Portrait of Ioannis Mitliagkas

Ioannis Mitliagkas

Core Academic Member
Canada CIFAR AI Chair
Associate Professor, Université de Montréal
Research Scientist, Google DeepMind
Research Topics
Deep Learning
Distributed Systems
Dynamical Systems
Generative Models
Machine Learning Theory
Optimization
Representation Learning

Biography

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) is an associate professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal, as well as a Core Academic member of Mila – Quebec Artificial Intelligence Institute and a Canada CIFAR AI Chair. He holds a part-time position as a staff research scientist at Google DeepMind Montréal.

Previously, he was a postdoctoral scholar in the Departments of statistics and computer science at Stanford University. He obtained his PhD from the Department of Electrical and Computer Engineering at the University of Texas at Austin.

His research includes topics in machine learning, with emphasis on optimization, deep learning theory, statistical learning. His recent work includes methods for efficient and adaptive optimization, studying the interaction between optimization and the dynamics of large-scale learning systems and the dynamics of games.

Current Students

PhD - Université de Montréal
Principal supervisor :
Professional Master's - Université de Montréal
PhD - Université de Montréal
Collaborating researcher - Université de Montréal
Principal supervisor :

Publications

h-detach: Modifying the LSTM Gradient Towards Better Optimization
Recurrent neural networks are known for their notorious exploding and vanishing gradient problem (EVGP). This problem becomes more evident i… (see more)n tasks where the information needed to correctly solve them exist over long time scales, because EVGP prevents important gradient components from being back-propagated adequately over a large number of steps. We introduce a simple stochastic algorithm (\textit{h}-detach) that is specific to LSTM optimization and targeted towards addressing this problem. Specifically, we show that when the LSTM weights are large, the gradient components through the linear path (cell state) in the LSTM computational graph get suppressed. Based on the hypothesis that these components carry information about long term dependencies (which we show empirically), their suppression can prevent LSTMs from capturing them. Our algorithm\footnote{Our code is available at this https URL.} prevents gradients flowing through this path from getting suppressed, thus allowing the LSTM to capture such dependencies better. We show significant improvements over vanilla LSTM gradient based training in terms of convergence speed, robustness to seed and learning rate, and generalization using our modification of LSTM gradient on various benchmark datasets.
Reducing the variance in online optimization by transporting past gradients
Most stochastic optimization methods use gradients once before discarding them. While variance reduction methods have shown that reusing pas… (see more)t gradients can be beneficial when there is a finite number of datapoints, they do not easily extend to the online setting. One issue is the staleness due to using past gradients. We propose to correct this staleness using the idea of implicit gradient transport (IGT) which transforms gradients computed at previous iterates into gradients evaluated at the current iterate without using the Hessian explicitly. In addition to reducing the variance and bias of our updates over time, IGT can be used as a drop-in replacement for the gradient estimate in a number of well-understood methods such as heavy ball or Adam. We show experimentally that it achieves state-of-the-art results on a wide range of architectures and benchmarks. Additionally, the IGT gradient estimator yields the optimal asymptotic convergence rate for online stochastic optimization in the restricted setting where the Hessians of all component functions are equal.
Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations
Deep networks have achieved impressive results across a variety of important tasks. However a known weakness is a failure to perform well wh… (see more)en evaluated on data which differ from the training distribution, even if these differences are very small, as is the case with adversarial examples. We propose Fortified Networks, a simple transformation of existing networks, which fortifies the hidden layers in a deep network by identifying when the hidden states are off of the data manifold, and maps these hidden states back to parts of the data manifold where the network performs well. Our principal contribution is to show that fortifying these hidden states improves the robustness of deep networks and our experiments (i) demonstrate improved robustness to standard adversarial attacks in both black-box and white-box threat models; (ii) suggest that our improvements are not primarily due to the gradient masking problem and (iii) show the advantage of doing this fortification in the hidden layers instead of the input space.
Accelerated Stochastic Power Iteration
Peng Xu
Bryan Dawei He
Christopher De Sa
Christopher Re
Principal component analysis (PCA) is one of the most powerful tools in machine learning. The simplest method for PCA, the power iteration, … (see more)requires O ( 1 / Δ ) full-data passes to recover the principal component of a matrix with eigen-gap Δ. Lanczos, a significantly more complex method, achieves an accelerated rate of O ( 1 / Δ ) passes. Modern applications, however, motivate methods that only ingest a subset of available data, known as the stochastic setting. In the online stochastic setting, simple algorithms like Oja's iteration achieve the optimal sample complexity O ( σ 2 / Δ 2 ) . Unfortunately, they are fully sequential, and also require O ( σ 2 / Δ 2 ) iterations, far from the O ( 1 / Δ ) rate of Lanczos. We propose a simple variant of the power iteration with an added momentum term, that achieves both the optimal sample and iteration complexity. In the full-pass setting, standard analysis shows that momentum achieves the accelerated rate, O ( 1 / Δ ) . We demonstrate empirically that naively applying momentum to a stochastic method, does not result in acceleration. We perform a novel, tight variance analysis that reveals the "breaking-point variance" beyond which this acceleration does not occur. By combining this insight with modern variance reduction techniques, we construct stochastic PCA algorithms, for the online and offline setting, that achieve an accelerated iteration complexity O ( 1 / Δ ) . Due to the embarassingly parallel nature of our methods, this acceleration translates directly to wall-clock time if deployed in a parallel environment. Our approach is very general, and applies to many non-convex optimization problems that can now be accelerated using the same technique.
Learning Generative Models with Locally Disentangled Latent Factors
Deep Learning @15 Petaflops/second: Semi-supervised pattern detection for 15 Terabytes of climate data
W. Collins
M. Wehner
M. Prabhat
Thorsten Kurth
Nadathur Satish
Jie Zhang
Evan Racah
Md. Mostofa Ali Patwary
Narayanan Sundaram
Pradeep Dubey