Portrait de Ioannis Mitliagkas

Ioannis Mitliagkas

Membre académique principal
Chaire en IA Canada-CIFAR
Professeur adjoint, Université de Montréal, Département d'informatique et de recherche opérationnelle
Chercheur scientifique, Google DeepMind
Sujets de recherche
Apprentissage de représentations
Apprentissage profond
Modèles génératifs
Optimisation
Systèmes distribués
Systèmes dynamiques
Théorie de l'apprentissage automatique

Biographie

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) est professeur associé au Département d'informatique et de recherche opérationnelle (DIRO) de l'Université de Montréal. Il est également membre académique principal à Mila – Institut québécois d’intelligence artificielle et titulaire d’une chaire en IA Canada-CIFAR. Il occupe présentement un poste de chercheur scientifique à temps partiel chez Google DeepMind à Montréal.

Auparavant, il était chercheur postdoctoral aux Départements de statistique et d'informatique de l'Université de Stanford. Il a obtenu un doctorat au Département d'ingénierie électrique et informatique de l'Université du Texas à Austin.

Ses recherches portent sur des sujets liés à l'apprentissage automatique, en particulier l'optimisation, la théorie de l'apprentissage profond et l'apprentissage statistique. Ses travaux récents portent notamment sur les méthodes d'optimisation efficace et adaptative, l'étude de l'interaction entre l'optimisation et la dynamique des systèmes d'apprentissage à grande échelle et la dynamique des jeux.

Étudiants actuels

Stagiaire de recherche - UdeM
Stagiaire de recherche - UdeM
Co-superviseur⋅e :
Postdoctorat - McGill
Superviseur⋅e principal⋅e :
Doctorat - UdeM
Co-superviseur⋅e :
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Doctorat - UdeM
Maîtrise recherche - UdeM

Publications

Learning to Defer for Causal Discovery with Imperfect Experts
Oscar Clivio
Divyat Mahajan
Perouz Taslakian
Sara Magliacane
Valentina Zantedeschi
Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge is not… (voir plus) guaranteed to be correct. Expert recommendations may contradict data-driven results, and their reliability can vary significantly depending on the domain or specific query. Existing methods based on soft constraints or inconsistencies in predicted causal relationships fail to account for these variations in expertise. To remedy this, we propose L2D-CD, a method for gauging the correctness of expert recommendations and optimally combining them with data-driven causal discovery results. By adapting learning-to-defer (L2D) algorithms for pairwise causal discovery (CD), we learn a deferral function that selects whether to rely on classical causal discovery methods using numerical data or expert recommendations based on textual meta-data. We evaluate L2D-CD on the canonical Tübingen pairs dataset and demonstrate its superior performance compared to both the causal discovery method and the expert used in isolation. Moreover, our approach identifies domains where the expert's performance is strong or weak. Finally, we outline a strategy for generalizing this approach to causal discovery on graphs with more than two variables, paving the way for further research in this area.
Solving Hidden Monotone Variational Inequalities with Surrogate Losses
Ryan D'Orazio
Danilo Vucetic
Zichu Liu
Junhyung Lyle Kim
Deep learning has proven to be effective in a wide variety of loss minimization problems. However, many applications of interest, like minim… (voir plus)izing projected Bellman error and min-max optimization, cannot be modelled as minimizing a scalar loss function but instead correspond to solving a variational inequality (VI) problem. This difference in setting has caused many practical challenges as naive gradient-based approaches from supervised learning tend to diverge and cycle in the VI case. In this work, we propose a principled surrogate-based approach compatible with deep learning to solve VIs. We show that our surrogate-based approach has three main benefits: (1) under assumptions that are realistic in practice (when hidden monotone structure is present, interpolation, and sufficient optimization of the surrogates), it guarantees convergence, (2) it provides a unifying perspective of existing methods, and (3) is amenable to existing deep learning optimizers like ADAM. Experimentally, we demonstrate our surrogate-based approach is effective in min-max optimization and minimizing projected Bellman error. Furthermore, in the deep reinforcement learning case, we propose a novel variant of TD(0) which is more compute and sample efficient.
Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
Daniel Beaglehole
Atish Agarwala
Understanding the mechanisms through which neural networks extract statistics from input-label pairs through feature learning is one of the … (voir plus)most important unsolved problems in supervised learning. Prior works demonstrated that the gram matrices of the weights (the neural feature matrices, NFM) and the average gradient outer products (AGOP) become correlated during training, in a statement known as the neural feature ansatz (NFA). Through the NFA, the authors introduce mapping with the AGOP as a general mechanism for neural feature learning. However, these works do not provide a theoretical explanation for this correlation or its origins. In this work, we further clarify the nature of this correlation, and explain its emergence. We show that this correlation is equivalent to alignment between the left singular structure of the weight matrices and the newly defined pre-activation tangent features at each layer. We further establish that the alignment is driven by the interaction of weight changes induced by SGD with the pre-activation features, and analyze the resulting dynamics analytically at early times in terms of simple statistics of the inputs and labels. We prove the derivative alignment occurs with high probability in specific high dimensional settings. Finally, motivated by the observation that the NFA is driven by this centered correlation, we introduce a simple optimization rule that dramatically increases the NFA correlations at any given layer and improves the quality of features learned.
Solving Hidden Monotone Variational Inequalities with Surrogate Losses
Ryan D'Orazio
Danilo Vucetic
Zichu Liu
Junhyung Lyle Kim
Deep learning has proven to be effective in a wide variety of loss minimization problems. However, many applications of interest, like minim… (voir plus)izing projected Bellman error and min-max optimization, cannot be modelled as minimizing a scalar loss function but instead correspond to solving a variational inequality (VI) problem. This difference in setting has caused many practical challenges as naive gradient-based approaches from supervised learning tend to diverge and cycle in the VI case. In this work, we propose a principled surrogate-based approach compatible with deep learning to solve VIs. We show that our surrogate-based approach has three main benefits: (1) under assumptions that are realistic in practice (when hidden monotone structure is present, interpolation, and sufficient optimization of the surrogates), it guarantees convergence, (2) it provides a unifying perspective of existing methods, and (3) is amenable to existing deep learning optimizers like ADAM. Experimentally, we demonstrate our surrogate-based approach is effective in min-max optimization and minimizing projected Bellman error. Furthermore, in the deep reinforcement learning case, we propose a novel variant of TD(0) which is more compute and sample efficient.
Understanding Adam Requires Better Rotation Dependent Assumptions
Lucas Maes
Tianyue H. Zhang
Alexia Jolicoeur-Martineau
Damien Scieur
Charles Guille-Escuret
Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This… (voir plus) paper investigates Adam's sensitivity to rotations of the parameter space. We demonstrate that Adam's performance in training transformers degrades under random rotations of the parameter space, indicating a crucial sensitivity to the choice of basis. This reveals that conventional rotation-invariant assumptions are insufficient to capture Adam's advantages theoretically. To better understand the rotation-dependent properties that benefit Adam, we also identify structured rotations that preserve or even enhance its empirical performance. We then examine the rotation-dependent assumptions in the literature, evaluating their adequacy in explaining Adam's behavior across various rotation types. This work highlights the need for new, rotation-dependent theoretical frameworks to fully understand Adam's empirical success in modern machine learning tasks.
Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching
Ange-Cl'ement Akazan
Alexia Jolicoeur-Martineau
Compositional Risk Minimization
Divyat Mahajan
Mohammad Pezeshki
Kartik Ahuja
Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training
Hiroki Naganuma
Xinzhi Zhang
Man-Chung Yue
Russell J. Hewett
Philipp Andre Witte
Yin Tat Lee
Recent trends of larger model and larger datasets require huge amounts of computational resources, making distributed deep learning essentia… (voir plus)l. Data parallelism is a common approach to speed up training, but it often involves frequent communication between workers, which can be a bottleneck. In this work, we propose a method called Pseudo-Asynchronous Local SGD (PALSGD) to improve the efficiency of data-parallel training. PALSGD is a novel extension of LocalSGD (SU Stich, 2018), designed to further reduce communication frequency by introducing a pseudo-synchronization mechanism. PALSGD allows the use of longer synchronization intervals compared to standard LocalSGD. Despite the reduced communication frequency, the pseudo-synchronization approach ensures that model consistency is maintained, leading to performance results comparable to those achieved with more frequent synchronization. Furthermore, we provide a theoretical analysis of PALSGD, establishing its convergence and deriving its convergence rate. This analysis offers insights into the algorithm's behavior and performance guarantees. We evaluated PALSGD on CIFAR-10 using a CNN and GPT-NEO on TinyStories. Our results show that PALSGD achieves better performance in less time compared to existing methods like distributed data parallel (DDP), Local SGD and DiLoCo (Douillard et al. 2023).
Understanding Adam Requires Better Rotation Dependent Assumptions
Lucas Maes
Tianyue H. Zhang
Alexia Jolicoeur-Martineau
Damien Scieur
Charles Guille-Escuret
Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This… (voir plus) paper investigates Adam's sensitivity to rotations of the parameter space. We demonstrate that Adam's performance in training transformers degrades under random rotations of the parameter space, indicating a crucial sensitivity to the choice of basis. This reveals that conventional rotation-invariant assumptions are insufficient to capture Adam's advantages theoretically. To better understand the rotation-dependent properties that benefit Adam, we also identify structured rotations that preserve or even enhance its empirical performance. We then examine the rotation-dependent assumptions in the literature, evaluating their adequacy in explaining Adam's behavior across various rotation types. This work highlights the need for new, rotation-dependent theoretical frameworks to fully understand Adam's empirical success in modern machine learning tasks.
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
Charles Guille-Escuret
Pierre-Andre Noel
David Vazquez
Joao Monteiro
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Charles Guille-Escuret
Hiroki Naganuma
Kilian FATRAS
Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-or… (voir plus)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.
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
Mehrnaz Mofakhami
Reza Bayat
Joao Monteiro
Valentina Zantedeschi