Ioannis Mitliagkas

verfied profile

∙

0 followers

∙

The University of Texas at Austin

∙

Université de Montréal

∙

Montréal Institute of Learning Algorithms

∙

Stanford University

I work on topics in optimization, dynamics and learning, with a focus on modern machine learning. I have done work in the intersection of systems and theory. Some recent topics:

- Min-max optimization and the dynamics of games

- Generalization and domain adaptation

- Optimization for deep learning

- Statistical learning and inference

research

∙ 04/10/2022

Towards efficient representation identification in supervised learning

Humans have a remarkable ability to disentangle complex sensory inputs (...

Kartik Ahuja, et al. ∙

research

∙ 10/28/2021

Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize

We investigate the convergence of stochastic mirror descent (SMD) in rel...

Ryan D'Orazio, et al. ∙

research

∙ 10/20/2021

Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks

We theoretically analyze the Feedback Alignment (FA) algorithm, an effic...

Manuela Girotti, et al. ∙

research

∙ 06/30/2021

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

Two of the most prominent algorithms for solving unconstrained smooth ga...

Nicolas Loizou, et al. ∙

research

∙ 06/11/2021

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization

The invariance principle from causality is at the heart of notable appro...

Kartik Ahuja, et al. ∙

research

∙ 05/28/2021

Gotta Go Fast When Generating Data with Score-Based Models

Score-based (denoising diffusion) generative models have recently gained...

Alexia Jolicoeur-Martineau, et al. ∙

research

∙ 12/10/2020

A Study of Condition Numbers for First-Order Optimization

The study of first-order optimization algorithms (FOA) typically starts ...

Charles Guille-Escuret, et al. ∙

research

∙ 10/26/2020

LEAD: Least-Action Dynamics for Min-Max Optimization

Adversarial formulations such as generative adversarial networks (GANs) ...

Reyhane Askari Hemmat, et al. ∙

research

∙ 10/22/2020

In Search of Robust Measures of Generalization

One of the principal scientific challenges in deep learning is explainin...

Gintare Karolina Dziugaite, et al. ∙

research

∙ 09/11/2020

Adversarial score matching and improved sampling for image generation

Denoising score matching with Annealed Langevin Sampling (DSM-ALS) is a ...

Alexia Jolicoeur-Martineau, et al. ∙

research

∙ 07/08/2020

Stochastic Hamiltonian Gradient Methods for Smooth Games

The success of adversarial formulations in machine learning has brought ...

Nicolas Loizou, et al. ∙

research

∙ 01/02/2020

Accelerating Smooth Games by Manipulating Spectral Shapes

We use matrix iteration theory to characterize acceleration in smooth ga...

Waïss Azizian, et al. ∙

research

∙ 11/03/2019

Adversarial target-invariant representation learning for domain generalization

In many applications of machine learning, the training and test set data...

Isabela Albuquerque, et al. ∙

research

∙ 10/15/2019

Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs

We generalize the concept of maximum-margin classifiers (MMCs) to arbitr...

Alexia Jolicoeur-Martineau, et al. ∙

research

∙ 06/17/2019

Lower Bounds and Conditioning of Differentiable Games

Many recent machine learning tools rely on differentiable game formulati...

Adam Ibrahim, et al. ∙

research

∙ 06/13/2019

A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games

We consider differentiable games: multi-objective minimization problems,...

Waïss Azizian, et al. ∙

research

∙ 06/08/2019

Reducing the variance in online optimization by transporting past gradients

Most stochastic optimization methods use gradients once before discardin...

Sébastien M. R. Arnold, et al. ∙

research

∙ 05/26/2019

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations

Machine learning promises methods that generalize well from finite label...

Alex Lamb, et al. ∙

research

∙ 03/29/2019

SysML: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoptio...

Alexander Ratner, et al. ∙

research

∙ 01/24/2019

Multi-objective training of Generative Adversarial Networks with multiple discriminators

Recent literature has demonstrated promising results for training Genera...

Isabela Albuquerque, et al. ∙

research

∙ 10/19/2018

A Modern Take on the Bias-Variance Tradeoff in Neural Networks

We revisit the bias-variance tradeoff for neural networks in light of mo...

Brady Neal, et al. ∙

research

∙ 10/06/2018

h-detach: Modifying the LSTM Gradient Towards Better Optimization

Recurrent neural networks are known for their notorious exploding and va...

Devansh Arpit, et al. ∙

research

∙ 07/12/2018

Negative Momentum for Improved Game Dynamics

Games generalize the optimization paradigm by introducing different obje...

Gauthier Gidel, et al. ∙

research

∙ 04/07/2018

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 impor...

Alex Lamb, et al. ∙

research

∙ 08/17/2017

Deep Learning at 15PF: Supervised and Semi-Supervised Classification for Scientific Data

This paper presents the first, 15-PetaFLOP Deep Learning system for solv...

Thorsten Kurth, et al. ∙

research

∙ 07/18/2017

Improving Gibbs Sampler Scan Quality with DoGS

The pairwise influence matrix of Dobrushin has long been used as an anal...

Ioannis Mitliagkas, et al. ∙

research

∙ 07/10/2017

Accelerated Stochastic Power Iteration

Principal component analysis (PCA) is one of the most powerful tools in ...

Christopher De Sa, et al. ∙

research

∙ 07/08/2017

Learning Representations and Generative Models for 3D Point Clouds

Three-dimensional geometric data offer an excellent domain for studying ...

Panos Achlioptas, et al. ∙

research

∙ 06/12/2017

YellowFin and the Art of Momentum Tuning

Hyperparameter tuning is one of the big costs of deep learning. State-of...

Jian Zhang, et al. ∙

research

∙ 06/23/2016

Parallel SGD: When does averaging help?

Consider a number of workers running SGD independently on the same pool ...

Jian Zhang, et al. ∙

research

∙ 06/10/2016

Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much

Gibbs sampling is a Markov Chain Monte Carlo sampling technique that ite...

Bryan He, et al. ∙

research

∙ 05/31/2016

Asynchrony begets Momentum, with an Application to Deep Learning

Asynchronous methods are widely used in deep learning, but have limited ...

Ioannis Mitliagkas, et al. ∙

research

∙ 06/28/2013

Memory Limited, Streaming PCA

We consider streaming, one-pass principal component analysis (PCA), in t...

Ioannis Mitliagkas, et al. ∙

Ioannis Mitliagkas

Featured Co-authors