Rishabh Agarwal

Ryan Mullins

Samaneh Saadat

S. M. Carthy

Sarah Perrin

S'ebastien M. R. Arnold

Se-bastian Krause

Shengyang Dai

S. Garg

Shruti Sheth

S. Ronstrom

Susan Chan

Timothy Jordan

Ting Yu

Tom Eccles

Tom Hennigan

Tomas Kocisky

Tulsee Doshi

Vihan Jain

Vikas Yadav

Vilobh Meshram

Vishal Dharmadhikari

Warren Barkley

Wei Wei

Wenming Ye

Woohyun Han

Woosuk Kwon

Xiang Xu

Zhe Shen

Zhitao Gong

Zichuan Wei

Victor Cotruta

Phoebe Kirk

Anand Rao

Minh Giang

Ludovic Peran

Tris Brian Warkentin

Eli Collins

Joelle Barral

Zoubin Ghahramani

Raia Hadsell

D. Sculley

Jeanine Banks

Anca Dragan

Slav Petrov

Oriol Vinyals

Jeffrey Dean

Demis Hassabis

Koray Kavukcuoglu

Clément Farabet

Elena Buchatskaya

Sebastian Borgeaud

Noah Fiedel

Armand Joulin

Kathleen Kenealy

Robert Dadashi

Alek Andreev

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2… (voir plus) billion to 27 billion parameters. In this new version, we apply several known technical modifications to the Transformer architecture, such as interleaving local-global attentions (Beltagy et al., 2020a) and group-query attention (Ainslie et al., 2023). We also train the 2B and 9B models with knowledge distillation (Hinton et al., 2015) instead of next token prediction. The resulting models deliver the best performance for their size, and even offer competitive alternatives to models that are 2-3 times bigger. We release all our models to the community.

2024-07-31

ArXiv (prépublication)

V-STaR: Training Verifiers for Self-Taught Reasoners

Arian Hosseini

Xingdi Yuan

Nikolay Malkin

Aaron Courville

Alessandro Sordoni

Common self-improvement approaches for large language models (LLMs), such as STaR (Zelikman et al., 2022), iteratively fine-tune LLMs on sel… (voir plus)f-generated solutions to improve their problem-solving ability. However, these approaches discard the large amounts of incorrect solutions generated during this process, potentially neglecting valuable information in such solutions. To address this shortcoming, we propose V-STaR that utilizes both the correct and incorrect solutions generated during the self-improvement process to train a verifier using DPO that judges correctness of model-generated solutions. This verifier is used at inference time to select one solution among many candidate solutions. Running V-STaR for multiple iterations results in progressively better reasoners and verifiers, delivering a 4% to 17% test accuracy improvement over existing self-improvement and verification approaches on common code generation and math reasoning benchmarks with LLaMA2 models.

2024-07-10

colmweb.org/COLM/2024/Conference (accepté)

SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning

Matthias Weissenbacher

Yoshinobu Kawahara

An open challenge in reinforcement learning (RL) is the effective deployment of a trained policy to new or slightly different situations as … (voir plus)well as semantically-similar environments. We introduce Symmetry-Invariant Transformer (SiT), a scalable vision transformer (ViT) that leverages both local and global data patterns in a self-supervised manner to improve generalisation. Central to our approach is Graph Symmetric Attention, which refines the traditional self-attention mechanism to preserve graph symmetries, resulting in invariant and equivariant latent representations. We showcase SiT’s superior generalization over ViTs on MiniGrid and Procgen RL benchmarks, and its sample efficiency on Atari 100k and CIFAR10.

2024-07-08

Proceedings of the 41st International Conference on Machine Learning (publié)

proceedings.mlr.press

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Jesse Farebrother

Jordi Orbay

Quan Vuong

Adrien Ali Taiga

Yevgen Chebotar

Ted Xiao

Alex Irpan

Sergey Levine

Aleksandra Faust

Aviral Kumar

Value functions are an essential component in deep reinforcement learning (RL), that are typically trained via mean squared error regression… (voir plus) to match bootstrapped target values. However, scaling value-based RL methods to large networks has proven challenging. This difficulty is in stark contrast to supervised learning: by leveraging a cross-entropy classification loss, supervised methods have scaled reliably to massive networks. Observing this discrepancy, in this paper, we investigate whether the scalability of deep RL can also be improved simply by using classification in place of regression for training value functions. We show that training value functions with categorical cross-entropy significantly enhances performance and scalability across various domains, including single-task RL on Atari 2600 games, multi-task RL on Atari with large-scale ResNets, robotic manipulation with Q-transformers, playing Chess without search, and a language-agent Wordle task with high-capacity Transformers, achieving state-of-the-art results on these domains. Through careful analysis, we show that categorical cross-entropy mitigates issues inherent to value-based RL, such as noisy targets and non-stationarity. We argue that shifting to categorical cross-entropy for training value functions can substantially improve the scalability of deep RL at little-to-no cost.

2024-07-08

Proceedings of the 41st International Conference on Machine Learning (publié)

The Position Dependence of Electron Beam Induced Effects in 2D Materials with Deep Neural Networks

Kevin M Roccapriore

Max Schwarzer

Joshua Greaves

Jesse Farebrother

Riccardo Torsi

Colton Bishop

Igor Mordatch

Ekin Dogus Cubuk

Aaron Courville

Marc Gendron-Bellemare

Joshua Robinson

Sergei V Kalinin

2024-07-01

Microscopy and Microanalysis (publié)

Many-Shot In-Context Learning

Avi Singh

Lei M Zhang

Bernd Bohnet

Luis Rosias

Stephanie C.Y. Chan

Ankesh Anand

Zaheer Abbas

Biao Zhang

Azade Nova

John D. Co-Reyes

Eric Chu

Feryal M. P. Behbahani

Aleksandra Faust

Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, w… (voir plus)ithout any weight updates. Newly expanded context windows allow us to investigate ICL with hundreds or thousands of examples -- the many-shot regime. Going from few-shot to many-shot, we observe significant performance gains across a wide variety of generative and discriminative tasks. While promising, many-shot ICL can be bottlenecked by the available amount of human-generated examples. To mitigate this limitation, we explore two new settings: Reinforced and Unsupervised ICL. Reinforced ICL uses model-generated chain-of-thought rationales in place of human examples. Unsupervised ICL removes rationales from the prompt altogether, and prompts the model only with domain-specific questions. We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks. Finally, we demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases and can learn high-dimensional functions with numerical inputs. Our analysis also reveals the limitations of next-token prediction loss as an indicator of downstream ICL performance.

2024-06-18

ICML.cc/2024/Workshop/ICL (poster)

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Jesse Farebrother

Jordi Orbay

Quan Vuong

Adrien Ali Taiga

Yevgen Chebotar

Ted Xiao

Alex Irpan

Sergey Levine

Aleksandra Faust

Aviral Kumar

2024-05-01

ICML.cc/2024/Conference (présentation orale)

Many-Shot In-Context Learning

Avi Singh

Lei M Zhang

Bernd Bohnet

Stephanie C.Y. Chan

Ankesh Anand

Zaheer Abbas

Azade Nova

John D Co-Reyes

Eric Chu

Feryal Behbahani

Aleksandra Faust

Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, w… (voir plus)ithout any weight updates. Newly expanded context windows allow us to investigate ICL with hundreds or thousands of examples -- the many-shot regime. Going from few-shot to many-shot, we observe significant performance gains across a wide variety of generative and discriminative tasks. While promising, many-shot ICL can be bottlenecked by the available amount of human-generated examples. To mitigate this limitation, we explore two new settings: Reinforced and Unsupervised ICL. Reinforced ICL uses model-generated chain-of-thought rationales in place of human examples. Unsupervised ICL removes rationales from the prompt altogether, and prompts the model only with domain-specific questions. We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks. Finally, we demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases, can learn high-dimensional functions with numerical inputs, and performs comparably to fine-tuning. We also find that inference cost increases linearly in the many-shot regime, and frontier LLMs benefit from many-shot ICL to varying degrees. Our analysis also reveals the limitations of next-token prediction loss as an indicator of downstream ICL performance.

2024-04-17

ArXiv (prépublication)

Many-Shot In-Context Learning

Avi Singh

Lei M Zhang

Bernd Bohnet

Stephanie C.Y. Chan

Ankesh Anand

Zaheer Abbas

Azade Nova

John D Co-Reyes

Eric Chu

Feryal Behbahani

Aleksandra Faust

Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, w… (voir plus)ithout any weight updates. Newly expanded context windows allow us to investigate ICL with hundreds or thousands of examples -- the many-shot regime. Going from few-shot to many-shot, we observe significant performance gains across a wide variety of generative and discriminative tasks. While promising, many-shot ICL can be bottlenecked by the available amount of human-generated examples. To mitigate this limitation, we explore two new settings: Reinforced and Unsupervised ICL. Reinforced ICL uses model-generated chain-of-thought rationales in place of human examples. Unsupervised ICL removes rationales from the prompt altogether, and prompts the model only with domain-specific questions. We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks. Finally, we demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases, can learn high-dimensional functions with numerical inputs, and performs comparably to fine-tuning. We also find that inference cost increases linearly in the many-shot regime, and frontier LLMs benefit from many-shot ICL to varying degrees. Our analysis also reveals the limitations of next-token prediction loss as an indicator of downstream ICL performance.

2024-04-17

ArXiv (prépublication)

Many-Shot In-Context Learning

Avi Singh

Lei M Zhang

Bernd Bohnet

Stephanie C.Y. Chan

Ankesh Anand

Zaheer Abbas

Azade Nova

John D Co-Reyes

Eric Chu

Feryal Behbahani

Aleksandra Faust

Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, w… (voir plus)ithout any weight updates. Newly expanded context windows allow us to investigate ICL with hundreds or thousands of examples -- the many-shot regime. Going from few-shot to many-shot, we observe significant performance gains across a wide variety of generative and discriminative tasks. While promising, many-shot ICL can be bottlenecked by the available amount of human-generated examples. To mitigate this limitation, we explore two new settings: Reinforced and Unsupervised ICL. Reinforced ICL uses model-generated chain-of-thought rationales in place of human examples. Unsupervised ICL removes rationales from the prompt altogether, and prompts the model only with domain-specific questions. We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks. Finally, we demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases, can learn high-dimensional functions with numerical inputs, and performs comparably to fine-tuning. We also find that inference cost increases linearly in the many-shot regime, and frontier LLMs benefit from many-shot ICL to varying degrees. Our analysis also reveals the limitations of next-token prediction loss as an indicator of downstream ICL performance.

2024-04-17

ArXiv (prépublication)

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Jesse Farebrother

Jordi Orbay

Quan Ho Vuong

Adrien Ali Taiga

Yevgen Chebotar

Ted Xiao

A. Irpan

Sergey Levine

Aleksandra Faust

Aviral Kumar

Value functions are a central component of deep reinforcement learning (RL). These functions, parameterized by neural networks, are trained … (voir plus)using a mean squared error regression objective to match bootstrapped target values. However, scaling value-based RL methods that use regression to large networks, such as high-capacity Transformers, has proven challenging. This difficulty is in stark contrast to supervised learning: by leveraging a cross-entropy classification loss, supervised methods have scaled reliably to massive networks. Observing this discrepancy, in this paper, we investigate whether the scalability of deep RL can also be improved simply by using classification in place of regression for training value functions. We demonstrate that value functions trained with categorical cross-entropy significantly improves performance and scalability in a variety of domains. These include: single-task RL on Atari 2600 games with SoftMoEs, multi-task RL on Atari with large-scale ResNets, robotic manipulation with Q-transformers, playing Chess without search, and a language-agent Wordle task with high-capacity Transformers, achieving state-of-the-art results on these domains. Through careful analysis, we show that the benefits of categorical cross-entropy primarily stem from its ability to mitigate issues inherent to value-based RL, such as noisy targets and non-stationarity. Overall, we argue that a simple shift to training value functions with categorical cross-entropy can yield substantial improvements in the scalability of deep RL at little-to-no cost.

2024-03-06

ArXiv (prépublication)

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Jesse Farebrother

Jordi Orbay

Quan Vuong

Adrien Ali Taiga

Yevgen Chebotar

Ted Xiao

Alex Irpan

Sergey Levine

Aleksandra Faust

Aviral Kumar

Value functions are a central component of deep reinforcement learning (RL). These functions, parameterized by neural networks, are trained … (voir plus)using a mean squared error regression objective to match bootstrapped target values. However, scaling value-based RL methods that use regression to large networks, such as high-capacity Transformers, has proven challenging. This difficulty is in stark contrast to supervised learning: by leveraging a cross-entropy classification loss, supervised methods have scaled reliably to massive networks. Observing this discrepancy, in this paper, we investigate whether the scalability of deep RL can also be improved simply by using classification in place of regression for training value functions. We demonstrate that value functions trained with categorical cross-entropy significantly improves performance and scalability in a variety of domains. These include: single-task RL on Atari 2600 games with SoftMoEs, multi-task RL on Atari with large-scale ResNets, robotic manipulation with Q-transformers, playing Chess without search, and a language-agent Wordle task with high-capacity Transformers, achieving state-of-the-art results on these domains. Through careful analysis, we show that the benefits of categorical cross-entropy primarily stem from its ability to mitigate issues inherent to value-based RL, such as noisy targets and non-stationarity. Overall, we argue that a simple shift to training value functions with categorical cross-entropy can yield substantial improvements in the scalability of deep RL at little-to-no cost.

2024-03-06

ArXiv (prépublication)