Alert button
Picture for Ioannis Mitliagkas

Ioannis Mitliagkas

Alert button

A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods

Oct 03, 2022
Tiago Salvador, Kilian Fatras, Ioannis Mitliagkas, Adam Oberman

Figure 1 for A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods
Figure 2 for A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods
Figure 3 for A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods
Figure 4 for A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods
Viaarxiv icon

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

Sep 29, 2022
Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti, Ioannis Mitliagkas, Murat A. Erdogdu

Figure 1 for Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
Figure 2 for Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
Viaarxiv icon

Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation

Jun 22, 2022
Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas

Figure 1 for Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Figure 2 for Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Figure 3 for Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Figure 4 for Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Viaarxiv icon

A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games

Jun 12, 2022
Samuel Sokota, Ryan D'Orazio, J. Zico Kolter, Nicolas Loizou, Marc Lanctot, Ioannis Mitliagkas, Noam Brown, Christian Kroer

Figure 1 for A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Figure 2 for A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Figure 3 for A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Figure 4 for A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Viaarxiv icon

Towards efficient representation identification in supervised learning

Apr 10, 2022
Kartik Ahuja, Divyat Mahajan, Vasilis Syrgkanis, Ioannis Mitliagkas

Figure 1 for Towards efficient representation identification in supervised learning
Figure 2 for Towards efficient representation identification in supervised learning
Figure 3 for Towards efficient representation identification in supervised learning
Figure 4 for Towards efficient representation identification in supervised learning
Viaarxiv icon

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

Nov 01, 2021
Ryan D'Orazio, Nicolas Loizou, Issam Laradji, Ioannis Mitliagkas

Figure 1 for Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize
Figure 2 for Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize
Figure 3 for Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize
Figure 4 for Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize
Viaarxiv icon

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

Oct 20, 2021
Manuela Girotti, Ioannis Mitliagkas, Gauthier Gidel

Figure 1 for Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks
Figure 2 for Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks
Figure 3 for Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks
Figure 4 for Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks
Viaarxiv icon

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

Jun 30, 2021
Nicolas Loizou, Hugo Berard, Gauthier Gidel, Ioannis Mitliagkas, Simon Lacoste-Julien

Figure 1 for Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
Figure 2 for Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
Figure 3 for Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
Figure 4 for Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
Viaarxiv icon

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

Jun 11, 2021
Kartik Ahuja, Ethan Caballero, Dinghuai Zhang, Yoshua Bengio, Ioannis Mitliagkas, Irina Rish

Figure 1 for Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Figure 2 for Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Figure 3 for Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Figure 4 for Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Viaarxiv icon

Gotta Go Fast When Generating Data with Score-Based Models

May 28, 2021
Alexia Jolicoeur-Martineau, Ke Li, Rémi Piché-Taillefer, Tal Kachman, Ioannis Mitliagkas

Figure 1 for Gotta Go Fast When Generating Data with Score-Based Models
Figure 2 for Gotta Go Fast When Generating Data with Score-Based Models
Figure 3 for Gotta Go Fast When Generating Data with Score-Based Models
Figure 4 for Gotta Go Fast When Generating Data with Score-Based Models
Viaarxiv icon