Portrait of Marco Jiralerspong is unavailable

Marco Jiralerspong

marco.jiralerspong@mila.quebec
PhD - Université de Montréal
Supervisor
Gauthier Gidel
Website
Github
Google Scholar

Publications

Expected flow networks in stochastic environments and two-player zero-sum games
Marco Jiralerspong
Bilun Sun
Danilo Vucetic
Tianyu Zhang
Yoshua Bengio
Gauthier Gidel
Nikolay Malkin
2024-01-16
ICLR.cc/2024/Conference (poster)
doi.org
openreview.net
On the Stability of Iterative Retraining of Generative Models on their own Data
Quentin Bertrand
Joey Bose
Alexandre Duplessis
Marco Jiralerspong
Gauthier Gidel
Deep generative models have made tremendous progress in modeling complex data, often exhibiting generation quality that surpasses a typical … (see more)human's ability to discern the authenticity of samples. Undeniably, a key driver of this success is enabled by the massive amounts of web-scale data consumed by these models. Due to these models' striking performance and ease of availability, the web will inevitably be increasingly populated with synthetic content. Such a fact directly implies that future iterations of generative models will be trained on both clean and artificially generated data from past models. In this paper, we develop a framework to rigorously study the impact of training generative models on mixed datasets---from classical training on real data to self-consuming generative models trained on purely synthetic data. We first prove the stability of iterative training under the condition that the initial generative models approximate the data distribution well enough and the proportion of clean training data (w.r.t. synthetic data) is large enough. We empirically validate our theory on both synthetic and natural images by iteratively training normalizing flows and state-of-the-art diffusion models on CIFAR10 and FFHQ.
2024-01-16
ICLR.cc/2024/Conference (spotlight)
doi.org
openreview.net
AI4GCC - Track 3: Consumption and the Challenges of Multi-Agent RL
Marco Jiralerspong
Gauthier Gidel
2023-08-09
ArXiv (preprint)
doi.org
arxiv.org
Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
Marco Jiralerspong
Joey Bose
Ian Gemp
Chongli Qin
Yoram Bachrach
Gauthier Gidel
openreview.net
Feature Likelihood Score: Evaluating Generalization of Generative Models Using Samples
Marco Jiralerspong
Avishek Joey Bose
Gauthier Gidel
Deep generative models have demonstrated the ability to generate complex, high-dimensional, and photo-realistic data. However, a unified fr… (see more)amework for evaluating different generative modeling families remains a challenge. Indeed, likelihood-based metrics do not apply in many cases while pure sample-based metrics such as FID fail to capture known failure modes such as overfitting on training data. In this work, we introduce the Feature Likelihood Score (FLS), a parametric sample-based score that uses density estimation to quantitatively measure the quality/diversity of generated samples while taking into account overfitting. We empirically demonstrate the ability of FLS to identify specific overfitting problem cases, even when previously proposed metrics fail. We further perform an extensive experimental evaluation on various image datasets and model classes. Our results indicate that FLS matches intuitions of previous metrics, such as FID, while providing a more holistic evaluation of generative models that highlights models whose generalization abilities are under or overappreciated. Code for computing FLS is provided at https://github.com/marcojira/fls.
2023-01-01
arXiv.org (preprint)
doi.org