Razvan Pascanu

Meta-learning how to Share Credit among Macro-Actions

Ionel-Alexandru Hosu

Traian Rebedea

Razvan Pascanu

2025-06-16

ArXiv (preprint)

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

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

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

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