Eugene Belilovsky

2025-03-17

TMLR (accepted)

Continual Pre-training of MoEs: How robust is your router?

Benjamin Thérien

Charles-Étienne Joseph

Zain Sarwar

Ashwinee Panda

Anirban Das

Shi-Xiong Zhang

Stephen Rawls

Sambit Sahu

Irina Rish

2025-03-06

ArXiv (preprint)

Adaptive Local Training in Federated Learning

Donald Shenaj

Pietro Zanuttigh

Federated Learning is a machine learning paradigm where multiple clients collaboratively train a global model by exchanging their locally tr… (see more)ained model weights instead of raw data. In the standard setting, every client trains the local model for the same number of epochs. We introduce ALT (Adaptive Local Training), a simple yet effective feedback mechanism that could be introduced at the client side to limit unnecessary and degrading computations. ALT dynamically adjusts the number of training epochs for each client based on the similarity between their local representations and the global one, ensuring that well-aligned clients can train longer without experiencing client drift. We evaluated ALT on federated partitions of the CIFAR-10 and TinyImageNet datasets, demonstrating its effectiveness in improving model convergence and stability.

2025-03-05

ICLR.cc/2025/Workshop/MCDC (accepted)

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training

Vaibhav Singh

Paul Janson

Paria Mehrbod

Adam Ibrahim

Irina Rish

Benjamin Thérien

The ever-growing availability of unlabeled data presents both opportunities and challenges for training artificial intelligence systems. Whi… (see more)le self-supervised learning (SSL) has emerged as a powerful paradigm for extracting meaningful representations from vast amounts of unlabeled data, existing methods still struggle to adapt to the non-stationary, non-IID nature of real-world data streams without forgetting previously learned knowledge. Recent works have adopted a repeated cosine annealing schedule for large-scale continual pre-training; however, these schedules (1) inherently cause forgetting during the re-warming phase and (2) have not been systematically compared to existing continual SSL methods. In this work, we systematically compare the widely used cosine schedule with the recently proposed infinite learning rate schedule and empirically find the latter to be a more effective alternative. Our extensive empirical evaluation across diverse image and language datasets demonstrates that the infinite learning rate schedule consistently enhances continual pre-training performance compared to a repeated cosine decay without being restricted to a fixed iteration budget. For instance, in a small-scale MAE pre-training setup, it outperforms several strong baselines from the literature. We then scale up our experiments to larger MAE pre-training and autoregressive language model pre-training. Our results show that the infinite learning rate schedule remains effective at scale, surpassing repeated cosine decay for both MAE pre-training and zero-shot LM benchmarks.

2025-03-04

ArXiv (preprint)

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training

Vaibhav Singh

Paul Janson

Paria Mehrbod

Adam Ibrahim

Irina Rish

Benjamin Thérien

The ever-growing availability of unlabeled data presents both opportunities and challenges for training artificial intelligence systems. Whi… (see more)le self-supervised learning (SSL) has emerged as a powerful paradigm for extracting meaningful representations from vast amounts of unlabeled data, existing methods still struggle to adapt to the non-stationary, non-IID nature of real-world data streams without forgetting previously learned knowledge. Recent works have adopted a repeated cosine annealing schedule for large-scale continual pre-training; however, these schedules (1) inherently cause forgetting during the re-warming phase and (2) have not been systematically compared to existing continual SSL methods. In this work, we systematically compare the widely used cosine schedule with the recently proposed infinite learning rate schedule and empirically find the latter to be a more effective alternative. Our extensive empirical evaluation across diverse image and language datasets demonstrates that the infinite learning rate schedule consistently enhances continual pre-training performance compared to a repeated cosine decay without being restricted to a fixed iteration budget. For instance, in a small-scale MAE pre-training setup, it outperforms several strong baselines from the literature. We then scale up our experiments to larger MAE pre-training and autoregressive language model pre-training. Our results show that the infinite learning rate schedule remains effective at scale, surpassing repeated cosine decay for both MAE pre-training and zero-shot LM benchmarks.

2025-03-04

ArXiv (preprint)

Channel-Selective Normalization for Label-Shift Robust Test-Time Adaptation

Pedro Vianna

Muawiz Chaudhary

Paria Mehrbod

An Tang

Guy Cloutier

Guy Wolf

Michael Eickenberg

Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the … (see more)data distribution. For example, in the biomedical field, their performance can be affected by changes in the data (different machines, populations) between training and test datasets. To ensure robustness and generalization to real-world scenarios, test-time adaptation has been recently studied as an approach to adjust models to a new data distribution during inference. Test-time batch normalization is a simple and popular method that achieved compelling performance on domain shift benchmarks. It is implemented by recalculating batch normalization statistics on test batches. Prior work has focused on analysis with test data that has the same label distribution as the training data. However, in many practical applications this technique is vulnerable to label distribution shifts, sometimes producing catastrophic failure. This presents a risk in applying test time adaptation methods in deployment. We propose to tackle this challenge by only selectively adapting channels in a deep network, minimizing drastic adaptation that is sensitive to label shifts. Our selection scheme is based on two principles that we empirically motivate: (1) later layers of networks are more sensitive to label shift (2) individual features can be sensitive to specific classes. We apply the proposed technique to three classification tasks, including CIFAR10-C, Imagenet-C, and diagnosis of fatty liver, where we explore both covariate and label distribution shifts. We find that our method allows to bring the benefits of TTA while significantly reducing the risk of failure common in other methods, while being robust to choice in hyperparameters.

2025-02-17

Proceedings of The 3rd Conference on Lifelong Learning Agents (published)

FairDropout: Using Example-Tied Dropout to Enhance Generalization of Minority Groups

G'eraldin Nanfack

Deep learning models frequently exploit spurious features in training data to achieve low training error, often resulting in poor generaliza… (see more)tion when faced with shifted testing distributions. To address this issue, various methods from imbalanced learning, representation learning, and classifier recalibration have been proposed to enhance the robustness of deep neural networks against spurious correlations. In this paper, we observe that models trained with empirical risk minimization tend to generalize well for examples from the majority groups while memorizing instances from minority groups. Building on recent findings that show memorization can be localized to a limited number of neurons, we apply example-tied dropout as a method we term FairDropout, aimed at redirecting this memorization to specific neurons that we subsequently drop out during inference. We empirically evaluate FairDropout using the subpopulation benchmark suite encompassing vision, language, and healthcare tasks, demonstrating that it significantly reduces reliance on spurious correlations, and outperforms state-of-the-art methods.

2025-02-10

ArXiv (preprint)

FairDropout: Using Example-Tied Dropout to Enhance Generalization of Minority Groups

G'eraldin Nanfack

2025-02-10

ArXiv (preprint)

Accelerating Training with Neuron Interaction and Nowcasting Networks

Boris Knyazev

Abhinav Moudgil

Guillaume Lajoie

Simon Lacoste-Julien

Neural network training can be accelerated when a learnable update rule is used in lieu of classic adaptive optimizers (e.g. Adam). However,… (see more) learnable update rules can be costly and unstable to train and use. A simpler recently proposed approach to accelerate training is to use Adam for most of the optimization steps and periodically, only every few steps, nowcast (predict future) parameters. We improve this approach by Neuron interaction and Nowcasting (NiNo) networks. NiNo leverages neuron connectivity and graph neural networks to more accurately nowcast parameters by learning in a supervised way from a set of training trajectories over multiple tasks. We show that in some networks, such as Transformers, neuron connectivity is non-trivial. By accurately modeling neuron connectivity, we allow NiNo to accelerate Adam training by up to 50\% in vision and language tasks.

2025-01-22

ICLR.cc/2025/Conference (poster)

AdaFisher: Adaptive Second Order Optimization via Fisher Information

Damien MARTINS GOMES

Yanlei Zhang

Guy Wolf

Mahdi S. Hosseini

First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limi… (see more)ted curvature information by employing the diagonal matrix preconditioning of the stochastic gradient during the training. Despite their widespread, second-order optimization algorithms exhibit superior convergence properties compared to their first-order counterparts e.g. Adam and SGD. However, their practicality in training DNNs are still limited due to increased per-iteration computations and suboptimal accuracy compared to the first order methods. We present AdaFisher--an adaptive second-order optimizer that leverages a block-diagonal approximation to the Fisher information matrix for adaptive gradient preconditioning. AdaFisher aims to bridge the gap between enhanced convergence capabilities and computational efficiency in second-order optimization framework for training DNNs. Despite the slow pace of second-order optimizers, we showcase that AdaFisher can be reliably adopted for image classification, language modelling and stand out for its stability and robustness in hyperparameter tuning. We demonstrate that AdaFisher outperforms the SOTA optimizers in terms of both accuracy and convergence speed. Code available from \href{https://github.com/AtlasAnalyticsLab/AdaFisher}{https://github.com/AtlasAnalyticsLab/AdaFisher}

2025-01-22

ICLR.cc/2025/Conference (poster)

Learning Versatile Optimizers on a Compute Diet

Abhinav Moudgil

Boris Knyazev

Guillaume Lajoie

Learned optimization has emerged as a promising alternative to hand-crafted optimizers, with the potential to discover stronger learned upda… (see more)te rules that enable faster, hyperparameter-free training of neural networks. A critical element for practically useful learned optimizers, that can be used off-the-shelf after meta-training, is strong meta-generalization: the ability to apply the optimizers to new tasks. Recent state-of-the-art work in learned optimizers, VeLO (Metz et al., 2022), requires a large number of highly diverse meta-training tasks along with massive computational resources, 4000 TPU months, to achieve meta-generalization. This makes further improvements to such learned optimizers impractical. In this work, we identify several key elements in learned optimizer architectures and meta-training procedures that can lead to strong meta-generalization. We also propose evaluation metrics to reliably assess quantitative performance of an optimizer at scale on a set of evaluation tasks. Our proposed approach, Celo, makes a significant leap in improving the meta-generalization performance of learned optimizers and also outperforms tuned state-of-the-art optimizers on a diverse set of out-of-distribution tasks, despite being meta-trained for just 24 GPU hours.

2025-01-22

ArXiv (preprint)

Learning Versatile Optimizers on a Compute Diet

Abhinav Moudgil

Boris Knyazev

Guillaume Lajoie

Learned optimization has emerged as a promising alternative to hand-crafted optimizers, with the potential to discover stronger learned upda… (see more)te rules that enable faster, hyperparameter-free training of neural networks. A critical element for practically useful learned optimizers, that can be used off-the-shelf after meta-training, is strong meta-generalization: the ability to apply the optimizers to new tasks. Recent state-of-the-art work in learned optimizers, VeLO (Metz et al., 2022), requires a large number of highly diverse meta-training tasks along with massive computational resources, 4000 TPU months, to achieve meta-generalization. This makes further improvements to such learned optimizers impractical. In this work, we identify several key elements in learned optimizer architectures and meta-training procedures that can lead to strong meta-generalization. We also propose evaluation metrics to reliably assess quantitative performance of an optimizer at scale on a set of evaluation tasks. Our proposed approach, Celo, makes a significant leap in improving the meta-generalization performance of learned optimizers and also outperforms tuned state-of-the-art optimizers on a diverse set of out-of-distribution tasks, despite being meta-trained for just 24 GPU hours.

2025-01-22

ArXiv (preprint)