Charlin

Marc'aurelio Ranzato

2023-04-25

ArXiv (prépublication)

Continually learning representations at scale

Alexandre Galashov

Jovana Mitrovic

Dhruva Tirumala

Yee Whye Teh

Timothy Nguyen

Arslan Chaudhry

2023-01-01

CoLLAs (publié)

proceedings.mlr.press

Predicting Unreliable Predictions by Shattering a Neural Network

Xu Ji

(Rex) Devon Hjelm

Andrea Vedaldi

Balaji Lakshminarayanan

Piecewise linear neural networks can be split into subfunctions, each with its own activation pattern, domain, and empirical error. Empirica… (voir plus)l error for the full network can be written as an expectation over empirical error of subfunctions. Constructing a generalization bound on subfunction empirical error indicates that the more densely a subfunction is surrounded by training samples in representation space, the more reliable its predictions are. Further, it suggests that models with fewer activation regions generalize better, and models that abstract knowledge to a greater degree generalize better, all else equal. We propose not only a theoretical framework to reason about subfunction error bounds but also a pragmatic way of approximately evaluating it, which we apply to predicting which samples the network will not successfully generalize to. We test our method on detection of misclassiﬁcation and out-of-distribution samples, ﬁnding that it performs competitively in both cases. In short, some network activation patterns are associated with higher reliability than others, and these can be identiﬁed using subfunction error bounds.

2021-01-01

arXiv.org (prépublication)

openreview.net

Theano: A Python framework for fast computation of mathematical expressions

Rami Al-rfou'

Guillaume Alain

Amjad Almahairi

Christof Angermüller

Dzmitry Bahdanau

Nicolas Ballas

Frédéric Bastien

Justin S. Bayer

A. Belikov

A. Belopolsky

Arnaud Bergeron

James Bergstra

Valentin Bisson

Josh Bleecher Snyder

Nicolas Bouchard

Nicolas Boulanger-Lewandowski

Xavier Bouthillier

Alexandre De Brébisson

Olivier Breuleux … (voir 92 de plus)

Pierre Luc Carrier

Kyunghyun Cho

Jan Chorowski

Paul F. Christiano

Tim Cooijmans

Marc-Alexandre Côté

Myriam Côté

Aaron Courville

Yann Dauphin

Olivier Delalleau

Julien Demouth

Guillaume Desjardins

Sander Dieleman

Laurent Dinh

M'elanie Ducoffe

Vincent Dumoulin

Samira Ebrahimi Kahou

Dumitru Erhan

Ziye Fan

Orhan Firat

Mathieu Germain

Xavier Glorot

Ian G Goodfellow

Matthew Graham

Caglar Gulcehre

Philippe Hamel

Iban Harlouchet

Jean-philippe Heng

Balázs Hidasi

Sina Honari

Arjun Jain

Sébastien Jean

Kai Jia

Mikhail V. Korobov

Vivek Kulkarni

Alex Lamb

Pascal Lamblin

Eric Larsen

César Laurent

S. Lee

Simon-mark Lefrancois

Simon Lemieux

Nicholas Léonard

Zhouhan Lin

J. Livezey

Cory R. Lorenz

Jeremiah L. Lowin

Qianli M. Ma

Pierre-Antoine Manzagol

Olivier Mastropietro

R. McGibbon

Roland Memisevic

Bart van Merriënboer

Vincent Michalski

Mehdi Mirza

Alberto Orlandi

Chris Pal

Mohammad Pezeshki

Colin Raffel

Daniel Renshaw

Matthew David Rocklin

Adriana Romero Soriano

Markus Dr. Roth

Peter Sadowski

John Salvatier

François Savard

Jan Schlüter

John D. Schulman

Gabriel Schwartz

Iulian V. Serban

Dmitriy Serdyuk

Samira Shabanian

Etienne Simon

Sigurd Spieckermann

S. Subramanyam

Jakub Sygnowski

Jérémie Tanguay

Gijs van Tulder

Joseph Turian

Sebastian Urban

Pascal Vincent

Francesco Visin

Harm de Vries

David Warde-Farley

Dustin J. Webb

M. Willson

Kelvin Xu

Lijun Xue

Li Yao

Saizheng Zhang

Ying Zhang

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficie… (voir plus)ntly. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it.

2016-05-09

ArXiv (prépublication)

Theano: A Python framework for fast computation of mathematical expressions

Rami Al-rfou'

Guillaume Alain

Amjad Almahairi

Christof Angermüller

Dzmitry Bahdanau

Nicolas Ballas

Frédéric Bastien

Justin S. Bayer

A. Belikov

A. Belopolsky

Arnaud Bergeron

J. Bergstra

Valentin Bisson

Josh Bleecher Snyder

Nicolas Bouchard

Nicolas Boulanger-Lewandowski

Xavier Bouthillier

Alexandre De Brébisson

Olivier Breuleux … (voir 92 de plus)

Pierre Luc Carrier

Kyunghyun Cho

Jan Chorowski

Paul F. Christiano

Tim Cooijmans

Marc-Alexandre Côté

Myriam Côté

Aaron Courville

Yann Dauphin

Olivier Delalleau

Julien Demouth

Guillaume Desjardins

Sander Dieleman

Laurent Dinh

M'elanie Ducoffe

Vincent Dumoulin

Samira Ebrahimi Kahou

Dumitru Erhan

Ziye Fan

Orhan Firat

Mathieu Germain

Xavier Glorot

Ian J. Goodfellow

Matthew Graham

Caglar Gulcehre

Philippe Hamel

Iban Harlouchet

Jean-philippe Heng

Balázs Hidasi

Sina Honari

Arjun Jain

S'ebastien Jean

Kai Jia

Mikhail V. Korobov

Vivek Kulkarni

Alex Lamb

Pascal Lamblin

Eric P. Larsen

César Laurent

S. Lee

Simon-mark Lefrancois

Simon Lemieux

Nicholas Léonard

Zhouhan Lin

J. Livezey

Cory R. Lorenz

Jeremiah L. Lowin

Qianli M. Ma

Pierre-Antoine Manzagol

Olivier Mastropietro

R. McGibbon

Roland Memisevic

Bart van Merriënboer

Vincent Michalski

Mehdi Mirza

Alberto Orlandi

Chris Pal

Mohammad Pezeshki

Colin Raffel

Daniel Renshaw

Matthew David Rocklin

Adriana Romero Soriano

Markus Dr. Roth

Peter Sadowski

John Salvatier

François Savard

Jan Schlüter

John D. Schulman

Gabriel Schwartz

Iulian V. Serban

Dmitriy Serdyuk

Samira Shabanian

Etienne Simon

Sigurd Spieckermann

S. Subramanyam

Jakub Sygnowski

Jérémie Tanguay

Gijs van Tulder

Joseph P. Turian

Sebastian Urban

Pascal Vincent

Francesco Visin

Harm de Vries

David Warde-Farley

Dustin J. Webb

M. Willson

Kelvin Xu

Lijun Xue

Li Yao

Saizheng Zhang

Ying Zhang

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficie… (voir plus)ntly. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it.

2016-05-09

ArXiv (preprint)

Theano: Deep Learning on GPUs with Python

James Bergstra

Frédéric Bastien

Olivier Breuleux

Pascal Lamblin

Olivier Delalleau

Guillaume Desjardins

David Warde-Farley

Ian G Goodfellow

Arnaud Bergeron