Razvan Pascanu

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.

2023-12-31

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

2023-12-31

CoLLAs (publié)

proceedings.mlr.press

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem

Maciej Wolczyk

Bartłomiej Cupiał

Mateusz Ostaszewski

Michal Bortkiewicz

Michał Zając

Lukasz Kuci'nski

Piotr Milo's

Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successfu… (voir plus)l applications of foundation models. However, fine-tuning reinforcement learning (RL) models remains a challenge. This work conceptualizes one specific cause of poor transfer, accentuated in the RL setting by the interplay between actions and observations: forgetting of pre-trained capabilities. Namely, a model deteriorates on the state subspace of the downstream task not visited in the initial phase of fine-tuning, on which the model behaved well due to pre-training. This way, we lose the anticipated transfer benefits. We identify conditions when this problem occurs, showing that it is common and, in many cases, catastrophic. Through a detailed empirical analysis of the challenging NetHack and Montezuma’s Revenge environments, we show that standard knowledge retention techniques mitigate the problem and thus allow us to take full advantage of the pre-trained capabilities. In particular, in NetHack, we achieve a new state-of-the-art for neural models, improving the previous best score from

2023-12-31

ICML (publié)

proceedings.mlr.press

Normalization and effective learning rates in reinforcement learning

Clare Lyle

Zeyu Zheng

Khimya Khetarpal

James Martens

Hado van Hasselt

Will Dabney

2023-12-31

Advances in Neural Information Processing Systems 37 (publié)

openreview.net

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.

2023-12-31

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

2023-04-24

ArXiv (prépublication)

Continually learning representations at scale

Alexandre Galashov

Jovana Mitrovic

Dhruva Tirumala

Yee Whye Teh

Timothy Nguyen

Arslan Chaudhry

2022-12-31

CoLLAs (publié)

proceedings.mlr.press

Test Sample Accuracy Scales with Training Sample Density in Neural Networks

Xu Ji

Devon Hjelm

Andrea Vedaldi

Balaji Lakshminarayanan

Yoshua Bengio

Intuitively, one would expect accuracy of a trained neural network's prediction on test samples to correlate with how densely the samples ar… (voir plus)e surrounded by seen training samples in representation space. We find that a bound on empirical training error smoothed across linear activation regions scales inversely with training sample density in representation space. Empirically, we verify this bound is a strong predictor of the inaccuracy of the network's prediction on test samples. For unseen test sets, including those with out-of-distribution samples, ranking test samples by their local region's error bound and discarding samples with the highest bounds raises prediction accuracy by up to 20% in absolute terms for image classification datasets, on average over thresholds.

2020-12-31

arXiv.org (prépublication)

Nicolas Boulanger-Lewandowski

openreview.net

Theano: A Python framework for fast computation of mathematical expressions

Rami Al-Rfou

Guillaume Alain

Amjad Almahairi

Christof Angermueller

Dzmitry Bahdanau

Nicolas Ballas

Frédéric Bastien

Justin Bayer

Anatoly Belikov

Alexander Belopolsky

Josh Bleecher Snyder

Xavier Bouthillier

Alexandre De Brébisson

Olivier Breuleux … (voir 92 de plus)

Pierre-Luc Carrier

Paul Christiano

Myriam Côté

Yann N. Dauphin

Julien Demouth

Sander Dieleman

Samira Ebrahimi Kahou

Ziye Fan

Mathieu Germain

Matt Graham

Balázs Hidasi

Arjun Jain

Kai Jia

Mikhail Korobov

Vivek Kulkarni

Alex Lamb

Pascal Lamblin

Eric Larsen

César Laurent

Sean Lee

Simon Lefrancois

Simon Lemieux

Nicholas Léonard

Zhouhan Lin

Jesse A. Livezey

Cory Lorenz

Jeremiah Lowin

Qianli Ma

Pierre-Antoine Manzagol

Robert T. McGibbon

Mehdi Mirza

Alberto Orlandi

Christopher Pal

Mohammad Pezeshki

Colin Raffel

Daniel Renshaw

Matthew Rocklin

Adriana Romero

Markus Roth

Peter Sadowski

John Salvatier

François Savard

Jan Schlüter

John Schulman

Gabriel Schwartz

Iulian Vlad Serban

Dmitriy Serdyuk

Samira Shabanian

Etienne Simon

Sigurd Spieckermann

S. Ramana Subramanyam

Gijs van Tulder

Sebastian Urban

Dustin J. Webb

Matthew Willson

Lijun Xue

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.

2015-12-31

arXiv (prépublication)

Theano: Deep Learning on GPUs with Python

Frédéric Bastien

Pascal Lamblin

Ian G Goodfellow

In this paper, we present Theano 1 , a framework in the Python programming language for defining, optimizing and evaluating expressions invo… (voir plus)lving high-level operations on tensors. Theano offers most of NumPy’s functionality, but adds automatic symbolic differentiation, GPU support, and faster expression evaluation. Theano is a general mathematical tool, but it was developed with the goal of facilitating research in deep learning. The Deep Learning Tutorials 2 introduce recent advances in deep learning, and showcase how Theano

2011-12-31

(publié)

www.semanticscholar.org

Theano: A CPU and GPU Math Compiler in Python

James Bergstra

Olivier Breuleux

Frédéric Bastien

Pascal Lamblin

Theano is a compiler for mathematical expressions in Python that combines the convenience of NumPy's syntax with the speed of optimized nati… (voir plus)ve machine language. The user composes mathematical expressions in a high-level description that mimics NumPy's syntax and semantics, while being statically typed and functional (as opposed to imperative). These expressions allow Theano to provide symbolic differentiation. Before performing computation, Theano optimizes the choice of expressions, translates them into C++ (or CUDA for GPU), compiles them into dynamically loaded Python modules, all automatically. Common machine learn- ing algorithms implemented with Theano are from 1:6 to 7:5 faster than competitive alternatives (including those implemented with C/C++, NumPy/SciPy and MATLAB) when compiled for the CPU and between 6:5 and 44 faster when compiled for the GPU. This paper illustrates how to use Theano, outlines the scope of the compiler, provides benchmarks on both CPU and GPU processors, and explains its overall design.

2009-12-31

Proceedings of the Python in Science Conference (publié)