Kilian Fatras

No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths

Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-or… (see more)der optimization algorithms are known to efficiently locate favorable minima in deep neural networks. This efficiency, however, contrasts with the non-convex and seemingly complex structure of neural loss landscapes. In this study, we delve into the fundamental geometric properties of sampled gradients along optimization paths. We focus on two key quantities, which appear in the restricted secant inequality and error bound. Both hold high significance for first-order optimization. Our analysis reveals that these quantities exhibit predictable, consistent behavior throughout training, despite the stochasticity induced by sampling minibatches. Our findings suggest that not only do optimization trajectories never encounter significant obstacles, but they also maintain stable dynamics during the majority of training. These observed properties are sufficiently expressive to theoretically guarantee linear convergence and prescribe learning rate schedules mirroring empirical practices. We conduct our experiments on image classification, semantic segmentation and language modeling across different batch sizes, network architectures, datasets, optimizers, and initialization seeds. We discuss the impact of each factor. Our work provides novel insights into the properties of neural network loss functions, and opens the door to theoretical frameworks more relevant to prevalent practice.

2024-07-08

Proceedings of the 41st International Conference on Machine Learning (published)

doi.org

openreview.net

PopulAtion Parameter Averaging (PAPA)

Alexia Jolicoeur-Martineau

Emy Gervais

Kilian Fatras

Yang Zhang

Simon Lacoste-Julien

2024-04-05

TMLR (accepted)

doi.org

openreview.net

Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport

Yanlei Zhang

Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their si… (see more)mulation-based maximum likelihood training. We introduce the generalized \textit{conditional flow matching} (CFM) technique, a family of simulation-free training objectives for CNFs. CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models. In contrast to both diffusion models and prior CNF training algorithms, CFM does not require the source distribution to be Gaussian or require evaluation of its density. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference, as evaluated in our experiments. Furthermore, OT-CFM is the first method to compute dynamic OT in a simulation-free way. Training CNFs with CFM improves results on a variety of conditional and unconditional generation tasks, such as inferring single cell dynamics, unsupervised image translation, and Schrödinger bridge inference.

2024-03-11

TMLR (accepted)

openreview.net

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation.

James Vuckovic

Eric Laufer

Cheng-Hao Liu

Michael M. Bronstein

2024-01-01

Neural Information Processing Systems (published)

dblp.uni-trier.de

Simulation-Free Schrödinger Bridges via Score and Flow Matching

Yanlei Zhang

We present simulation-free score and flow matching ([SF]…

2024-01-01

AISTATS (published)

doi.org

openreview.net

Simulation-Free Schrödinger Bridges via Score and Flow Matching

Yanlei Zhang

We present simulation-free score and flow matching ([SF]…

2023-06-19

ICML.cc/2023/Workshop/Frontiers4LCD (published)

doi.org

openreview.net

A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods

Unsupervised Domain Adaptation (UDA) aims at classifying unlabeled target images leveraging source labeled ones. In the case of an extreme l… (see more)abel shift scenario between the source and target domains, where we have extra source classes not present in the target domain, the UDA problem becomes a harder problem called Partial Domain Adaptation (PDA). While different methods have been developed to solve the PDA problem, most successful algorithms use model selection strategies that rely on target labels to find the best hyper-parameters and/or models along training. These strategies violate the main assumption in PDA: only unlabeled target domain samples are available. In addition, there are also experimental inconsistencies between developed methods - different architectures, hyper-parameter tuning, number of runs - yielding unfair comparisons. The main goal of this work is to provide a realistic evaluation of PDA methods under different model selection strategies and a consistent evaluation protocol. We evaluate 6 state-of-the-art PDA algorithms on 2 different real-world datasets using 7 different model selection strategies. Our two main findings are: (i) without target labels for model selection, the accuracy of the methods decreases up to 30 percentage points; (ii) only one method and model selection pair performs well on both datasets. Experiments were performed with our PyTorch framework, BenchmarkPDA, which we open source.

2023-06-11

TMLR (accepted)

doi.org

openreview.net

PopulAtion Parameter Averaging (PAPA)

Alexia Jolicoeur-Martineau

Emy Gervais

Kilian Fatras

Yan Zhang

Simon Lacoste-Julien

Ensemble methods combine the predictions of multiple models to improve performance, but they require significantly higher computation costs … (see more)at inference time. To avoid these costs, multiple neural networks can be combined into one by averaging their weights. However, this usually performs significantly worse than ensembling. Weight averaging is only beneficial when different enough to benefit from combining them, but similar enough to average well. Based on this idea, we propose PopulAtion Parameter Averaging (PAPA): a method that combines the generality of ensembling with the efficiency of weight averaging. PAPA leverages a population of diverse models (trained on different data orders, augmentations, and regularizations) while slowly pushing the weights of the networks toward the population average of the weights. We also propose PAPA variants (PAPA-all, and PAPA-2) that average weights rarely rather than continuously; all methods increase generalization, but PAPA tends to perform best. PAPA reduces the performance gap between averaging and ensembling, increasing the average accuracy of a population of models by up to 0.8% on CIFAR-10, 1.9% on CIFAR-100, and 1.6% on ImageNet when compared to training independent (non-averaged) models.

2023-04-06

ArXiv (preprint)

doi.org

arxiv.org

PopulAtion Parameter Averaging (PAPA)

Alexia Jolicoeur-Martineau

Emy Gervais

Kilian Fatras

Yan Zhang

Simon Lacoste-Julien

Ensemble methods combine the predictions of multiple models to improve performance, but they require significantly higher computation costs … (see more)at inference time. To avoid these costs, multiple neural networks can be combined into one by averaging their weights. However, this usually performs significantly worse than ensembling. Weight averaging is only beneficial when different enough to benefit from combining them, but similar enough to average well. Based on this idea, we propose PopulAtion Parameter Averaging (PAPA): a method that combines the generality of ensembling with the efficiency of weight averaging. PAPA leverages a population of diverse models (trained on different data orders, augmentations, and regularizations) while slowly pushing the weights of the networks toward the population average of the weights. We also propose PAPA variants (PAPA-all, and PAPA-2) that average weights rarely rather than continuously; all methods increase generalization, but PAPA tends to perform best. PAPA reduces the performance gap between averaging and ensembling, increasing the average accuracy of a population of models by up to 0.8% on CIFAR-10, 1.9% on CIFAR-100, and 1.6% on ImageNet when compared to training independent (non-averaged) models.

2023-04-06

ArXiv (preprint)

doi.org

arxiv.org

Improving and generalizing flow-based generative models with minibatch optimal transport

Yanlei Zhang

Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their si… (see more)mulation-based maximum likelihood training. We introduce the generalized conditional flow matching (CFM) technique, a family of simulation-free training objectives for CNFs. CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models. In contrast to both diffusion models and prior CNF training algorithms, CFM does not require the source distribution to be Gaussian or require evaluation of its density. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference, as evaluated in our experiments. Furthermore, we show that when the true OT plan is available, our OT-CFM method approximates dynamic OT. Training CNFs with CFM improves results on a variety of conditional and unconditional generation tasks, such as inferring single cell dynamics, unsupervised image translation, and Schr\"odinger bridge inference.

2023-02-01

ArXiv (preprint)

arxiv.org

Improving and generalizing flow-based generative models with minibatch optimal transport

Yanlei Zhang

Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their si… (see more)mulation-based maximum likelihood training. We introduce the generalized conditional flow matching (CFM) technique, a family of simulation-free training objectives for CNFs. CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models. In contrast to both diffusion models and prior CNF training algorithms, CFM does not require the source distribution to be Gaussian or require evaluation of its density. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference, as evaluated in our experiments. Furthermore, we show that when the true OT plan is available, our OT-CFM method approximates dynamic OT. Training CNFs with CFM improves results on a variety of conditional and unconditional generation tasks, such as inferring single cell dynamics, unsupervised image translation, and Schr\"odinger bridge inference.

2023-02-01

ArXiv (preprint)

arxiv.org

Improving and generalizing flow-based generative models with minibatch optimal transport

Yanlei Zhang

Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their si… (see more)mulation-based maximum likelihood training. We introduce the generalized conditional flow matching (CFM) technique, a family of simulation-free training objectives for CNFs. CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models. In contrast to both diffusion models and prior CNF training algorithms, CFM does not require the source distribution to be Gaussian or require evaluation of its density. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference, as evaluated in our experiments. Furthermore, we show that when the true OT plan is available, our OT-CFM method approximates dynamic OT. Training CNFs with CFM improves results on a variety of conditional and unconditional generation tasks, such as inferring single cell dynamics, unsupervised image translation, and Schr\"odinger bridge inference.

2023-02-01

ArXiv (preprint)

arxiv.org

Custom AI Learning Programs

Mil'Haq Fest 2025

Mila Community of Practice

Supervision Requests

Kilian Fatras

Publications

Custom AI Learning Programs

Mil'Haq Fest 2025

Mila Community of Practice

Supervision Requests

Popular keywords:

Kilian Fatras

Publications