SelfIE: Self-Interpretation of Large Language Model Embeddings
Haozhe Chen
Carl Vondrick
Chengzhi Mao
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
doi.org
openreview.net
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Adam Ibrahim
Benjamin Thérien
Kshitij Gupta
Mats Leon Richter
Quentin Gregory Anthony
Timothee LESORT
Eugene Belilovsky
Irina Rish
2024-07-08
TMLR (accepted)
doi.org
openreview.net
SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning
Matthias Weissenbacher
Rishabh Agarwal
Yoshinobu Kawahara
An open challenge in reinforcement learning (RL) is the effective deployment of a trained policy to new or slightly different situations as … (see more)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 (published)
proceedings.mlr.press
Stealing part of a production language model
Nicholas Carlini
Daniel Paleka
Krishnamurthy Dj Dvijotham
Thomas Steinke
Jonathan Hayase
A. Feder Cooper
Katherine Lee
Matthew Jagielski
Milad Nasr
Arthur Conmy
Eric Wallace
David Rolnick
Florian Tramèr
We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like … (see more)OpenAI's ChatGPT or Google's PaLM-2. Specifically, our attack recovers the embedding projection layer (up to symmetries) of a transformer model, given typical API access. For under \\
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
doi.org
openreview.net
Stochastic positional embeddings improve masked image modeling
Amir Bar
Florian Bordes
Assaf Shocher
Mahmoud Assran
Pascal Vincent
Nicolas Ballas
Trevor Darrell
Amir Globerson
Yann LeCun
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
proceedings.mlr.press
openreview.net
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
Pablo Samuel Castro
Aleksandra Faust
Aviral Kumar
Rishabh Agarwal
Value functions are an essential component in deep reinforcement learning (RL), that are typically trained via mean squared error regression… (see more) 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 (published)
doi.org
openreview.net
A Tale of Tails: Model Collapse as a Change of Scaling Laws
Elvis Dohmatob
Yunzhen Feng
Pu Yang
Francois Charton
Julia Kempe
As AI model size grows, neural scaling laws have become a crucial tool to predict the improvements of large models when increasing … (see more)capacity and the size of original (human or natural) training data. Yet, the widespread use of popular models means that the ecosystem of online data and text will co-evolve to progressively contain increased amounts of synthesized data. In this paper we ask: How will the scaling laws change in the inevitable regime where synthetic data makes its way into the training corpus? Will future models, still improve, or be doomed to degenerate up to total (model) collapse? We develop a theoretical framework of model collapse through the lens of scaling laws. We discover a wide range of decay phenomena, analyzing loss of scaling, shifted scaling with number of generations, the ”un-learning" of skills, and grokking when mixing human and synthesized data. Our theory is validated by large-scale experiments with a transformer on an arithmetic task and text generation using the large language model Llama2.
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
doi.org
arxiv.org
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
Ziquan Liu
Yufei Cui
Yan Yan
Yi Xu
Xiangyang Ji
Xue (Steve) Liu
Antoni B. Chan
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient healt… (see more)h and road safety, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks and reliable uncertainty quantification in decision-making. With extensive research focused on enhancing adversarial robustness through various forms of adversarial training (AT), a notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. To address this gap, this study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks within the adversarial defense community. It is first unveiled that existing CP methods do not produce informative prediction sets under the commonly used
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
proceedings.mlr.press
Think Before You Act: Decision Transformers with Working Memory
Jikun Kang
Romain Laroche
Xingdi Yuan
Adam Trischler
Xue (Steve) Liu
Jie Fu
Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance rel… (see more)ies on massive data and computation. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training. As a result, training on a new task may deteriorate the model’s performance on previous tasks. In contrast to LLMs’ implicit memory mechanism, the human brain utilizes distributed memory storage, which helps manage and organize multiple skills efficiently, mitigating the forgetting phenomenon. Inspired by this, we propose a working memory module to store, blend, and retrieve information for different downstream tasks. Evaluation results show that the proposed method improves training efficiency and generalization in Atari games and Meta-World object manipulation tasks. Moreover, we demonstrate that memory fine-tuning further enhances the adaptability of the proposed architecture.
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
proceedings.mlr.press
Towards Modular LLMs by Building and Reusing a Library of LoRAs
Oleksiy Ostapenko
Zhan Su
Edoardo Ponti
Laurent Charlin
Nicolas Le Roux
Matheus Pereira
Lucas Caccia
Alessandro Sordoni
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
doi.org
openreview.net
Do Transformer World Models Give Better Policy Gradients?
Michel Ma
Tianwei Ni
Clement Gehring
Pierluca D'Oro
Pierre-Luc Bacon
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
doi.org
openreview.net
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
Antonio Orvieto
Soham De
Caglar Gulcehre
Razvan Pascanu
Samuel L. Smith
Deep neural networks based on linear RNNs interleaved with position-wise MLPs are gaining traction as competitive approaches for sequence mo… (see more)deling. Examples of such architectures include state-space models (SSMs) like S4, LRU, and Mamba: recently proposed models that achieve promising performance on text, genetics, and other data that require long-range reasoning. Despite experimental evidence highlighting these architectures’ effectiveness and computational efficiency, their expressive power remains relatively unexplored, especially in connection to specific choices crucial in practice - e.g., carefully designed initialization distribution and potential use of complex numbers. In this paper, we show that combining MLPs with both real or complex linear diagonal recurrences leads to arbitrarily precise approximation of regular causal sequence-to-sequence maps. At the heart of our proof, we rely on a separation of concerns: the linear RNN provides a lossless encoding of the input sequence, and the MLP performs non-linear processing on this encoding. While we show that real diagonal linear recurrences are enough to achieve universality in this architecture, we prove that employing complex eigenvalues near unit disk - i.e., empirically the most successful strategy in S4 - greatly helps the RNN in storing information. We connect this finding with the vanishing gradient issue and provide experiments supporting our claims.
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
proceedings.mlr.press
arxiv.org