Portrait of Razvan Pascanu is unavailable

Razvan Pascanu

Alumni

Publications

What Can Grokking Teach Us About Learning Under Nonstationarity?
Clare Lyle
Gharda Sokar
Razvan Pascanu
Andr'as Gyorgy
In continual learning problems, it is often necessary to overwrite components of a neural network's learned representation in response to ch… (see more)anges in the data stream; however, neural networks often exhibit \primacy bias, whereby early training data hinders the network's ability to generalize on later tasks. While feature-learning dynamics of nonstationary learning problems are not well studied, the emergence of feature-learning dynamics is known to drive the phenomenon of grokking, wherein neural networks initially memorize their training data and only later exhibit perfect generalization. This work conjectures that the same feature-learning dynamics which facilitate generalization in grokking also underlie the ability to overwrite previous learned features as well, and methods which accelerate grokking by facilitating feature-learning dynamics are promising candidates for addressing primacy bias in non-stationary learning problems. We then propose a straightforward method to induce feature-learning dynamics as needed throughout training by increasing the effective learning rate, i.e. the ratio between parameter and update norms. We show that this approach both facilitates feature-learning and improves generalization in a variety of settings, including grokking, warm-starting neural network training, and reinforcement learning tasks.
2025-07-01
arXiv (published)
doi.org
arxiv.org
Meta-learning how to Share Credit among Macro-Actions
Ionel-Alexandru Hosu
Traian Rebedea
Razvan Pascanu
2025-06-16
ArXiv (preprint)
doi.org
arxiv.org
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
Johannes Von Oswald
Nino Scherrer
Seijin Kobayashi
Luca Versari
Songlin Yang
Maximilian Schlegel
Kaitlin Maile
Yanick Schimpf
Oliver Sieberling
Alexander Meulemans
Rif A. Saurous
Guillaume Lajoie
Charlotte Frenkel
Razvan Pascanu
Blaise Aguera y Arcas
João Sacramento
Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, trans… (see more)formers require scaling memory and compute linearly during inference. A recent stream of work linearized the softmax operation, resulting in powerful recurrent neural network (RNN) models with constant memory and compute costs such as DeltaNet, Mamba or xLSTM. These models can be unified by noting that their recurrent layer dynamics can all be derived from an in-context regression objective, approximately optimized through an online learning rule. Here, we join this line of work and introduce a numerically stable, chunkwise parallelizable version of the recently proposed Mesa layer (von Oswald et al., 2024), and study it in language modeling at the billion-parameter scale. This layer again stems from an in-context loss, but which is now minimized to optimality at every time point using a fast conjugate gradient solver. Through an extensive suite of experiments, we show that optimal test-time training enables reaching lower language modeling perplexity and higher downstream benchmark performance than previous RNNs, especially on tasks requiring long context understanding. This performance gain comes at the cost of additional flops spent during inference time. Our results are therefore intriguingly related to recent trends of increasing test-time compute to improve performance -- here by spending compute to solve sequential optimization problems within the neural network itself.
2025-06-05
ArXiv (preprint)
arxiv.org
arxiv.org
Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization
Wojciech Masarczyk
Mateusz Ostaszewski
Tin Sum Cheng
Tomasz Trzci'nski
Aurélien Lucchi
Razvan Pascanu
The softmax function is a fundamental building block of deep neural networks, commonly used to define output distributions in classification… (see more) tasks or attention weights in transformer architectures. Despite its widespread use and proven effectiveness, its influence on learning dynamics and learned representations remains poorly understood, limiting our ability to optimize model behavior. In this paper, we study the pivotal role of the softmax function in shaping the model's representation. We introduce the concept of rank deficit bias - a phenomenon in which softmax-based deep networks find solutions of rank much lower than the number of classes. This bias depends on the softmax function's logits norm, which is implicitly influenced by hyperparameters or directly modified by softmax temperature. Furthermore, we demonstrate how to exploit the softmax dynamics to learn compressed representations or to enhance their performance on out-of-distribution data. We validate our findings across diverse architectures and real-world datasets, highlighting the broad applicability of temperature tuning in improving model performance. Our work provides new insights into the mechanisms of softmax, enabling better control over representation learning in deep neural networks.
2025-06-02
ArXiv (preprint)
arxiv.org
arxiv.org
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
Johannes Von Oswald
Nino Scherrer
Seijin Kobayashi
Luca Versari
Songlin Yang
Maximilian Schlegel
Kaitlin Maile
Yanick Schimpf
Oliver Sieberling
Alexander Meulemans
Rif A. Saurous
Guillaume Lajoie
Charlotte Frenkel
Razvan Pascanu
Blaise Aguera y Arcas
João Sacramento
Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, trans… (see more)formers require scaling memory and compute linearly during inference. A recent stream of work linearized the softmax operation, resulting in powerful recurrent neural network (RNN) models with constant memory and compute costs such as DeltaNet, Mamba or xLSTM. These models can be unified by noting that their recurrent layer dynamics can all be derived from an in-context regression objective, approximately optimized through an online learning rule. Here, we join this line of work and introduce a numerically stable, chunkwise parallelizable version of the recently proposed Mesa layer (von Oswald et al., 2024), and study it in language modeling at the billion-parameter scale. This layer again stems from an in-context loss, but which is now minimized to optimality at every time point using a fast conjugate gradient solver. Through an extensive suite of experiments, we show that optimal test-time training enables reaching lower language modeling perplexity and higher downstream benchmark performance than previous RNNs, especially on tasks requiring long context understanding. This performance gain comes at the cost of additional flops spent during inference time. Our results are therefore intriguingly related to recent trends of increasing test-time compute to improve performance -- here by spending compute to solve sequential optimization problems within the neural network itself.
2025-06-01
arXiv (published)
doi.org
arxiv.org
Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization
Wojciech Masarczyk
Mateusz Ostaszewski
Tin Sum Cheng
Tomasz Trzci'nski
Aurélien Lucchi
Razvan Pascanu
The softmax function is a fundamental building block of deep neural networks, commonly used to define output distributions in classification… (see more) tasks or attention weights in transformer architectures. Despite its widespread use and proven effectiveness, its influence on learning dynamics and learned representations remains poorly understood, limiting our ability to optimize model behavior. In this paper, we study the pivotal role of the softmax function in shaping the model's representation. We introduce the concept of rank deficit bias - a phenomenon in which softmax-based deep networks find solutions of rank much lower than the number of classes. This bias depends on the softmax function's logits norm, which is implicitly influenced by hyperparameters or directly modified by softmax temperature. Furthermore, we demonstrate how to exploit the softmax dynamics to learn compressed representations or to enhance their performance on out-of-distribution data. We validate our findings across diverse architectures and real-world datasets, highlighting the broad applicability of temperature tuning in improving model performance. Our work provides new insights into the mechanisms of softmax, enabling better control over representation learning in deep neural networks.
2025-06-01
arXiv (published)
doi.org
arxiv.org
Plasticity as the Mirror of Empowerment
David Abel
Michael Bowling
Andre Barreto
Will Dabney
Shi Dong
Steven Hansen
Anna Harutyunyan
Khimya Khetarpal
Clare Lyle
Razvan Pascanu
Georgios Piliouras
Doina Precup
Jonathan Richens
Mark Rowland
Tom Schaul
Satinder Singh
2025-05-15
ArXiv (preprint)
arxiv.org
arxiv.org
Plasticity as the Mirror of Empowerment
David Abel
Michael Bowling
Andre Barreto
Will Dabney
Shi Dong
Steven Hansen
Anna Harutyunyan
Khimya Khetarpal
Clare Lyle
Razvan Pascanu
Georgios Piliouras
Doina Precup
Jonathan Richens
Mark Rowland
Tom Schaul
Satinder Singh
2025-05-01
arXiv (published)
doi.org
arxiv.org
On the generalization of language models from in-context learning and finetuning: a controlled study
Andrew Lampinen
Arslan Chaudhry
Stephanie C.Y. Chan
Cody Wild
Diane Wan
Alexander Y. Ku
Alex Ku
Jörg Bornschein
Razvan Pascanu
Murray P. Shanahan
James L McClelland
2025-05-01
arXiv (published)
doi.org
arxiv.org
On the generalization of language models from in-context learning and finetuning: a controlled study
Andrew Lampinen
Arslan Chaudhry
Stephanie C.Y. Chan
Cody Wild
Diane Wan
Alexander Y. Ku
Jörg Bornschein
Razvan Pascanu
Murray P. Shanahan
James L McClelland
Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to … (see more)generalize to simple reversals of relations they are trained on, or fail to make simple logical deductions based on trained information. These failures to generalize from fine-tuning can hinder practical application of these models. On the other hand, language models' in-context learning shows different inductive biases, and can generalize better in some cases. Here, we explore these differences in generalization between in-context- and fine-tuning-based learning. To do so, we constructed several novel datasets to evaluate and improve models' abilities to generalize from finetuning data. The datasets are designed to create clean tests of generalization, by isolating the knowledge in the dataset from that in pretraining. We expose pretrained large models to controlled subsets of the information in these datasets -- either in context, or through fine-tuning -- and evaluate their performance on test sets that require various types of generalization. We find overall that in data-matched settings, in-context learning can generalize more flexibly than fine-tuning (though we also find some qualifications of prior findings, such as cases when fine-tuning can generalize to reversals embedded in a larger structure of knowledge). We build on these findings to propose a method to enable improved generalization from fine-tuning: adding in-context inferences to finetuning data. We show that this method improves generalization across various splits of our datasets and other benchmarks. Our results have implications for understanding the inductive biases of different modes of learning in language models, and practically improving their performance.
2025-05-01
ArXiv (preprint)
doi.org
arxiv.org
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
Thomas Schmied
Jörg Bornschein
Jordi Grau-Moya
Markus Wulfmeier
Razvan Pascanu
2025-04-22
ArXiv (preprint)
arxiv.org
arxiv.org
Why do LLMs attend to the first token?
Federico Barbero
'Alvaro Arroyo
Xiangming Gu
Christos Perivolaropoulos
Michael M. Bronstein
Petar Velivckovi 'c
Razvan Pascanu
2025-04-03
ArXiv (preprint)
arxiv.org
arxiv.org