Aaron Courville

Anirudh Buvanesh

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Laurent Charlin

anirudb1102@gmail.com

Razvan Ciuca

Maîtrise recherche - Université de Montréal

Alexandre Diz Ganito

Maîtrise recherche - UdeM

Juan Duque

Doctorat - UdeM

Doctorat - UdeM

Doctorat - UdeM

Uday Kapur

Maîtrise professionnelle - UdeM

Amr Khalifa

Doctorat - UdeM

andrei.nicolicioiu@gmail.com

Samuel Lavoie

Doctorat - UdeM

Zhixuan Lin

Doctorat - UdeM

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Doctorat - UdeM

Co-superviseur⋅e :

Rishabh Agarwal

Andrei Nicolicioiu

Doctorat - UdeM

Google Scholar

Evgenii Nikishin

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Co-superviseur⋅e :

Johan Samir Obando Ceron

Doctorat - UdeM

Co-superviseur⋅e :

Maîtrise recherche - UdeM

pichedereck@gmail.com

Esra'a Saleh

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Maîtrise recherche - UdeM

Superviseur⋅e principal⋅e :

Anna (Cheng-Zhi) Huang

Shawn Tan

Doctorat - UdeM

Doctorat - UdeM

Superviseur⋅e principal⋅e :

(Rex) Devon Hjelm

Google Scholar

Ankit Vani

Doctorat - UdeM

Google Scholar

Yusong Wu

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Anna (Cheng-Zhi) Huang

Dinghuai Zhang

Doctorat - UdeM

Co-superviseur⋅e :

Doctorat - UdeM

Hattie Zhou

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Hugo Larochelle

Publications

Advantage Alignment Algorithms

Juan Agustin Duque

Milad Aghajohari

Tim Cooijmans

razvan ciuca

Tianyu Zhang

Gauthier Gidel

2025-01-22

ICLR.cc/2025/Conference (présentation orale)

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

Michael Noukhovitch

Shengyi Huang

Sophie Xhonneux

Arian Hosseini

Rishabh Agarwal

The dominant paradigm for RLHF is online and on-policy RL: synchronously generating from the large language model (LLM) policy, labelling wi… (voir plus)th a reward model, and learning using feedback on the LLM's own outputs. While performant, this paradigm is computationally inefficient. Inspired by classical deep RL literature, we propose separating generation and learning in RLHF. This enables asynchronous generation of new samples while simultaneously training on old samples, leading to faster training and more compute-optimal scaling. However, asynchronous training relies on an underexplored regime, online but off-policy RLHF: learning on samples from previous iterations of our model. To understand the challenges in this regime, we investigate a fundamental question: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? Among several RLHF algorithms we tested, we find that online DPO is most robust to off-policy data, and robustness increases with the scale of the policy model. We study further compute optimizations for asynchronous RLHF but find that they come at a performance cost, giving rise to a trade-off. Finally, we verify the scalability of asynchronous RLHF by training LLaMA 3.1 8B on an instruction-following task 40% faster than a synchronous run while matching final performance.

2025-01-22

ICLR.cc/2025/Conference (poster)

doi.org

Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL

Ghada Sokar

Johan Samir Obando Ceron

Hugo Larochelle

Pablo Samuel Castro

The use of deep neural networks in reinforcement learning (RL) often suffers from performance degradation as model size increases. While sof… (voir plus)t mixtures of experts (SoftMoEs) have recently shown promise in mitigating this issue for online RL, the reasons behind their effectiveness remain largely unknown. In this work we provide an in-depth analysis identifying the key factors driving this performance gain. We discover the surprising result that tokenizing the encoder output, rather than the use of multiple experts, is what is behind the efficacy of SoftMoEs. Indeed, we demonstrate that even with an appropriately scaled single expert, we are able to maintain the performance gains, largely thanks to tokenization.

2025-01-22

ICLR.cc/2025/Conference (spotlight)

doi.org

Faster, More Efficient RLHF through Off-Policy Asynchronous Learning

Michael Noukhovitch

Shengyi Huang

Sophie Xhonneux

Arian Hosseini

Rishabh Agarwal

To achieve state-of-the-art chatbots, large language models are finetuned with reinforcement learning (RL), frequently to optimize human fee… (voir plus)dback (RLHF). This process is computationally expensive and can take weeks. Offline approaches, like DPO, learn on a static dataset and are efficient but not performant. The dominant paradigm, online and on-policy---synchronously generating from the model, labelling with a reward model, and learning on feedback from the model's own outputs---is performant but not efficient. Following prior work in the generall deep RL setting, we propose separating the actor and learner in RLHF. This enables the asynchronously generation of new samples while learning on prior samples, thus leading to overall faster training and better scaling. But this requires a novel regime for RLHF, online but off-policy: learning on samples from a previous version of our model. We ask a fundamental question: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? We find that a contrastive loss, Online DPO, is most robust to off-policy data and that robustness increases with the scale of the policy model. We show even further compute optimizations but demonstrate that they come at a performance cost, giving rise to a trade-off. Finally, we verify our design choices by training LLaMA 3.1 8B with RLHF as a helpful chatbot in half the time of a synchronous run while matching final performance.

2025-01-22

ICLR.cc/2025/Conference (poster)

Forgetting Transformer: Softmax Attention with a Forget Gate

Zhixuan Lin

Evgenii Nikishin

Xu He

An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we… (voir plus) show that a forget gate can be naturally incorporated into Transformers by down-weighting the unnormalized attention scores in a data-dependent way. We name this attention mechanism the Forgetting Attention and the resulting model the Forgetting Transformer (FoX). We show that FoX outperforms the Transformer on long-context language modeling, length extrapolation, and short-context downstream tasks, while performing on par with the Transformer on long-context downstream tasks. Moreover, it is compatible with the FlashAttention algorithm and does not require any positional embeddings. Several analyses, including the needle-in-the-haystack test, show that FoX also retains the Transformer's superior long-context capabilities over recurrent sequence models such as Mamba-2, HGRN2, and DeltaNet. We also introduce a ``Pro'' block design that incorporates some common architectural components in recurrent sequence models and find it significantly improves the performance of both FoX and the Transformer. Our code is available at [`https://github.com/zhixuan-lin/forgetting-transformer`](https://github.com/zhixuan-lin/forgetting-transformer).

2025-01-22

ICLR.cc/2025/Conference (poster)

Neuroplastic Expansion in Deep Reinforcement Learning

Jiashun Liu

Johan Samir Obando Ceron

Ling Pan

2025-01-22

ICLR.cc/2025/Conference (poster)

doi.org

Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study

Shawn Tan

Songlin Yang

Rameswar Panda

Yikang Shen

The self-attention mechanism traditionally relies on the softmax operator, necessitating positional embeddings like RoPE, or position biases… (voir plus) to account for token order. But current methods using still face length generalisation challenges. We investigate an alternative attention mechanism based on the stick-breaking process in larger scale settings. The method works as follows: For each token before the current, we determine a break point, which represents the proportion of the stick, the weight of the attention, to allocate to the current token. We repeat this on the remaining stick, until all tokens are allocated a weight, resulting in a sequence of attention weights. This process naturally incorporates recency bias, which has linguistic motivations for grammar parsing (Shen et al., 2017). We study the implications of replacing the conventional softmax-based attention mechanism with stick-breaking attention. We then discuss implementation of numerically stable stick-breaking attention and adapt Flash Attention to accommodate this mechanism. When used as a drop-in replacement for current softmax+RoPE attention systems, we find that stick-breaking attention performs competitively with current methods on length generalisation and downstream tasks. Stick-breaking also performs well at length generalisation, allowing a model trained with

2025-01-22

ICLR.cc/2025/Conference (poster)